1
|
Ye K, Zhang L, Zhou H, Mo X, Shi C. Machine learning-based radiomic features of perivascular adipose tissue in coronary computed tomography angiography predicting inflammation status around atherosclerotic plaque: a retrospective cohort study. Ann Med 2025; 57:2431606. [PMID: 39665384 PMCID: PMC11639068 DOI: 10.1080/07853890.2024.2431606] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 05/15/2024] [Revised: 10/23/2024] [Accepted: 10/24/2024] [Indexed: 12/13/2024] Open
Abstract
OBJECTIVES This study expolored the relationship between perivascular adipose tissue (PVAT) radiomic features derived from coronary computed tomography angiography (CCTA) and the presence of coronary artery plaques. It aimed to determine whether PVAT radiomic could non-invasively assess vascular inflammation associated with plaque presence. METHODS In this retrospective cohort study, data from patients undergoing coronary artery examination between May 2021 and December 2022 were analyzed. Demographics, clinical data, plaque location and stenosis severity were recorded. PVAT radiomic features were extracted using PyRadiomics with key features selected using Least Absolute Shrinkage and Selection Operator (LASSO) and recursive feature elimination (RFE) to create a radiomics signature (RadScore).Stepwise logistic regression identified clinical predictors. Predictive models (clinical, radiomics-based and combined) were constructed to differentiate plaque-containing segments from normal ones. The final model was presented as a nomogram and evaluated using calibration curves, ROC analysis and decision curve analysis. RESULTS Analysis included 208 coronary segments from 102 patients. The RadScore achieved an Area Under the Curve (AUC) of 0.897 (95% CI: 0.88-0.92) in the training set and 0.717 (95% CI: 0.63-0.81) in the validation set. The combined model (RadScore + Clinic) demonstrated improved performance with an AUC of 0.783 (95% CI: 0.69-0.87) in the validation set and 0.903 (95% CI: 0.83-0.98) in an independent test set. Both RadScore and combined models significantly outperformed the clinical model (p < .001). The nomogram integrating clinical and radiomics features showed robust calibration and discrimination (c-index: 0.825 in training, 0.907 in testing). CONCLUSION CCTA-based PVAT radiomics effectively distinguished coronary artery segments with and without plaques. The combined model and nomogram demostrated clinical utility, offering a novel approach for early diagnosis and risk stratification in coronary heart disease.
Collapse
Affiliation(s)
- Kunlin Ye
- Medical Imaging Center, The First Affiliated Hospital of Jinan University, Guangzhou, China
| | - Lingtao Zhang
- Medical Imaging Center, The First Affiliated Hospital of Jinan University, Guangzhou, China
| | - Hao Zhou
- Medical Imaging Center, The First Affiliated Hospital of Jinan University, Guangzhou, China
| | - Xukai Mo
- Medical Imaging Center, The First Affiliated Hospital of Jinan University, Guangzhou, China
| | - Changzheng Shi
- Medical Imaging Center, The First Affiliated Hospital of Jinan University, Guangzhou, China
- Subingtian center for speed research and training/Guangdong Key Laboratory of speed capability research, School of physical education, Jinan University,Guangzhou, China
| |
Collapse
|
2
|
Zhao KF, Xie CB, Wu Y. Prediction of the efficacy of first transarterial chemoembolization for advanced hepatocellular carcinoma via a clinical-radiomics model. World J Clin Cases 2025; 13:101742. [DOI: 10.12998/wjcc.v13.i23.101742] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/26/2024] [Revised: 03/09/2025] [Accepted: 04/25/2025] [Indexed: 06/04/2025] Open
Abstract
BACKGROUND Hepatocellular carcinoma (HCC) is a common tumor with a poor prognosis. Early intervention is essential; thus, good prognostic markers to identify patients who benefit from first transarterial chemoembolization (TACE) are needed.
AIM To investigate the efficacy of computed tomography (CT) radiomics in predicting the success of the first TACE in patients with advanced HCC and to develop an early prediction model based on clinical radiomics features.
METHODS Data from 122 patients with advanced HCC treated with TACE were analyzed. Intratumoral and peritumoral areas on arterial and venous CT images were selected to extract radiomic features, which were screened in the training cohort using the minimum redundancy maximum correlation. Then, support vector machines were used to construct the model. To construct a receiver operating characteristic curve, the predictive efficacy of each model was evaluated on the basis of the area under the curve (AUC).
RESULTS Among the 122 patients, 72 patients were effectively treated via TACE, and in 50 patients, this treatment was ineffective. In the radiomics model, the areas under the curve of the venous phase model were 0.867 (95%CI: 0.790-0.940) in the training cohort and 0.755 (0.600-0.910) in the validation cohort, indicating good predictive efficacy. The multivariate logistic regression results indicated that preoperative alpha-fetoprotein levels (P = 0.01) were a risk factor for TACE. The screened clinical features were combined with the radiomic features to construct a combined model. This combined model had an AUC of 0.92 (0.87-0.95) in the training cohort and 0.815 (0.67-0.95) in the validation cohort.
CONCLUSION CT radiomics has good value in predicting the efficacy of the first TACE treatment in patients with HCC. The combined model was a better tool for predicting the first TACE efficacy in patients with advanced HCC and could provide an efficient predictive tool to help with the selection of patients for TACE.
Collapse
Affiliation(s)
- Kai-Fei Zhao
- Department of Radiology, The Affiliated Hospital of Zunyi Medical University, Zunyi 563000, Guizhou Province, China
| | - Chao-Bang Xie
- Department of Radiology, The Affiliated Hospital of Guizhou Medical University, Guiyang 563000, Guizhou Province, China
| | - Yang Wu
- Department of Intervention, The Second Affiliated Hospital of Zunyi Medical University, Zunyi 563000, Guizhou Province, China
| |
Collapse
|
3
|
Michalet M, Valenzuela G, Nougaret S, Tardieu M, Azria D, Riou O. Development of Multiparametric Prognostic Models for Stereotactic Magnetic Resonance Guided Radiation Therapy of Pancreatic Cancers. Int J Radiat Oncol Biol Phys 2025; 122:678-689. [PMID: 40185208 DOI: 10.1016/j.ijrobp.2025.03.039] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/20/2024] [Revised: 03/17/2025] [Accepted: 03/19/2025] [Indexed: 04/07/2025]
Abstract
PURPOSE Stereotactic magnetic resonance guided adaptive radiation therapy (SMART) is a new option for local treatment of unresectable pancreatic ductal adenocarcinoma, showing interesting survival and local control (LC) results. Despite this, some patients will experience early local and/or metastatic recurrence leading to death. We aimed to develop multiparametric prognostic models for these patients. METHODS AND MATERIALS All patients treated in our institution with SMART for an unresectable pancreatic ductal adenocarcinoma between October 21, 2019, and August 5, 2022 were included. Several initial clinical characteristics as well as dosimetric data of SMART were recorded. Radiomics data from 0.35-T simulation magnetic resonance imaging were extracted. All these data were combined to build prognostic models of overall survival (OS) and LC using machine learning algorithms. RESULTS Eighty-three patients with a median age of 64.9 years were included. A majority of patients had a locally advanced pancreatic cancer (77%). The median OS was 21 months after SMART completion and 27 months after chemotherapy initiation. The 6- and 12-month post-SMART OS was 87.8% (IC95%, 78.2%-93.2%) and 70.9% (IC95%, 58.8%-80.0%), respectively. The best model for OS was the Cox proportional hazard survival analysis using clinical data, with a concordance index inverse probability of censoring weighted of 0.87. Tested on its 12-month OS prediction capacity, this model had good performance (sensitivity 67%, specificity 71%, and area under the curve 0.90). The median LC was not reached. The 6- and 12-month post-SMART LC was 92.4% [IC95%, 83.7%-96.6%] and 76.3% [IC95%, 62.6%-85.5%], respectively. The best model for LC was the component-wise gradient boosting survival analysis using clinical and radiomics data, with a concordance index inverse probability of censoring weighted of 0.80. Tested on its 9-month LC prediction capacity, this model had good performance (sensitivity 50%, specificity 97%, and area under the curve 0.78). CONCLUSIONS Combining clinical and radiomics data in multiparametric prognostic models using machine learning algorithms showed good performance for the prediction of OS and LC. External validation of these models will be needed.
Collapse
Affiliation(s)
- Morgan Michalet
- University Federation of Radiation Oncology of Mediterranean Occitanie, Montpellier Cancer Institute, Montpellier University, Montpellier, France; Montpellier Cancer Research Institute, Montpellier University, Montpellier, France.
| | - Gladis Valenzuela
- Montpellier Cancer Research Institute, Montpellier University, Montpellier, France
| | - Stéphanie Nougaret
- Montpellier Cancer Research Institute, Montpellier University, Montpellier, France
| | - Marion Tardieu
- Montpellier Cancer Research Institute, Montpellier University, Montpellier, France
| | - David Azria
- University Federation of Radiation Oncology of Mediterranean Occitanie, Montpellier Cancer Institute, Montpellier University, Montpellier, France; University Federation of Radiation Oncology of Mediterranean Occitanie, Institut de Cancérologie du Gard, Centre Hospitalier Universitaire Carémeau, Nîmes, France; Montpellier Cancer Research Institute, Montpellier University, Montpellier, France
| | - Olivier Riou
- University Federation of Radiation Oncology of Mediterranean Occitanie, Montpellier Cancer Institute, Montpellier University, Montpellier, France; Montpellier Cancer Research Institute, Montpellier University, Montpellier, France
| |
Collapse
|
4
|
Ellmann S, von Rohr F, Komina S, Bayerl N, Amann K, Polifka I, Hartmann A, Sikic D, Wullich B, Uder M, Bäuerle T. Tumor grade-titude: XGBoost radiomics paves the way for RCC classification. Eur J Radiol 2025; 188:112146. [PMID: 40334367 DOI: 10.1016/j.ejrad.2025.112146] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/27/2025] [Revised: 04/21/2025] [Accepted: 04/28/2025] [Indexed: 05/09/2025]
Abstract
This study aimed to develop and evaluate a non-invasive XGBoost-based machine learning model using radiomic features extracted from pre-treatment CT images to differentiate grade 4 renal cell carcinoma (RCC) from lower-grade tumours. A total of 102 RCC patients who underwent contrast-enhanced CT scans were included in the analysis. Radiomic features were extracted, and a two-step feature selection methodology was applied to identify the most relevant features for classification. The XGBoost model demonstrated high performance in both training (AUC = 0.87) and testing (AUC = 0.92) sets, with no significant difference between the two (p = 0.521). The model also exhibited high sensitivity, specificity, positive predictive value, and negative predictive value. The selected radiomic features captured both the distribution of intensity values and spatial relationships, which may provide valuable insights for personalized treatment decision-making. Our findings suggest that the XGBoost model has the potential to be integrated into clinical workflows to facilitate personalized adjuvant immunotherapy decision-making, ultimately improving patient outcomes. Further research is needed to validate the model in larger, multicentre cohorts and explore the potential of combining radiomic features with other clinical and molecular data.
Collapse
Affiliation(s)
- Stephan Ellmann
- Institute of Radiology, University Hospital Erlangen, Friedrich-Alexander-Universität (FAU) Erlangen-Nürnberg, Erlangen, Germany; Radiologisch-Nuklearmedizinisches Zentrum (RNZ), Martin-Richter-Straße 43, 90489 Nürnberg, Germany.
| | - Felicitas von Rohr
- Institute of Radiology, University Hospital Erlangen, Friedrich-Alexander-Universität (FAU) Erlangen-Nürnberg, Erlangen, Germany
| | - Selim Komina
- Institute of Pathology, Faculty of Medicine, Ss Cyril and Methodius University ul. 50 Divizija bb 1000 Skopje, North Macedonia
| | - Nadine Bayerl
- Institute of Radiology, University Hospital Erlangen, Friedrich-Alexander-Universität (FAU) Erlangen-Nürnberg, Erlangen, Germany
| | - Kerstin Amann
- Institute of Pathology, University Hospital Erlangen, Friedrich-Alexander-Universität (FAU) Erlangen-Nürnberg, Erlangen, Germany; BZKF: Bavarian Cancer Research Center (BZKF), Erlangen, Germany
| | - Iris Polifka
- Institute of Pathology, University Hospital Erlangen, Friedrich-Alexander-Universität (FAU) Erlangen-Nürnberg, Erlangen, Germany; Humanpathologie Dr. Weiß MVZ GmbH, Am Weichselgarten 30a, 91058 Erlangen-Tennenlohe, Germany
| | - Arndt Hartmann
- Institute of Pathology, University Hospital Erlangen, Friedrich-Alexander-Universität (FAU) Erlangen-Nürnberg, Erlangen, Germany; Comprehensive Cancer Center Erlangen - EMD, Friedrich-Alexander-Universität (FAU) Erlangen-Nürnberg, Erlangen, Germany; BZKF: Bavarian Cancer Research Center (BZKF), Erlangen, Germany
| | - Danijel Sikic
- Clinic of Urology and Pediatric Urology, University Hospital Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg, 91054 Erlangen, Germany; BZKF: Bavarian Cancer Research Center (BZKF), Erlangen, Germany
| | - Bernd Wullich
- Clinic of Urology and Pediatric Urology, University Hospital Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg, 91054 Erlangen, Germany; Comprehensive Cancer Center Erlangen - EMD, Friedrich-Alexander-Universität (FAU) Erlangen-Nürnberg, Erlangen, Germany; BZKF: Bavarian Cancer Research Center (BZKF), Erlangen, Germany
| | - Michael Uder
- Institute of Radiology, University Hospital Erlangen, Friedrich-Alexander-Universität (FAU) Erlangen-Nürnberg, Erlangen, Germany; Comprehensive Cancer Center Erlangen - EMD, Friedrich-Alexander-Universität (FAU) Erlangen-Nürnberg, Erlangen, Germany; BZKF: Bavarian Cancer Research Center (BZKF), Erlangen, Germany
| | - Tobias Bäuerle
- Institute of Radiology, University Hospital Erlangen, Friedrich-Alexander-Universität (FAU) Erlangen-Nürnberg, Erlangen, Germany; University Medical Center of Johannes Gutenberg-University Mainz, Department of Diagnostic and Interventional Radiology, Langenbeckstr. 1, 55131 Mainz, Germany
| |
Collapse
|
5
|
Kleiburg F, de Geus-Oei LF, Spijkerman R, Noortman WA, van Velden FHP, Manohar S, Smit F, Toonen FAJ, Luelmo SAC, van der Hulle T, Heijmen L. Baseline PSMA PET/CT parameters predict overall survival and treatment response in metastatic castration-resistant prostate cancer patients. Eur Radiol 2025; 35:4223-4232. [PMID: 39843627 DOI: 10.1007/s00330-025-11360-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/12/2024] [Revised: 12/01/2024] [Accepted: 12/13/2024] [Indexed: 01/24/2025]
Abstract
OBJECTIVE Metastatic castration-resistant prostate cancer (mCRPC) is a heterogeneous disease with varying survival outcomes. This study investigated whether baseline PSMA PET/CT parameters are associated with survival and treatment response. METHODS Sixty mCRPC patients underwent [18F]PSMA-1007 PET/CT before treatment with androgen receptor-targeted agents (ARTAs) or chemotherapy. Intensity-based parameters, volumetric parameters, metastatic sites and DmaxVox (distance between the two outermost voxels) from baseline PSMA PET/CT were collected, as well as age, Gleason score and laboratory parameters. Cox regression analysis evaluated their prognostic value for overall survival (OS). Additionally, a preliminary lesion-level analysis was done (n = 241 lesions) with lesion location and twelve radiomic features selected from previous literature. Logistic regression evaluated their association with PSMA PET/CT-based lesion progression after 3-4 months of treatment. RESULTS Total tumour volume (PSMA-TV) (HR = 1.41 per doubling [1.17-1.70]), total lesion uptake (TL-PSMA) (HR = 1.40 per doubling [1.16-1.69]) and DmaxVox (HR = 1.31 per 10 cm increase [1.07-1.62]) were prognostic for OS, each independent of baseline PSA level (HR = 0.82 per doubling [0.68-0.98]), haemoglobin level (HR = 0.68 per mmol/L increase [0.49-0.95]) and line of treatment. On lesion-level, location (prostate vs bone OR = 0.23 [0.06-0.83]) and SUVmean (OR = 1.72 per doubling [1.08-2.75]) were independent prognostic markers for lesion progression, morphological and texture-based radiomic features were not. CONCLUSION Baseline PSMA PET/CT scans have prognostic value in mCRPC patients and can potentially aid in treatment decision-making. DmaxVox can serve as a simpler alternative to PSMA-TV when automated segmentation software is not available. When combined with PSMA-TV, lower PSA levels indicated worse OS, which may be a marker of tumour dedifferentiation. Further research is needed to validate these models in larger patient cohorts. KEY POINTS Question mCRPC is a highly heterogeneous disease, requiring good prognostic markers. Findings PSMA-TV was the best independent prognostic marker for OS; maximum distance between lesions (DmaxVox) can be used as a simpler alternative. Clinical relevance Baseline PSMA PET/CT parameters representing tumour burden were independently associated with OS in mCRPC patients, providing prognostic insights for clinical decision-making. Although PSMA-TV was the best prognostic marker, DmaxVox can serve as an easier to obtain alternative.
Collapse
Affiliation(s)
- Fleur Kleiburg
- Biomedical Photonic Imaging Group, University of Twente, Enschede, The Netherlands.
- Department of Radiology, Section of Nuclear Medicine, Leiden University Medical Center, Leiden, The Netherlands.
| | - Lioe-Fee de Geus-Oei
- Biomedical Photonic Imaging Group, University of Twente, Enschede, The Netherlands
- Department of Radiology, Section of Nuclear Medicine, Leiden University Medical Center, Leiden, The Netherlands
- Department of Radiation Science & Technology, Delft University of Technology, Delft, The Netherlands
| | - Romy Spijkerman
- Department of Radiology, Section of Nuclear Medicine, Leiden University Medical Center, Leiden, The Netherlands
| | - Wyanne A Noortman
- Biomedical Photonic Imaging Group, University of Twente, Enschede, The Netherlands
- Department of Radiology, Section of Nuclear Medicine, Leiden University Medical Center, Leiden, The Netherlands
| | - Floris H P van Velden
- Department of Radiology, Section of Nuclear Medicine, Leiden University Medical Center, Leiden, The Netherlands
| | - Srirang Manohar
- Multi-Modality Medical Imaging, University of Twente, Enschede, The Netherlands
| | - Frits Smit
- Department of Nuclear Medicine, Alrijne Hospital, Leiderdorp, The Netherlands
| | - Frank A J Toonen
- Department of Oncology, Alrijne Hospital, Leiderdorp, The Netherlands
| | - Saskia A C Luelmo
- Department of Medical Oncology, Leiden University Medical Center, Leiden, The Netherlands
| | - Tom van der Hulle
- Department of Medical Oncology, Leiden University Medical Center, Leiden, The Netherlands
| | - Linda Heijmen
- Department of Radiology, Section of Nuclear Medicine, Leiden University Medical Center, Leiden, The Netherlands
| |
Collapse
|
6
|
Bruixola G, Dualde-Beltrán D, Jimenez-Pastor A, Nogué A, Bellvís F, Fuster-Matanzo A, Alfaro-Cervelló C, Grimalt N, Salhab-Ibáñez N, Escorihuela V, Iglesias ME, Maroñas M, Alberich-Bayarri Á, Cervantes A, Tarazona N. CT-based clinical-radiomics model to predict progression and drive clinical applicability in locally advanced head and neck cancer. Eur Radiol 2025; 35:4277-4288. [PMID: 39706922 DOI: 10.1007/s00330-024-11301-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/30/2024] [Revised: 10/19/2024] [Accepted: 11/17/2024] [Indexed: 12/23/2024]
Abstract
BACKGROUND Definitive chemoradiation is the primary treatment for locally advanced head and neck carcinoma (LAHNSCC). Optimising outcome predictions requires validated biomarkers, since TNM8 and HPV could have limitations. Radiomics may enhance risk stratification. METHODS This single-centre observational study collected clinical data and baseline CT scans from 171 LAHNSCC patients treated with chemoradiation. The dataset was divided into training (80%) and test (20%) sets, with a 5-fold cross-validation on the training set. Researchers extracted 108 radiomics features from each primary tumour and applied survival analysis and classification models to predict progression-free survival (PFS) and 5-year progression, respectively. Performance was evaluated using inverse probability of censoring weights and c-index for the PFS model and AUC, sensitivity, specificity, and accuracy for the 5-year progression model. Feature importance was measured by the SHapley Additive exPlanations (SHAP) method and patient stratification was assessed through Kaplan-Meier curves. RESULTS The final dataset included 171 LAHNSCC patients, with 53% experiencing disease progression at 5 years. The random survival forest model best predicted PFS, with an AUC of 0.64 and CI of 0.66 on the test set, highlighting 4 radiomics features and TNM8 as significant contributors. It successfully stratified patients into low and high-risk groups (log-rank p < 0.005). The extreme gradient boosting model most effectively predicted a 5-year progression, incorporating 12 radiomics features and four clinical variables, achieving an AUC of 0.74, sensitivity of 0.53, specificity of 0.81, and accuracy of 0.66 on the test set. CONCLUSION The combined clinical-radiomics model improved the standard TNM8 and clinical variables in predicting 5-year progression though further validation is necessary. KEY POINTS Question There is an unmet need for non-invasive biomarkers to guide treatment in locally advanced head and neck cancer. Findings Clinical data (TNM8 staging, primary tumour site, age, and smoking) plus radiomics improved 5-year progression prediction compared with the clinical comprehensive model or TNM staging alone. Clinical relevance SHAP simplifies complex machine learning radiomics models for clinicians by using easy-to-understand graphical representations, promoting explainability.
Collapse
Affiliation(s)
- Gema Bruixola
- Medical Oncology Department, Hospital Clinico Universitario de Valencia-INCLIVA Biomedical Research Institute, University of Valencia, Valencia, Spain
| | - Delfina Dualde-Beltrán
- Radiology Department, Hospital Clinico Universitario de Valencia, University of Valencia, Valencia, Spain
| | | | - Anna Nogué
- Quibim-Quantitative Imaging Biomarkers in Medicine, Valencia, Spain
| | | | | | - Clara Alfaro-Cervelló
- Pathology Department, Hospital Clinico Universitario de Valencia-INCLIVA Instituto de Investigación Sanitaria, University of Valencia, Valencia, Spain
| | - Nuria Grimalt
- Medical Oncology Department, Hospital Clinico Universitario de Valencia-INCLIVA Biomedical Research Institute, University of Valencia, Valencia, Spain
| | - Nader Salhab-Ibáñez
- Radiology Department, Hospital Clinico Universitario de Valencia, University of Valencia, Valencia, Spain
| | - Vicente Escorihuela
- Otorhinolaryngology Department, Hospital Clinico Universitario de Valencia, Valencia, Spain
| | - María Eugenia Iglesias
- Oral and Maxillary Surgery Department, Hospital Clinico Universitario de Valencia, Valencia, Spain
| | - María Maroñas
- Radiation Oncology Department, Hospital Clinico Universitario de Valencia, Valencia, Spain
| | | | - Andrés Cervantes
- Medical Oncology Department, Hospital Clinico Universitario de Valencia-INCLIVA Biomedical Research Institute, University of Valencia, Valencia, Spain.
- Instituto de Salud Carlos III, CIBERONC, Madrid, Spain.
| | - Noelia Tarazona
- Medical Oncology Department, Hospital Clinico Universitario de Valencia-INCLIVA Biomedical Research Institute, University of Valencia, Valencia, Spain.
- Instituto de Salud Carlos III, CIBERONC, Madrid, Spain.
| |
Collapse
|
7
|
Wang X, Wang X, Xu Y, Yan Z, Shi Z, Liu Y, Liu X, Li Y. Radiomics-based analysis of choroid plexus abnormalities in neuromyelitis optica spectrum disorders and multiple sclerosis and their clinical implications. Mult Scler Relat Disord 2025; 99:106465. [PMID: 40306094 DOI: 10.1016/j.msard.2025.106465] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/31/2024] [Revised: 04/21/2025] [Accepted: 04/22/2025] [Indexed: 05/02/2025]
Abstract
BACKGROUND The choroid plexus (CP) is closely linked to inflammation in multiple sclerosis (MS). While the CP volume is enlarged in MS compared with healthy controls (HC), no such changes are observed in neuromyelitis optica spectrum disorder (NMOSD), a disease with similar clinical and imaging features to MS. It remains unclear whether the CP plays a similar role in NMOSD as in MS. PURPOSE To investigate the abnormal CP radiomics in NMOSD and MS and explore their clinical implications. METHODS This retrospective study included 111 MS, 69 Aquaporin-4 (AQP4)-IgG positive NMOSD, and 82 HC, with age and sex matching. Radiomics features of the CP were extracted from T1-weighted images after automated segmentation, including shape, first order statistics (intensity), and texture features (N=1051). Analysis of covariance was used to assess group differences in these features, and 11 classic machine learning algorithms were employed to construct disease classification models. Moreover, partial correlation analysis was performed to further explore the relationships between differential radiomics features and clinical measures, such as Expanded Disability Status Scale (EDSS) and Symbol Digit Modalities Test (SDMT). RESULTS Compared with HC, MS exhibited significant differences in 453 features, including shape, intensity, and texture, while NMOSD displayed differences in 102 intensity and texture features, with no differences in shape. NMOSD and MS differed in 178 features, primarily texture (P < 0.05, Bonferroni correction). In the classification models based on CP radiomics features, the best AUC for MS vs HC was 0.935 (95% CI: 0.830 - 0.997) with the Partial Least Squares Regression Generalized Linear Model (plsRglm), while for NMOSD vs HC, it was 0.822 (95% CI: 0.629 - 0.962) with the Light Gradient Boosting Machine (LightGBM). Meanwhile, the best AUC for NMOSD vs MS was 0.832 (95% CI: 0.667 - 0.960) with the Quadratic Discriminant Analysis (QDA). Furthermore, of the 453 abnormal radiomics features of MS patients, 120 were significantly correlated with EDSS and 234 with SDMT scores (P < 0.05, FDR correction), while no radiomics features in NMOSD were significantly correlated with clinical scores (P > 0.05, FDR correction). CONCLUSION Radiomics can detect varying degrees of CP abnormalities in NMOSD and MS, suggesting CP involvement in the pathophysiology of NMOSD, albeit to a lesser extent than in MS. It may help understand the potential pathophysiological differences between the two diseases and their impact on clinical monitoring.
Collapse
Affiliation(s)
- Xiaohua Wang
- Department of Radiology, The First Affiliated Hospital of Chongqing Medical University, Chongqing, 400016, China; College of Medical Informatics, Chongqing Medical University, Chongqing, 400016, China
| | - Xiaolong Wang
- College of Computer and Information Science, Southwest University, Chongqing, 400715, China
| | - Yuhui Xu
- Department of Radiology, The First Affiliated Hospital of Chongqing Medical University, Chongqing, 400016, China
| | - Zichun Yan
- Department of Radiology, The First Affiliated Hospital of Chongqing Medical University, Chongqing, 400016, China
| | - Zhuowei Shi
- Department of Radiology, The First Affiliated Hospital of Chongqing Medical University, Chongqing, 400016, China
| | - Yanbing Liu
- College of Medical Informatics, Chongqing Medical University, Chongqing, 400016, China
| | - Xiaojuan Liu
- School of Artificial Intelligence, Chongqing University of Technology, Chongqing, 400054, China.
| | - Yongmei Li
- Department of Radiology, The First Affiliated Hospital of Chongqing Medical University, Chongqing, 400016, China.
| |
Collapse
|
8
|
Huang S, Liu D, Deng K, Shu C, Wu Y, Zhou Z. A computed tomography angiography-based radiomics model for prognostic prediction of endovascular abdominal aortic repair. Int J Cardiol 2025; 429:133138. [PMID: 40090490 DOI: 10.1016/j.ijcard.2025.133138] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/21/2025] [Revised: 02/25/2025] [Accepted: 03/06/2025] [Indexed: 03/18/2025]
Abstract
OBJECTIVE This study aims to develop a radiomics machine learning (ML) model that uses preoperative computed tomography angiography (CTA) data to predict the prognosis of endovascular aneurysm repair (EVAR) for abdominal aortic aneurysm (AAA) patients. METHODS In this retrospective study, 164 AAA patients underwent EVAR and were categorized into shrinkage (good prognosis) or stable (poor prognosis) groups based on post-EVAR sac regression. From preoperative AAA and perivascular adipose tissue (PVAT) image, radiomics features (RFs) were extracted for model creation. Patients were split into 80 % training and 20 % test sets. A support vector machine model was constructed for prediction. Accuracy is evaluated via the area under the receiver operating characteristic curve (AUC). RESULTS Demographics and comorbidities showed no significant differences between shrinkage and stable groups. The model containing 5 AAA RFs (which are original_firstorder_InterquartileRange, log-sigma-3-0-mm-3D_glrlm_GrayLevelNonUniformityNormalized, log-sigma-3-0-mm-3D_glrlm_RunPercentage, log-sigma-4-0-mm-3D_glrlm_ShortRunLowGrayLevelEmphasis, wavelet-LLH_glcm_SumEntropy) had AUCs of 0.86 (training) and 0.77 (test). The model containing 7 PVAT RFs (which are log-sigma-3-0-mm-3D_firstorder_InterquartileRange, log-sigma-3-0-mm-3D_glcm_Correlation, wavelet-LHL_firstorder_Energy, wavelet-LHL_firstorder_TotalEnergy, wavelet-LHH_firstorder_Mean, wavelet-LHH_glcm_Idmn, wavelet-LHH_glszm_GrayLevelNonUniformityNormalized) had AUCs of 0.76 (training) and 0.78 (test). Combining AAA and PVAT RFs yielded the highest accuracy: AUCs of 0.93 (training) and 0.87 (test). CONCLUSIONS Radiomics-based CTA model predicts aneurysm sac regression post-EVAR in AAA patients. PVAT RFs from preoperative CTA images were closely related to AAA prognosis after EVAR, enhancing accuracy when combined with AAA RFs. This preliminary study explores a predictive model designed to assist clinicians in optimizing therapeutic strategies during clinical decision-making processes.
Collapse
Affiliation(s)
- Shanya Huang
- National Clinical Research Center for Metabolic Diseases, Metabolic Syndrome Research Center, and Department of Metabolism and Endocrinology, The Second Xiangya Hospital of Central South University, 139 Middle Renmin Road, Changsha, 410011, Hunan, China; Department of Ultrasound, The Second Xiangya Hospital, Central South University, Changsha 410011, China
| | - Dingxiao Liu
- Department of Vascular Surgery, The Second Xiangya Hospital of Central South University, Changsha 410011, Hunan, China
| | - Kai Deng
- Department of Radiology, The Second Xiangya Hospital, Central South University, Changsha, Hunan, China
| | - Chang Shu
- Department of Vascular Surgery, The Second Xiangya Hospital of Central South University, Changsha 410011, Hunan, China; Fuwai Hospital, National Center for Cardiovascular Disease, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China.
| | - Yan Wu
- National Clinical Research Center for Metabolic Diseases, Metabolic Syndrome Research Center, and Department of Metabolism and Endocrinology, The Second Xiangya Hospital of Central South University, 139 Middle Renmin Road, Changsha, 410011, Hunan, China.
| | - Zhiguang Zhou
- National Clinical Research Center for Metabolic Diseases, Metabolic Syndrome Research Center, and Department of Metabolism and Endocrinology, The Second Xiangya Hospital of Central South University, 139 Middle Renmin Road, Changsha, 410011, Hunan, China.
| |
Collapse
|
9
|
Xu J, Wang T, Li J, Wang Y, Zhu Z, Fu X, Wang J, Zhang Z, Cai W, Song R, Hou C, Yang LZ, Wang H, Wong STC, Li H. A multimodal fusion system predicting survival benefits of immune checkpoint inhibitors in unresectable hepatocellular carcinoma. NPJ Precis Oncol 2025; 9:185. [PMID: 40517171 DOI: 10.1038/s41698-025-00979-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/31/2024] [Accepted: 05/27/2025] [Indexed: 06/16/2025] Open
Abstract
Early identification of unresectable hepatocellular carcinoma (HCC) patients who may benefit from immune checkpoint inhibitors (ICIs) is crucial for optimizing outcomes. Here, we developed a multimodal fusion (MMF) system integrating CT-derived deep learning features and clinical data to predict overall survival (OS) and progression-free survival (PFS). Using retrospective multicenter data (n = 859), the MMF combining an ensemble deep learning (Ensemble-DL) model with clinical variables achieved strong external validation performance (C-index: OS = 0.74, PFS = 0.69), outperforming radiomics (29.8% OS improvement), mRECIST (27.6% OS improvement), clinical benchmarks (C-index: OS = 0.67, p = 0.0011; PFS = 0.65, p = 0.033), and Ensemble-DL (C-index: OS = 0.69, p = 0.0028; PFS = 0.66, p = 0.044). The MMF system effectively stratified patients across clinical subgroups and demonstrated interpretability through activation maps and radiomic correlations. Differential gene expression analysis revealed enrichment of the PI3K/Akt pathway in patients identified by the MMF system. The MMF system provides an interpretable, clinically applicable approach to guide personalized ICI treatment in unresectable HCC.
Collapse
Affiliation(s)
- Jun Xu
- Hefei Cancer Hospital of CAS, Institute of Health and Medical Technology, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei, P. R. China
- University of Science and Technology of China, Hefei, P. R. China
- Department of Oncology, Hefei Cancer Hospital; Chinese Academy of Sciences, Hefei, P. R. China
- Department of Interventional Radiology, The First Affiliated Hospital of USTC, Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei, P. R. China
| | - Tengfei Wang
- Hefei Cancer Hospital of CAS, Institute of Health and Medical Technology, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei, P. R. China
- University of Science and Technology of China, Hefei, P. R. China
- Department of Oncology, Hefei Cancer Hospital; Chinese Academy of Sciences, Hefei, P. R. China
| | - Junjun Li
- Department of Radiology, The First Affiliated Hospital of University of Science and Technology of China, Hefei, P. R. China
| | - Yong Wang
- Department of Radiology, The First Affiliated Hospital of Wannan Medical College (Yijishan Hospital of Wannan Medical College), Wuhu, P. R. China
| | - Zhangxiang Zhu
- Department of Radiology, The First Affiliated Hospital of Anhui Medical University, Hefei, P. R. China
| | - Xiao Fu
- Hefei Cancer Hospital of CAS, Institute of Health and Medical Technology, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei, P. R. China
- Department of Oncology, Hefei Cancer Hospital; Chinese Academy of Sciences, Hefei, P. R. China
| | - Junjie Wang
- Hefei Cancer Hospital of CAS, Institute of Health and Medical Technology, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei, P. R. China
- University of Science and Technology of China, Hefei, P. R. China
| | - Zhenglin Zhang
- Hefei Cancer Hospital of CAS, Institute of Health and Medical Technology, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei, P. R. China
- University of Science and Technology of China, Hefei, P. R. China
| | - Wei Cai
- Department of Hepatobiliary Surgery, The First Affiliated Hospital of USTC, Division of Life Sciences and Medicine, the University of Science and Technology of China, Anhui Province Key Laboratory of Hepatopancreatobiliary Surgery, Anhui Provincial Clinical Research Center for Hepatobiliary Diseases, Hefei, P. R. China
| | - Ruipeng Song
- Department of Hepatobiliary Surgery, The First Affiliated Hospital of USTC, Division of Life Sciences and Medicine, the University of Science and Technology of China, Anhui Province Key Laboratory of Hepatopancreatobiliary Surgery, Anhui Provincial Clinical Research Center for Hepatobiliary Diseases, Hefei, P. R. China
| | - Changlong Hou
- Department of Interventional Radiology, The First Affiliated Hospital of USTC, Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei, P. R. China
| | - Li-Zhuang Yang
- Hefei Cancer Hospital of CAS, Institute of Health and Medical Technology, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei, P. R. China
- University of Science and Technology of China, Hefei, P. R. China
- Department of Oncology, Hefei Cancer Hospital; Chinese Academy of Sciences, Hefei, P. R. China
| | - Hongzhi Wang
- Hefei Cancer Hospital of CAS, Institute of Health and Medical Technology, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei, P. R. China
- University of Science and Technology of China, Hefei, P. R. China
- Department of Oncology, Hefei Cancer Hospital; Chinese Academy of Sciences, Hefei, P. R. China
| | - Stephen T C Wong
- Department of Systems Medicine and Bioengineering, Houston Methodist Neal Cancer Center, Houston Methodist Hospital, Houston, TX, USA.
- Department of Radiology, Weill Cornell Medical College, New York, NY, USA.
| | - Hai Li
- Hefei Cancer Hospital of CAS, Institute of Health and Medical Technology, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei, P. R. China.
- University of Science and Technology of China, Hefei, P. R. China.
- Department of Oncology, Hefei Cancer Hospital; Chinese Academy of Sciences, Hefei, P. R. China.
| |
Collapse
|
10
|
Kamel S, Humbert-Vidan L, Kaffey Z, Mirbahaeddin S, Abusaif A, Fuentes DTA, Wahid K, Dede C, Naser MA, He R, Moawad AW, Elsayes KM, Chen MM, Otun AO, Rigert J, Chambers MS, Hope A, Watson E, Brock KK, Hutcheson K, van Dijk L, Moreno AC, Lai SY, Fuller CD, Mohamed ASR, MD Anderson Head and Neck Cancer Symptom Working Group. Computed tomography radiomics-based cross-sectional detection of mandibular osteoradionecrosis in head and neck cancer survivors. Oral Oncol 2025; 167:107337. [PMID: 40516152 DOI: 10.1016/j.oraloncology.2025.107337] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/16/2024] [Revised: 04/22/2025] [Accepted: 04/23/2025] [Indexed: 06/16/2025]
Abstract
PURPOSE This study aims to identify radiomic features from contrast-enhanced CT (CECT) scans that differentiate osteoradionecrosis (ORN) from normal mandibular bone in head and neck cancer (HNC) patients treated with radiotherapy (RT). MATERIALS AND METHODS CECT images from 150 patients with confirmed ORN diagnosis (2008-2018) at MD Anderson Cancer Center (MDACC) were analyzed (80 % train, 20 % test). Radiomic features were extracted using PyRadiomics from manually segmented ORN regions and automated contralateral healthy mandible regions. Correlation analysis (r > 0.95) reduced features for model training. A random Forest (RF) classifier with Recursive Feature Elimination identified discriminative features. Explainability was assessed using SHapley Additive exPlanations (SHAP) analysis on the 20 most important features identified by the trained RF classifier. RESULTS Of the 1316 radiomic features extracted, 810 features were excluded for high collinearity. From a set of 506 pre-selected radiomic features, 67 were optimal for RF classification, yielding 88% accuracy and a ROC AUC of 0.96. The model well calibrated (Log Loss 0.296, ECE 0.125) and achieved an accuracy of 88% and a ROC AUC of 0.96. The SHAP analysis revealed that higher values of Wavelet-LLH First order Mean and Median were associated with ORN of the jaw (ORNJ). Conversely, higher Exponential GLDM Dependence Entropy and lower Square First-order Kurtosis were more characteristic of normal mandibular tissue. CONCLUSION This study successfully developed a CECT-based radiomics model for differentiating ORNJ from healthy mandibular tissue in HNC patients after RT. Future work will focus on detecting subclinical ORNJ regions to guide earlier interventions.
Collapse
Affiliation(s)
- Serageldin Kamel
- The University of Texas MD Anderson Cancer Center, Department of Radiation Oncology, Houston, USA
| | - Laia Humbert-Vidan
- The University of Texas MD Anderson Cancer Center, Department of Radiation Oncology, Houston, USA
| | - Zaphanlene Kaffey
- The University of Texas MD Anderson Cancer Center, Department of Radiation Oncology, Houston, USA
| | - Sarah Mirbahaeddin
- The University of Texas MD Anderson Cancer Center, Department of Radiation Oncology, Houston, USA
| | - Abdulrahman Abusaif
- The University of Texas MD Anderson Cancer Center, Department of Radiation Oncology, Houston, USA
| | - David T A Fuentes
- The University of Texas MD Anderson Cancer Center, Department of Imaging Physics, Houston, USA
| | - Kareem Wahid
- The University of Texas MD Anderson Cancer Center, Department of Radiation Oncology, Houston, USA; The University of Texas MD Anderson Cancer Center, Department of Imaging Physics, Houston, USA
| | - Cem Dede
- The University of Texas MD Anderson Cancer Center, Department of Radiation Oncology, Houston, USA
| | - Mohamed A Naser
- The University of Texas MD Anderson Cancer Center, Department of Radiation Oncology, Houston, USA
| | - Renjie He
- The University of Texas MD Anderson Cancer Center, Department of Radiation Oncology, Houston, USA
| | - Ahmed W Moawad
- The University of Texas MD Anderson Cancer Center, Department of Radiology, Houston, USA
| | - Khaled M Elsayes
- The University of Texas MD Anderson Cancer Center, Department of Radiology, Houston, USA
| | - Melissa M Chen
- The University of Texas MD Anderson Cancer Center, Department of Radiology, Houston, USA
| | - Adegbenga O Otun
- The University of Texas MD Anderson Cancer Center, Department of Head and Neck Surgery, Houston, USA
| | - Jillian Rigert
- The University of Texas MD Anderson Cancer Center, Department of Radiation Oncology, Houston, USA
| | - Mark S Chambers
- The University of Texas MD Anderson Cancer Center, Department of Head and Neck Surgery, Houston, USA
| | - Andrew Hope
- Department of Radiation Oncology, Princess Margaret Cancer Centre, Toronto, Canada
| | - Erin Watson
- Department of Radiation Oncology, Princess Margaret Cancer Centre, Toronto, Canada; Faculty of Dentistry, University of Toronto, Toronto, Canada
| | - Kristy K Brock
- The University of Texas MD Anderson Cancer Center, Department of Imaging Physics, Houston, USA
| | - Katherine Hutcheson
- The University of Texas MD Anderson Cancer Center, Department of Head and Neck Surgery, Houston, USA
| | - Lisanne van Dijk
- Department of Radiation Oncology, University Medical Center Groningen, the Netherlands
| | - Amy C Moreno
- The University of Texas MD Anderson Cancer Center, Department of Radiation Oncology, Houston, USA
| | - Stephen Y Lai
- The University of Texas MD Anderson Cancer Center, Department of Radiation Oncology, Houston, USA; The University of Texas MD Anderson Cancer Center, Department of Head and Neck Surgery, Houston, USA.
| | - Clifton D Fuller
- The University of Texas MD Anderson Cancer Center, Department of Radiation Oncology, Houston, USA.
| | - Abdallah S R Mohamed
- The University of Texas MD Anderson Cancer Center, Department of Radiation Oncology, Houston, USA; Department of Radiation Oncology, Baylor College of Medicine, Houston, USA.
| | | |
Collapse
|
11
|
Pirozzi MA, Franza F, Chianese M, Papallo S, De Rosa AP, Nardo FD, Caiazzo G, Esposito F, Donisi L. Combining radiomics and connectomics in MRI studies of the human brain: A systematic literature review. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2025; 266:108771. [PMID: 40233442 DOI: 10.1016/j.cmpb.2025.108771] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 10/15/2024] [Revised: 03/17/2025] [Accepted: 04/09/2025] [Indexed: 04/17/2025]
Abstract
Advances in MRI techniques continue to open new avenues to investigate the structure and function of the human brain. Radiomics, involving the extraction of quantitative image features, and connectomics, involving the estimation of structural and functional neural connections, from large amounts and different types of MRI data sets, represent two key research areas for advancing neuroimaging while exploiting progress in computational and theoretical modelling applied to MRI. This systematic literature review aimed at exploring the combination of radiomics and connectomics in human brain MRI studies, highlighting how the combination of these approaches can provide novel or additional insights into the human brain under normal and pathological conditions. The review was conducted according to the Preferred Reported Item for Systematic Reviews and Meta-Analyses (PRISMA) statement, seeking documents from Scopus and PubMed archives. Eleven studies (out of the initial 675 records) have met the established criteria and reported combined approaches from radiomics and connectomics. Three subgroups of approaches were identified, based on the MRI modalities used to obtain radiomic and connectomic features. The first group of 3 studies combined radiomics and connectomics applied to structural MRI (sMRI) data sets; the second group of 5 studies combined radiomics applied to sMRI data and connectomics applied to diffusion (dMRI) and/or functional MRI (fMRI) data sets; the third group of 3 studies combined radiomics and connectomics applied to fMRI. This review highlighted the recent growing interest in combining MRI-based radiomics and connectomics to explore the human brain for neurological, psychiatric, and oncological conditions. Current methodologies and challenges were discussed, pointing out future research directions to improve or standardize these approaches and the gaps to be filled to advance the field.
Collapse
Affiliation(s)
- Maria Agnese Pirozzi
- Department of Advanced Medical and Surgical Sciences, University of Campania Luigi Vanvitelli, Piazza Luigi Miraglia, 2, Naples 80138, Italy
| | - Federica Franza
- Department of Advanced Medical and Surgical Sciences, University of Campania Luigi Vanvitelli, Piazza Luigi Miraglia, 2, Naples 80138, Italy
| | - Marianna Chianese
- Department of Advanced Medical and Surgical Sciences, University of Campania Luigi Vanvitelli, Piazza Luigi Miraglia, 2, Naples 80138, Italy
| | - Simone Papallo
- Department of Advanced Medical and Surgical Sciences, University of Campania Luigi Vanvitelli, Piazza Luigi Miraglia, 2, Naples 80138, Italy
| | - Alessandro Pasquale De Rosa
- Department of Advanced Medical and Surgical Sciences, University of Campania Luigi Vanvitelli, Piazza Luigi Miraglia, 2, Naples 80138, Italy
| | - Federica Di Nardo
- Department of Advanced Medical and Surgical Sciences, University of Campania Luigi Vanvitelli, Piazza Luigi Miraglia, 2, Naples 80138, Italy
| | - Giuseppina Caiazzo
- Department of Advanced Medical and Surgical Sciences, University of Campania Luigi Vanvitelli, Piazza Luigi Miraglia, 2, Naples 80138, Italy
| | - Fabrizio Esposito
- Department of Advanced Medical and Surgical Sciences, University of Campania Luigi Vanvitelli, Piazza Luigi Miraglia, 2, Naples 80138, Italy.
| | - Leandro Donisi
- Department of Advanced Medical and Surgical Sciences, University of Campania Luigi Vanvitelli, Piazza Luigi Miraglia, 2, Naples 80138, Italy
| |
Collapse
|
12
|
Khene ZE, Bhanvadia R, Tachibana I, Sharma P, Trevino I, Graber W, Bertail T, Fleury R, Acosta O, De Crevoisier R, Bensalah K, Lotan Y, Margulis V. Impact of contrast enhancement phase on CT-based radiomics analysis for predicting post-surgical recurrence in renal cell carcinoma. Jpn J Radiol 2025; 43:977-984. [PMID: 39907976 DOI: 10.1007/s11604-025-01740-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/12/2024] [Accepted: 01/09/2025] [Indexed: 02/06/2025]
Abstract
PURPOSE To investigate the effect of CT enhancement phase on radiomics features for predicting post-surgical recurrence of clear cell renal cell carcinoma (ccRCC). METHODS This retrospective study included 144 patients who underwent radical or partial nephrectomy for ccRCC. Preoperative multiphase abdominal CT scans (non-contrast, corticomedullary, and nephrographic phases) were obtained for each patient. Automated segmentation of renal masses was performed using the nnU-Net framework. Radiomics signatures (RS) were developed for each phase using ensembles of machine learning-based models (Random Survival Forests [RSF], Survival Support Vector Machines [S-SVM], and Extreme Gradient Boosting [XGBoost]) with and without feature selection. Feature selection was performed using Affinity Propagation Clustering. The primary endpoint was disease-free survival, assessed by concordance index (C-index). RESULTS The study included 144 patients. Radical and partial nephrectomies were performed in 81% and 19% of patients, respectively, with 81% of tumors classified as high grade. Disease recurrence occurred in 74 patients (51%). A total of 1,316 radiomics features were extracted per phase per patient. Without feature selection, C-index values for RSF, S-SVM, XGBoost, and Penalized Cox models ranged from 0.43 to 0.61 across phases. With Affinity Propagation feature selection, C-index values improved to 0.51-0.74, with the corticomedullary phase achieving the highest performance (C-index up to 0.74). CONCLUSIONS The results of our study indicate that radiomics analysis of corticomedullary phase contrast-enhanced CT images may provide valuable predictive insight into recurrence risk for non-metastatic ccRCC following surgical resection. However, the lack of external validation is a limitation, and further studies are needed to confirm these findings in independent cohorts.
Collapse
Affiliation(s)
- Zine-Eddine Khene
- Department of Urology, University of Texas Southwestern Medical Center, 2001 Inwood Rd, WCB3, Floor 4, Dallas, TX, 75390, USA.
- Department of Urology, University of Rennes, Rennes, France.
- Image and Signal Processing Laboratory, Inserm U1099, University of Rennes, Rennes, France.
| | - Raj Bhanvadia
- Department of Urology, University of Texas Southwestern Medical Center, 2001 Inwood Rd, WCB3, Floor 4, Dallas, TX, 75390, USA
| | - Isamu Tachibana
- Department of Urology, University of Texas Southwestern Medical Center, 2001 Inwood Rd, WCB3, Floor 4, Dallas, TX, 75390, USA
| | - Prajwal Sharma
- Department of Urology, University of Texas Southwestern Medical Center, 2001 Inwood Rd, WCB3, Floor 4, Dallas, TX, 75390, USA
| | - Ivan Trevino
- Department of Urology, University of Texas Southwestern Medical Center, 2001 Inwood Rd, WCB3, Floor 4, Dallas, TX, 75390, USA
| | - William Graber
- Department of Urology, University of Texas Southwestern Medical Center, 2001 Inwood Rd, WCB3, Floor 4, Dallas, TX, 75390, USA
| | | | - Raphael Fleury
- Department of Urology, University of Rennes, Rennes, France
| | - Oscar Acosta
- Image and Signal Processing Laboratory, Inserm U1099, University of Rennes, Rennes, France
| | - Renaud De Crevoisier
- Image and Signal Processing Laboratory, Inserm U1099, University of Rennes, Rennes, France
- Department of Radiation Oncology, CLCC Eugene Marquis, Rennes, France
| | - Karim Bensalah
- Department of Urology, University of Rennes, Rennes, France
| | - Yair Lotan
- Department of Urology, University of Texas Southwestern Medical Center, 2001 Inwood Rd, WCB3, Floor 4, Dallas, TX, 75390, USA
| | - Vitaly Margulis
- Department of Urology, University of Texas Southwestern Medical Center, 2001 Inwood Rd, WCB3, Floor 4, Dallas, TX, 75390, USA
| |
Collapse
|
13
|
Benhabib H, Brandenberger D, Lajkosz K, Demicco EG, Tsoi KM, Wunder JS, Ferguson PC, Griffin AM, Naraghi A, Haider MA, White LM. MRI Radiomics Analysis in the Diagnostic Differentiation of Malignant Soft Tissue Myxoid Sarcomas From Benign Soft Tissue Musculoskeletal Myxomas. J Magn Reson Imaging 2025; 61:2630-2641. [PMID: 39843987 PMCID: PMC12063761 DOI: 10.1002/jmri.29691] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/01/2024] [Revised: 12/11/2024] [Accepted: 12/12/2024] [Indexed: 01/24/2025] Open
Abstract
BACKGROUND Differentiation of benign myxomas and malignant myxoid sarcomas can be difficult with an overlapping spectrum of morphologic MR findings. PURPOSE To assess the diagnostic utility of MRI radiomics in the differentiation of musculoskeletal myxomas and myxoid sarcomas. STUDY TYPE Retrospective. POPULATION A total of 523 patients were included; histologically proven myxomas (N = 201) and myxoid sarcomas (N = 322), randomly divided (70:30) into training:test subsets. SEQUENCE/FIELD STRENGTH T1-weighted (T1W), T2-weighted fat-suppressed (fluid-sensitive), and T1-weighted post-contrast (T1W + C) sequences at 1.0 T, 1.5 T, or 3.0 T. ASSESSMENT Seven semantic (qualitative) tumor features were assessed in each case. Manual 3D tumor segmentations performed with radiomics features extracted from T1W, fluid-sensitive, and T1W + C acquisitions. Models were constructed based on radiomic features from individual sequences and from their combination, both with and without the addition of qualitative tumor features. STATISTICAL TESTS Intraclass correlation evaluated in 60 cases segmented by three readers. Features with intraclass correlation <0.7 excluded from further analysis. Boruta feature selection and Random Forest modeling performed using the training-dataset, with resultant models used to assess class discrimination (myxoma vs. myxoid sarcoma) in the test dataset. Radiomics score defined as probability class = myxoma. Logistic regression modeling employed to estimate performance of the radiomics score. Area under the receiver operating characteristic curve (AUC) was used to assess diagnostic performance, and DeLong's test to assess performance between constructed models. A P-value <0.05 was considered significant. RESULTS Four qualitative semantic features showed significant predictive power in class discrimination. Radiomic models demonstrated excellent differentiation of myxomas from myxoid sarcomas: AUC of 0.9271 (T1W), 0.9049 (fluid-sensitive), and 0.9179 (T1W + C). Incorporation of multiparametric data or semantic features did not significantly improve model performance (P ≥ 0.08) compared to radiomic models derived from any individual MRI sequence alone. DATA CONCLUSION MRI radiomics appears to be accurate in the differentiation of myxomas from myxoid sarcomas. Classification performance did not improve when incorporating qualitative features or multiparametric imaging data. PLAIN LANGUAGE SUMMARY Accurately distinguishing between benign soft tissue myxomas and malignant myxoid sarcomas is essential for guiding appropriate management but remains challenging with conventional MRI interpretation. This study utilized radiomics, a method that extracts quantitative mathematically derived features from images, to develop predictive models based on routine MRI examination. Analyzing over 500 cases, MRI radiomics demonstrated excellent diagnostic accuracy in differentiating between benign myxomas and malignant myxoid sarcomas, highlighting the potential of the technique, as a powerful non-invasive tool that could complement current diagnostic approaches, and enhance clinical decision-making in patients with soft tissue myxoid tumors of the musculoskeletal system. LEVEL OF EVIDENCE 3 TECHNICAL EFFICACY: Stage 2.
Collapse
Affiliation(s)
- Hadas Benhabib
- Department of Medical ImagingUniversity of TorontoTorontoOntarioCanada
- Joint Department of Medical ImagingUniversity Health Network, Sinai Health System, Women's College Hospital, Mount Sinai HospitalTorontoOntarioCanada
| | - Daniel Brandenberger
- Department of Medical ImagingUniversity of TorontoTorontoOntarioCanada
- Joint Department of Medical ImagingUniversity Health Network, Sinai Health System, Women's College Hospital, Mount Sinai HospitalTorontoOntarioCanada
- Institut für Radiologie und NuklearmedizinKantonsspital BasellandLiestalSwitzerland
| | - Katherine Lajkosz
- Department of BiostatisticsUniversity Health NetworkTorontoOntarioCanada
| | - Elizabeth G. Demicco
- Department of Pathology and Laboratory MedicineMount Sinai HospitalTorontoOntarioCanada
- Department of Laboratory Medicine and PathobiologyUniversity of TorontoTorontoOntarioCanada
| | - Kim M. Tsoi
- Department of Pathology and Laboratory MedicineMount Sinai HospitalTorontoOntarioCanada
- Department of Laboratory Medicine and PathobiologyUniversity of TorontoTorontoOntarioCanada
- Department of SurgeryUniversity of TorontoTorontoOntarioCanada
| | - Jay S. Wunder
- Department of SurgeryUniversity of TorontoTorontoOntarioCanada
- University Musculoskeletal Oncology Unit, Division of Orthopedic SurgeryMount Sinai HospitalTorontoOntarioCanada
| | - Peter C. Ferguson
- Department of SurgeryUniversity of TorontoTorontoOntarioCanada
- University Musculoskeletal Oncology Unit, Division of Orthopedic SurgeryMount Sinai HospitalTorontoOntarioCanada
| | - Anthony M. Griffin
- University Musculoskeletal Oncology Unit, Division of Orthopedic SurgeryMount Sinai HospitalTorontoOntarioCanada
| | - Ali Naraghi
- Department of Medical ImagingUniversity of TorontoTorontoOntarioCanada
- Joint Department of Medical ImagingUniversity Health Network, Sinai Health System, Women's College Hospital, Mount Sinai HospitalTorontoOntarioCanada
| | - Masoom A. Haider
- Department of Medical ImagingUniversity of TorontoTorontoOntarioCanada
- Joint Department of Medical ImagingUniversity Health Network, Sinai Health System, Women's College Hospital, Mount Sinai HospitalTorontoOntarioCanada
| | - Lawrence M. White
- Department of Medical ImagingUniversity of TorontoTorontoOntarioCanada
- Joint Department of Medical ImagingUniversity Health Network, Sinai Health System, Women's College Hospital, Mount Sinai HospitalTorontoOntarioCanada
- Department of SurgeryUniversity of TorontoTorontoOntarioCanada
| |
Collapse
|
14
|
Jensen LJ, Kim D, Elgeti T, Steffen IG, Schaafs LA, Cretnik A, Hamm B, Nagel SN. Effects of parametric feature maps on the reproducibility of radiomics from different fields of view in cardiac magnetic resonance cine images- a clinical and experimental study setting. Int J Cardiovasc Imaging 2025; 41:1173-1184. [PMID: 40266551 PMCID: PMC12162737 DOI: 10.1007/s10554-025-03404-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 10/05/2024] [Accepted: 04/10/2025] [Indexed: 04/24/2025]
Abstract
In cardiac MRI, the field of view (FOV) is adapted to the individual patient's size, influencing spatial resolution and myocardial radiomics. This study aimed to investigate the effects of parametric feature maps on radiomics derived from cine images acquired with different FOV sizes on individuals without myocardial pathologies. In the clinical setting, cardiac MRI scans from clinical care were screened retrospectively for patients without pathological findings, neither in the MRI nor the medical history or follow-up, resulting in 61 included patients. In the experimental setting, 12 healthy volunteers were prospectively examined on a 1.5 Tesla MRI scanner with cine images acquired with three different FOVs (256 × 329 mm, 279 × 359 mm, 302 × 390 mm). One midventricular end-diastolic short-axis slice of the non-enhanced cine images was extracted for healthy volunteers and patients. The left ventricular myocardium was encompassed with regions of interest (ROIs). Ninety-three features were extracted using PyRadiomics. Images were converted to parametric radiomic feature maps using pretested software. ROIs were copied to the maps to retrieve the feature quantity. The variability of features across the different FOVs from the original images and feature maps was assessed with coefficients of variation (COVs) and rated stable at up to 10%. When derived from the original images, out of the 93 extracted features, only 24 (patients) and 29 (volunteers) revealed COVs < 10%. When extracted from the parametric maps, the number of stable features increased by 63% and 66%, with 39 (patients) and 48 (volunteers) features showing COVs < 10%, respectively. Software-computed parametric feature maps improve the reproducibility of radiomics across different FOVs in cardiac cine images of individuals without myocardial pathologies. Prospective investigations with different FOVs of a patient collective with myocardial pathologies could enhance the generalizability of the findings.
Collapse
Affiliation(s)
- Laura Jacqueline Jensen
- Department of Radiology, Charité- Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin, Humboldt-Universität zu Berlin and Berlin Institute of Health, Hindenburgdamm 30, 12203, Berlin, Germany.
| | - Damon Kim
- Department of Radiology, Charité- Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin, Humboldt-Universität zu Berlin and Berlin Institute of Health, Hindenburgdamm 30, 12203, Berlin, Germany
| | - Thomas Elgeti
- Department of Radiology, Charité- Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin, Humboldt-Universität zu Berlin and Berlin Institute of Health, Hindenburgdamm 30, 12203, Berlin, Germany
| | - Ingo Günter Steffen
- Department of Radiology, Charité- Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin, Humboldt-Universität zu Berlin and Berlin Institute of Health, Hindenburgdamm 30, 12203, Berlin, Germany
| | - Lars-Arne Schaafs
- Department of Radiology, Charité- Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin, Humboldt-Universität zu Berlin and Berlin Institute of Health, Hindenburgdamm 30, 12203, Berlin, Germany
| | - Anja Cretnik
- Department of Cardiology, Angiology and Intensive Care Medicine, Charité- Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin, Humboldt-Universität zu Berlin and Berlin Institute of Health, Hindenburgdamm 30, 12203, Berlin, Germany
| | - Bernd Hamm
- Department of Radiology, Charité- Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin, Humboldt-Universität zu Berlin and Berlin Institute of Health, Hindenburgdamm 30, 12203, Berlin, Germany
| | - Sebastian Niko Nagel
- Department of Radiology, Charité- Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin, Humboldt-Universität zu Berlin and Berlin Institute of Health, Hindenburgdamm 30, 12203, Berlin, Germany
- Department of Diagnostic and Interventional Radiology and Paediatric Radiology, Bielefeld University Medical School and University Medical Center East Westphalia-Lippe Protestant Hospital of the Bethel Foundation Academic, Burgsteig 13, 33617, Bielefeld, Germany
| |
Collapse
|
15
|
Schiulaz A, Nordio G, Giacomel A, Easmin R, Bettinelli A, Selvaggi P, Williams S, Turkheimer F, Jauhar S, Howes O, Veronese M, FDOPA PET Imaging Working Group. Radiomic Analysis of Striatal [ 18F]FDOPA PET Imaging in Patients with Psychosis for the Identification of Antipsychotic Response. Mol Imaging Biol 2025; 27:365-378. [PMID: 40323469 PMCID: PMC12162767 DOI: 10.1007/s11307-025-02014-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Collaborators] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/30/2024] [Revised: 03/25/2025] [Accepted: 04/23/2025] [Indexed: 06/16/2025]
Abstract
PURPOSE Schizophrenia (SCZ) is a severe psychiatric disorder marked by abnormal dopamine synthesis, measurable through [18F]FDOPA PET imaging. This imaging technique has been proposed as a biomarker for treatment stratification in SCZ, where one-third of patients respond poorly to standard antipsychotics. This study explores the use of radiomics on [18F]FDOPA PET data to examine dopamine synthesis in SCZ and predict antipsychotic response. METHODS We analysed 273 [18F]FDOPA PET scans from healthy controls (n = 138) and SCZ patients (n = 135) from multiple cohorts, including first-episode psychosis cases. Radiomic features from striatal regions were extracted using the MIRP Python package. Reproducibility was assessed with test-retest scans, selecting features with an intraclass correlation coefficient (ICC) > 0.80. These features were grouped via hierarchical clustering based on Spearman correlation. Regression analysis evaluated sex and age effects on radiomic features. Predictive power for treatment response was tested and compared to standard imaging analysis obtained from the Standardised Uptake Value ratio (SUVr) of striatal over cerebellar tracer activity. RESULTS Out of 177 features, 15 met the ICC criteria (ICC: 0.81-0.99). Age and sex influenced features in patients but not in controls. The best performance were was by the GLCM joint maximum feature, which effectively differentiated responders from non-responders (AUC: 0.66-0.87), but did not reach statistical significance in classification over SUVr. CONCLUSION Radiomic analysis of [18F]FDOPA PET supports its use as a biomarker for assessing antipsychotic efficacy in schizophrenia, highlighting differential striatal tracer uptake based on patient response. While it provides modest classification improvements over standard imaging, further validation in larger datasets and integration with multivariate classification algorithms are needed.
Collapse
Affiliation(s)
- Astrid Schiulaz
- Department of Information Engineering, University of Padua, Padua, Italy
| | - Giovanna Nordio
- Department of Neuroimaging, Institute of Psychiatry, Psychology & Neuroscience, King's College London, London, UK
| | - Alessio Giacomel
- Department of Neuroimaging, Institute of Psychiatry, Psychology & Neuroscience, King's College London, London, UK
| | - Rubaida Easmin
- Department of Neuroimaging, Institute of Psychiatry, Psychology & Neuroscience, King's College London, London, UK
| | - Andrea Bettinelli
- Medical Physics Department, Veneto Institute of Oncology IOV - IRCCS, Padova, Italy
| | - Pierluigi Selvaggi
- Department of Neuroimaging, Institute of Psychiatry, Psychology & Neuroscience, King's College London, London, UK
- Department of Translational Biomedicine and Neuroscience, University of Bari Aldo Moro, Bari, Italy
| | - Steven Williams
- Department of Neuroimaging, Institute of Psychiatry, Psychology & Neuroscience, King's College London, London, UK
| | - Federico Turkheimer
- Department of Neuroimaging, Institute of Psychiatry, Psychology & Neuroscience, King's College London, London, UK
| | - Sameer Jauhar
- Department of Psychosis Studies, Institute of Psychiatry, Psychology & Neuroscience, King's College London, London, UK
- Psychiatric Imaging Group, MRC London Institute of Medical Sciences, Hammersmith Hospital, Imperial College London, London, UK
| | - Oliver Howes
- Department of Psychosis Studies, Institute of Psychiatry, Psychology & Neuroscience, King's College London, London, UK
- Psychiatric Imaging Group, MRC London Institute of Medical Sciences, Hammersmith Hospital, Imperial College London, London, UK
- South London and Maudsley NHS Foundation Trust, London, UK
| | - Mattia Veronese
- Department of Information Engineering, University of Padua, Padua, Italy.
- Department of Neuroimaging, Institute of Psychiatry, Psychology & Neuroscience, King's College London, London, UK.
| | | |
Collapse
Collaborators
Ilinca Angelescu, Micheal Bloomfield, Ilaria Bonoldi, Faith Borgan, Tarik Dahoun, Enrico D'Ambrosio, Arsime Demjaha, Jecek Donocik, Alice Egerton, Stephen Kaar, Euitae Kim, Seoyoung Kim, James Maccabe, Julian Matthews, Robert McCutcheon, Philip McGuire, Chiara Nosarti, Matthew Nour, Maria Rogdaki, Grazia Rutigliano, Peter S Talbot, Luke Vano,
Collapse
|
16
|
Zhou J, Yu X, Cui Y, Zhou Q, Xu Q, Zhang X, Bai Y, Chen R, Wu Q, Wang M. Prediction of molecular subtypes of endometrial cancer patients on the basis of intratumoral and peritumoral radiomic features from multiparametric MR images. Eur J Radiol 2025; 187:112110. [PMID: 40262460 DOI: 10.1016/j.ejrad.2025.112110] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/16/2025] [Revised: 03/25/2025] [Accepted: 04/09/2025] [Indexed: 04/24/2025]
Abstract
OBJECTIVES The purpose of this study was to assess the performance of multiparametric MRI-based radiomic models in predicting the molecular subtypes of endometrial cancer (EC) patients. METHODS A total of 310 patients with pathologically confirmed EC who underwent preoperative MRI were enrolled this retrospective study and randomly divided into training (n = 217) and testing (n = 93) cohorts. We extracted 22,640 radiomic features from intratumoral and 3-mm peritumoral regions of interest (ROIs) on MR images. Feature selection was performed using the Mann-Whitney U test, Max-Relevance and Min-Redundancy (mRMR) and the least absolute shrinkage and selection operator (LASSO). Twelve radiomic signatures (RSs) were constructed using logistic regression to predict four molecular subtypes (POLEmut, MMRd, NSMP, and p53abn). The performance of these RSs was assessed using receiving operating characteristic (ROC) curve analysis, and the area under the curve (AUC), sensitivity, specificity, and accuracy were calculated. RESULTS In the testing cohort, the RSs based on intratumoral features for predicting the POLEmut, MMRd, NSMP and p53abn subtypes yielded AUCs of 0.764, 0.812, 0.893 and 0.731, respectively, whereas those based on peritumoral features yielded AUCs of 0.847, 0.836, 0.871 and 0.804, respectively. The RSs constructed by combining intratumoral and peritumoral features for predicting the POLEmut, MMRd, NSMP and p53abn subtypes had the AUCs of 0.844, 0.880, 0.943 and 0.801, respectively. CONCLUSION The combination of intratumoral and peritumoral radiomic features from multiparametric MRI enables effective and noninvasive prediction of EC molecular subtypes.
Collapse
Affiliation(s)
- Jing Zhou
- From the Department of Radiology, Henan Provincial People's Hospital & Zhengzhou University People's Hospital & Henan Provincial Key Laboratory of Neurological Disease Imaging Diagnosis and Research, 7 Weiwu Road, Zhengzhou 450000, China.
| | - Xuan Yu
- From the Department of Radiology, Henan Provincial People's Hospital & Zhengzhou University People's Hospital & Henan Provincial Key Laboratory of Neurological Disease Imaging Diagnosis and Research, 7 Weiwu Road, Zhengzhou 450000, China.
| | - Yingying Cui
- From the Department of Radiology, Henan Provincial People's Hospital & Zhengzhou University People's Hospital & Henan Provincial Key Laboratory of Neurological Disease Imaging Diagnosis and Research, 7 Weiwu Road, Zhengzhou 450000, China.
| | - Qian Zhou
- From the Department of Radiology, Henan Provincial People's Hospital & Zhengzhou University People's Hospital & Henan Provincial Key Laboratory of Neurological Disease Imaging Diagnosis and Research, 7 Weiwu Road, Zhengzhou 450000, China.
| | - Qiannan Xu
- Department of Gynecology and Obstetrics, Henan Provincial People's Hospital & Zhengzhou University People's Hospital, Zhengzhou 450000, China.
| | - Xianwei Zhang
- Department of Pathology, Henan Provincial People's Hospital & Zhengzhou University People's Hospital, Zhengzhou 450000, China.
| | - Yan Bai
- From the Department of Radiology, Henan Provincial People's Hospital & Zhengzhou University People's Hospital & Henan Provincial Key Laboratory of Neurological Disease Imaging Diagnosis and Research, 7 Weiwu Road, Zhengzhou 450000, China.
| | - Rushi Chen
- From the Department of Radiology, Henan Provincial People's Hospital & Zhengzhou University People's Hospital & Henan Provincial Key Laboratory of Neurological Disease Imaging Diagnosis and Research, 7 Weiwu Road, Zhengzhou 450000, China.
| | - Qingxia Wu
- Beijing United Imaging Research Institute of Intelligent Imaging & United Imaging Intelligence (Beijing) Co., Ltd., Beijing 100089, China.
| | - Meiyun Wang
- From the Department of Radiology, Henan Provincial People's Hospital & Zhengzhou University People's Hospital & Henan Provincial Key Laboratory of Neurological Disease Imaging Diagnosis and Research, 7 Weiwu Road, Zhengzhou 450000, China; Biomedical Research Institute, Henan Academy of Sciences, Zhengzhou 450000, China; Henan Key Laboratory for Medical Imaging of Neurological Diseases, Zhengzhou 450000, China.
| |
Collapse
|
17
|
Fang Y, Zhang Q, Yan J, Yu S. Application of radiomics in acute and severe non-neoplastic diseases: A literature review. J Crit Care 2025; 87:155027. [PMID: 39848114 DOI: 10.1016/j.jcrc.2025.155027] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/14/2024] [Revised: 11/01/2024] [Accepted: 01/10/2025] [Indexed: 01/25/2025]
Abstract
Radiomics involves the integration of computer technology, big data analysis, and clinical medicine. Currently, there have been initial advancements in the fields of acute cerebrovascular disease and cardiovascular disease. The objective of radiomics is to extract quantitative features from medical images for analysis to predict the risk or treatment outcome, help in differential diagnosis, and guide clinical decisions and management. Radiomics applied research has reached a more advanced stage yet encounters several obstacles, including the need for standardization of radiomics features and alignment with treatment requirements for acute and severe illnesses. Future research should aim to seamlessly incorporate radiomics with various disciplines, leverage big data and artificial intelligence advancements, cater to the requirements of acute and critical medicine, and enhance the effectiveness of technological innovation and application in diagnosing and treating acute and critical illnesses.
Collapse
Affiliation(s)
- Yu Fang
- Department of Emergency Medicine, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430000, China; Department of Critical Care Medicine, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430000, China
| | - Qiannan Zhang
- Department of Emergency Medicine, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430000, China
| | - Jingjun Yan
- Department of Emergency Medicine, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430000, China; Department of Critical Care Medicine, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430000, China
| | - Shanshan Yu
- Department of Emergency Medicine, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430000, China; Department of Critical Care Medicine, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430000, China.
| |
Collapse
|
18
|
Kiso T, Okada Y, Kawata S, Shichiji K, Okumura E, Hatsumi N, Matsuura R, Kaminaga M, Kuwano H, Okumura E. Ultrasound-based radiomics and machine learning for enhanced diagnosis of knee osteoarthritis: Evaluation of diagnostic accuracy, sensitivity, specificity, and predictive value. Eur J Radiol Open 2025; 14:100649. [PMID: 40236979 PMCID: PMC11999524 DOI: 10.1016/j.ejro.2025.100649] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/09/2024] [Revised: 03/21/2025] [Accepted: 03/26/2025] [Indexed: 04/17/2025] Open
Abstract
Purpose To evaluate the usefulness of radiomics features extracted from ultrasonographic images in diagnosing and predicting the severity of knee osteoarthritis (OA). Methods In this single-center, prospective, observational study, radiomics features were extracted from standing radiographs and ultrasonographic images of knees of patients aged 40-85 years with primary medial OA and without OA. Analysis was conducted using LIFEx software (version 7.2.n), ANOVA, and LASSO regression. The diagnostic accuracy of three different models, including a statistical model incorporating background factors and machine learning models, was evaluated. Results Among 491 limbs analyzed, 318 were OA and 173 were non-OA cases. The mean age was 72.7 (±8.7) and 62.6 (±11.3) years in the OA and non-OA groups, respectively. The OA group included 81 (25.5 %) men and 237 (74.5 %) women, whereas the non-OA group included 73 men (42.2 %) and 100 (57.8 %) women. A statistical model using the cutoff value of MORPHOLOGICAL_SurfaceToVolumeRatio (IBSI:2PR5) achieved a specificity of 0.98 and sensitivity of 0.47. Machine learning diagnostic models (Model 2) demonstrated areas under the curve (AUCs) of 0.88 (discriminant analysis) and 0.87 (logistic regression), with sensitivities of 0.80 and 0.81 and specificities of 0.82 and 0.80, respectively. For severity prediction, the statistical model using MORPHOLOGICAL_SurfaceToVolumeRatio (IBSI:2PR5) showed sensitivity and specificity values of 0.78 and 0.86, respectively, whereas machine learning models achieved an AUC of 0.92, sensitivity of 0.81, and specificity of 0.85 for severity prediction. Conclusion The use of radiomics features in diagnosing knee OA shows potential as a supportive tool for enhancing clinicians' decision-making.
Collapse
Affiliation(s)
- Takeharu Kiso
- Department of Radiology, Medical Corporation Seireikai Tachikawa Memorial Hospital, 2-12-14 Yakumo, Kasama, Ibaraki 309-1611, Japan
- Graduate School of Medical Sciences, Suzuka University, 1001-1, Kishioka-cho, Suzuka-shi, Mie 510-0293, Japan
| | - Yukinori Okada
- Graduate School of Medical Sciences, Suzuka University, 1001-1, Kishioka-cho, Suzuka-shi, Mie 510-0293, Japan
- Tokyo Medical University Hospital, Department of Clinical Medicine, Division of Radiation Oncology, 6-7-1 Nishi-Shinjuku, Shinjuku-ku, Tokyo 160-0023, Japan
| | - Satoru Kawata
- Department of Radiology, Faculty of Medical and Health Sciences, Tsukuba International University, 6-20-1 Manabe, Tsuchiura-shi, Ibaraki 300-0051, Japan
- Postdoctoral Program, Graduate School of Health Sciences, Kyorin University, 5-4-1 Shimorenjaku, Mitaka-shi, Tokyo 181-8612, Japan
| | - Kouta Shichiji
- Department of Radiology, Medical Corporation Seireikai Tachikawa Memorial Hospital, 2-12-14 Yakumo, Kasama, Ibaraki 309-1611, Japan
| | - Eiichiro Okumura
- Department of Radiology, Faculty of Medical and Health Sciences, Tsukuba International University, 6-20-1 Manabe, Tsuchiura-shi, Ibaraki 300-0051, Japan
| | - Noritaka Hatsumi
- Department of Radiology, Medical Corporation Seireikai Tachikawa Memorial Hospital, 2-12-14 Yakumo, Kasama, Ibaraki 309-1611, Japan
| | - Ryohei Matsuura
- Department of Radiology, Medical Corporation Seireikai Tachikawa Memorial Hospital, 2-12-14 Yakumo, Kasama, Ibaraki 309-1611, Japan
| | - Masaki Kaminaga
- Department of Radiology, Medical Corporation Seireikai Tachikawa Memorial Hospital, 2-12-14 Yakumo, Kasama, Ibaraki 309-1611, Japan
| | - Hikaru Kuwano
- Department of Radiology, Medical Corporation Seireikai Tachikawa Memorial Hospital, 2-12-14 Yakumo, Kasama, Ibaraki 309-1611, Japan
| | - Erika Okumura
- Graduate School of Medical Sciences, Suzuka University, 1001-1, Kishioka-cho, Suzuka-shi, Mie 510-0293, Japan
- Department of Radiology, Tsukuba Medical Center Hospital, 1-3-1 Amakubo, Tsukuba City, Ibaraki Prefecture 305-8558, Japan
| |
Collapse
|
19
|
Chirra PV, Giriprakash P, Rizk AG, Kurowski JA, Viswanath SE, Gandhi NS. Developing a Reproducible Radiomics Model for Diagnosis of Active Crohn's Disease on CT Enterography Across Annotation Variations and Acquisition Differences. JOURNAL OF IMAGING INFORMATICS IN MEDICINE 2025; 38:1594-1605. [PMID: 39466507 DOI: 10.1007/s10278-024-01303-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 05/22/2024] [Revised: 09/24/2024] [Accepted: 10/11/2024] [Indexed: 10/30/2024]
Abstract
To systematically identify radiomics features on CT enterography (CTE) scans which can accurately diagnose active Crohn's disease across multiple sources of variation. Retrospective study of CTE scans curated between 2013 and 2015, comprising 164 subjects (65 male, 99 female; all patients were over the age of 18) with endoscopic confirmation for the presence or absence of active Crohn's disease. All patients had three distinct sets of scans available (full and reduced dose, where the latter had been reconstructed via two different methods), acquired on a single scanner at a single institution. Radiomics descriptors from annotated terminal ileum regions were individually and systematically evaluated for resilience to different imaging variations (changes in dose/reconstruction, batch effects, and simulated annotation differences) via multiple reproducibility measures. Multiple radiomics models (by accounting for each source of variation) were evaluated in terms of classifier area under the ROC curve (AUC) for identifying patients with active Crohn's disease, across separate discovery and hold-out validation cohorts. Radiomics descriptors selected based on resiliency to multiple sources of imaging variation yielded the highest overall classification performance in the discovery cohort (AUC = 0.79 ± 0.04) which also best generalized in hold-out validation (AUC = 0.81). Performance was maintained across multiple doses and reconstructions while also being significantly better (p < 0.001) than non-resilient descriptors or descriptors only resilient to a single source of variation. Radiomics features can accurately diagnose active Crohn's disease on CTE scans across multiple sources of imaging variation via systematic analysis of reproducibility measures. Clinical utility and translatability of radiomics features for diagnosis and characterization of Crohn's disease on CTE scans will be contingent on their reproducibility across multiple types and sources of imaging variation.
Collapse
Affiliation(s)
- Prathyush V Chirra
- Department of Biomedical Engineering, Case Western Reserve University, Cleveland, OH, USA
| | - Pavithran Giriprakash
- Department of Biomedical Engineering, Case Western Reserve University, Cleveland, OH, USA
| | - Alain G Rizk
- Section, Abdominal Imaging, Imaging Institute, and Digestive Diseases and Surgery Institute and Cancer Institute, Cleveland Clinic, Cleveland, OH, USA
| | - Jacob A Kurowski
- Department of Pediatric Gastroenterology, Hepatology & Nutrition, Cleveland Clinic, Cleveland, OH, USA
| | - Satish E Viswanath
- Department of Biomedical Engineering, Case Western Reserve University, Cleveland, OH, USA.
- Cleveland Veterns Affairs Medical Center, Cleveland, OH, USA.
| | - Namita S Gandhi
- Section, Abdominal Imaging, Imaging Institute, and Digestive Diseases and Surgery Institute and Cancer Institute, Cleveland Clinic, Cleveland, OH, USA
| |
Collapse
|
20
|
Schwartz M. Editorial for "MRI Radiomics Analysis in the Diagnostic Differentiation of Malignant Soft Tissue Myxoid Sarcomas From Benign Soft Tissue Musculoskeletal Myxomas". J Magn Reson Imaging 2025; 61:2642-2643. [PMID: 39865486 DOI: 10.1002/jmri.29696] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/12/2024] [Accepted: 12/14/2024] [Indexed: 01/28/2025] Open
Affiliation(s)
- Martin Schwartz
- Section on Experimental Radiology, Diagnostic and Interventional Radiology, University Hospital of Tübingen, Tübingen, Germany
| |
Collapse
|
21
|
Ceriani L, Milan L, Chauvie S, Zucca E. Understandings 18 FDG PET radiomics and its application to lymphoma. Br J Haematol 2025; 206:1546-1559. [PMID: 40230306 DOI: 10.1111/bjh.20074] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/18/2025] [Accepted: 03/28/2025] [Indexed: 04/16/2025]
Abstract
The early identification of lymphoma patients who fail front-line treatment is crucial for optimizing disease management. Positron emission tomography, a well-established tool for staging and response evaluation in lymphoma, is typically assessed visually or semiquantitatively, leaving much of its latent information unexploited. Radiomic analysis, which employs mathematical descriptors, can enable the extraction of quantitative features from baseline images that correlate with the disease's biological characteristics. Emerging radiomic features such as metabolic tumour volume, total lesion glycolysis and markers of disease dissemination and metabolic heterogeneity are proving to be powerful prognostic biomarkers in lymphoma. Texture analysis, the most advanced area of radiomics, offers highly complex features that require further standardization and validation before being adopted as reliable biomarkers. Combining radiomic features with clinical risk factors and genomic data holds promising potential for improving clinical risk prediction. This review explores the current state of radiomic analysis, progress towards its standardization and its incorporation into clinical practice and trial designs. The integration of radiomic markers with circulating tumour DNA may provide a comprehensive approach to developing baseline and dynamic risk scores, facilitating the testing of novel treatments and advancing personalized treatment of aggressive lymphomas.
Collapse
Affiliation(s)
- Luca Ceriani
- Nuclear Medicine and PET/CT Centre, Imaging Institute of Southern Switzerland, Ente Ospedaliero Cantonale, Lugano, Switzerland
- Institute of Oncology Research, Faculty of Biomedical Sciences, Università della Svizzera Italiana, Bellinzona, Switzerland
| | - Lisa Milan
- Nuclear Medicine and PET/CT Centre, Imaging Institute of Southern Switzerland, Ente Ospedaliero Cantonale, Lugano, Switzerland
| | - Stephane Chauvie
- Medical Physics Division, Santa Croce e Carlo Hospital, Cuneo, Italy
| | - Emanuele Zucca
- Institute of Oncology Research, Faculty of Biomedical Sciences, Università della Svizzera Italiana, Bellinzona, Switzerland
- Haematology, Oncology Institute of Southern Switzerland, Ente Ospedaliero Cantonale, Bellinzona, Switzerland
- Department of Medical Oncology, Bern University Hospital and University of Bern, Bern, Switzerland
| |
Collapse
|
22
|
Liu H, Meng X, Wang G, Yao S, Wang Y, Wang R, Wang T. Differentiating second primary lung cancer from pulmonary metastasis in patients of single solitary pulmonary lesion with extrapulmonary tumor using multiparametric analysis of FDG PET/CT. Ann Nucl Med 2025; 39:567-575. [PMID: 40042775 PMCID: PMC12095392 DOI: 10.1007/s12149-025-02034-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/13/2024] [Accepted: 02/24/2025] [Indexed: 05/22/2025]
Abstract
OBJECTIVE Using fluorine-18-fluorodeoxyglucose (18F-FDG) positron emission tomography/computed tomography (PET/CT), a multiparametric analysis will be performed in the differential diagnosis of patients with single solitary pulmonary lesion and extrapulmonary malignant tumor to discriminate between a second primary lung cancer (SPLC) and pulmonary metastasis (PM). METHODS This study retrospectively studied 84 patients with preoperative exams utilizing 18F-FDG PET/CT. Using complementing PET/CT parameters, a composite model was developed. A receiver operating characteristic (ROC) analysis assessed the combined model and each independent parameter's differential diagnostic efficacies. Furthermore, this study investigated the improvement in diagnostic efficacy using other metrics, such as integrated discriminatory improvement (IDI) and net reclassification improvement (NRI). RESULTS The highest discriminative diagnostic value was obtained by the independent parameters energy (1,039,358.1 [95126.2-1,965,032.2] vs. 92,011.0 [45916.3-365,322.9], P = 0.001). In comparison to peak standardized uptake value (SUVpeak), total lesion glycolysis (TLG), energy, lobulation, and spiculation alone, the combined model (addition of these factors) significantly improved the differential diagnostic efficacy of SPLCs and PMs (sensitivity = 76.2%, specificity = 83.8%, area under the curve [AUC] = 0.826) and permitted reclassification using IDI = 0.176 (P < 0.001), 0.169 (P < 0.001), 0.127 (P < 0.001), and categorical NRI = 0.678 (P < 0.001), 0.637 (P < 0.001), and 0.592 (P < 0.001) compared to SUVpeak, TLG and energy separately. DeLong's test revealed a statistically significant enhancement in ROC when compared to SUVpeak (Z = 2.372, P = 0.018), TLG (Z = 2.095, P = 0.036), and energy (Z = 2.318, P = 0.020). CONCLUSION Combining multiple parameters using 18F-FDG PET/CT may further improve distinguishing between SPLCs and PMs in patients with single solitary pulmonary lesion and extrapulmonary malignant tumor.
Collapse
Affiliation(s)
- Honghong Liu
- Departments of Nuclear Medicine, the First Medical Center, Chinese PLA General Hospital, No.28 Fuxing Road, Beijing, 100853, China
| | - Xiaolin Meng
- Departments of Nuclear Medicine, the First Medical Center, Chinese PLA General Hospital, No.28 Fuxing Road, Beijing, 100853, China
| | - Guanyun Wang
- Department of Nuclear Medicine, Beijing Friendship Hospital, Capital Medical University, Beijing, 100050, China
| | - Shulin Yao
- Departments of Nuclear Medicine, the First Medical Center, Chinese PLA General Hospital, No.28 Fuxing Road, Beijing, 100853, China
| | - Yanmei Wang
- GE Healthcare China, Pudong New Town, Shanghai, 200125, China
| | - Ruimin Wang
- Departments of Nuclear Medicine, the First Medical Center, Chinese PLA General Hospital, No.28 Fuxing Road, Beijing, 100853, China.
| | - Tao Wang
- Departments of Thoracic Surgery, the First Medical Center, Chinese PLA General Hospital, No.28 Fuxing Road, Beijing, 100853, China.
| |
Collapse
|
23
|
Peters J, van Leeuwen MM, Moriakov N, van Dijck JAAM, Mann RM, Teuwen J, Lips EH, van den Belt-Dusebout AW, Wesseling J, Penning de Vries BBL, Verboom S, Karssemeijer N, Elias SG, Broeders MJM. Development of radiomics-based models on mammograms with mass lesions to predict prognostically relevant characteristics of invasive breast cancer in a screening cohort. Br J Cancer 2025; 132:1040-1049. [PMID: 40188293 PMCID: PMC12120084 DOI: 10.1038/s41416-025-02995-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/13/2024] [Revised: 01/17/2025] [Accepted: 03/21/2025] [Indexed: 04/07/2025] Open
Abstract
BACKGROUND Optimizing breast-screening performance involves minimizing overdiagnosis of prognostically favorable invasive breast cancer (IBC) that does not need immediate recall and underdiagnosis of prognostically unfavorable IBC that is not recalled timely. We investigated whether mammographic features of masses predict prognostically relevant IBC characteristics. METHODS In a screening cohort, we obtained pathological information of 1587 IBCs presenting as a mass through the nationwide cancer registry and pathology databank. We developed models based on mammographic tumor appearance to predict whether IBC was prognostically favorable (T1N0M0 luminal A-like) or unfavorable. Models were based on 1095 positive screening mammograms (possible overdiagnosis), or on 603 last negative mammograms with in retrospect visible masses (possible underdiagnosis). We calculated performance metrics using cross-validation. RESULTS 23.5% of masses were prognostically favorable IBC. Using 1095 positive mammograms, the model's predictions to have prognostically favorable IBC (10th-90th percentile range 8.7-47.0%) yielded AUC 0.75 (SD across repeats 0.01), slope 1.16 (SD 0.07). Performance in 603 last negative screening mammograms with masses was poor: AUC 0.60 (SD 0.02), slope 0.85 (SD 0.28). CONCLUSIONS Mammography-based models from masses representing IBC at time of recall (possible overdiagnosis) predict prognostically relevant characteristics of IBC. Models based on in retrospect visible masses (possible underdiagnosis) performed poorly.
Collapse
Affiliation(s)
- Jim Peters
- Department IQ Health, Radboud University Medical Center, Nijmegen, Netherlands.
| | - Merle M van Leeuwen
- Division of Molecular Pathology, Netherlands Cancer Institute (NKI), Amsterdam, Netherlands
| | - Nikita Moriakov
- Department of Radiation Oncology, Netherlands Cancer Institute (NKI), Amsterdam, Netherlands
- Department of Radiology, Netherlands Cancer Institute (NKI), Amsterdam, Netherlands
| | - Jos A A M van Dijck
- Department IQ Health, Radboud University Medical Center, Nijmegen, Netherlands
| | - Ritse M Mann
- Department of Radiology, Netherlands Cancer Institute (NKI), Amsterdam, Netherlands
- Department of Medical Imaging, Radboud University Medical Center, Nijmegen, Netherlands
| | - Jonas Teuwen
- Department of Radiation Oncology, Netherlands Cancer Institute (NKI), Amsterdam, Netherlands
| | - Esther H Lips
- Division of Molecular Pathology, Netherlands Cancer Institute (NKI), Amsterdam, Netherlands
| | | | - Jelle Wesseling
- Division of Molecular Pathology, Netherlands Cancer Institute (NKI), Amsterdam, Netherlands
- Department of Pathology, Netherlands Cancer Institute (NKI), Amsterdam, Netherlands
- Department of Pathology, Leiden University Medical Center, Leiden, Netherlands
| | - Bas B L Penning de Vries
- Julius Center for Health Sciences and Primary Care, UMC Utrecht, University Utrecht, Utrecht, Netherlands
| | - Sarah Verboom
- Department of Medical Imaging, Radboud University Medical Center, Nijmegen, Netherlands
| | - Nico Karssemeijer
- Department of Medical Imaging, Radboud University Medical Center, Nijmegen, Netherlands
| | - Sjoerd G Elias
- Julius Center for Health Sciences and Primary Care, UMC Utrecht, University Utrecht, Utrecht, Netherlands
| | - Mireille J M Broeders
- Department IQ Health, Radboud University Medical Center, Nijmegen, Netherlands
- Dutch Expert Centre for Screening, Nijmegen, Netherlands
| |
Collapse
|
24
|
Zhu Y, Liu T, Chen J, Wen L, Zhang J, Zheng D. Prediction of therapeutic response to transarterial chemoembolization plus systemic therapy regimen in hepatocellular carcinoma using pretreatment contrast-enhanced MRI based habitat analysis and Crossformer model. Abdom Radiol (NY) 2025; 50:2464-2475. [PMID: 39586897 DOI: 10.1007/s00261-024-04709-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/04/2024] [Revised: 11/14/2024] [Accepted: 11/15/2024] [Indexed: 11/27/2024]
Abstract
PURPOSE To develop habitat and deep learning (DL) models from multi-phase contrast-enhanced magnetic resonance imaging (CE-MRI) habitat images categorized using the K-means clustering algorithm. Additionally, we aim to assess the predictive value of identified regions for early evaluation of the responsiveness of hepatocellular carcinoma (HCC) patients to treatment with transarterial chemoembolization (TACE) plus molecular targeted therapies (MTT) and anti-PD-(L)1. METHODS A total of 102 patients with HCC from two institutions (A, n = 63 and B, n = 39) who received TACE plus systemic therapy were enrolled from September 2020 to January 2024. Multiple CE-MRI sequences were used to outline 3D volumes of interest (VOI) of the lesion. Subsequently, K-means clustering was applied to categorize intratumoral voxels into three distinct subgroups, based on signal intensity values of images. Using data from institution A, the habitat model was built with the ExtraTrees classifier after extracting radiomics features from intratumoral habitats. Similarly, the Crossformer model and ResNet50 model were trained on multi-channel data in institution A, and a DL model with Transformer-based aggregation was constructed to predict the response. Finally, all models underwent validation at institution B. RESULTS The Crossformer model and the habitat model both showed high area under the receiver operating characteristic curves (AUCs) of 0.869 and 0.877 (training cohort). In validation, AUC was 0.762 for the Crossformer model and 0.721 for the habitat model. CONCLUSION The habitat model and DL model based on CE-MRI possesses the capability to non-invasively predict the efficacy of TACE plus systemic therapy in HCC patients, which is critical for precision treatment and patient outcomes.
Collapse
Affiliation(s)
- Yuemin Zhu
- Department of Radiology, Clinical Oncology School of Fujian Medical University, Fujian Cancer Hospital, Fuzhou, China
| | - Tao Liu
- Department of Radiology, Chongqing University Cancer Hospital, Chongqing Cancer Institute, and Chongqing Cancer Hospital, Chongqing, China
| | - Jianwei Chen
- Department of Radiology, Clinical Oncology School of Fujian Medical University, Fujian Cancer Hospital, Fuzhou, China
| | - Liting Wen
- Department of Radiology, Clinical Oncology School of Fujian Medical University, Fujian Cancer Hospital, Fuzhou, China
| | - Jiuquan Zhang
- Department of Radiology, Chongqing University Cancer Hospital, Chongqing Cancer Institute, and Chongqing Cancer Hospital, Chongqing, China.
| | - Dechun Zheng
- Department of Radiology, Clinical Oncology School of Fujian Medical University, Fujian Cancer Hospital, Fuzhou, China.
| |
Collapse
|
25
|
Ammari S, Quillent A, Elvira V, Bidault F, Garcia GCTE, Hartl DM, Balleyguier C, Lassau N, Chouzenoux É. Using Machine Learning on MRI Radiomics to Diagnose Parotid Tumours Before Comparing Performance with Radiologists: A Pilot Study. JOURNAL OF IMAGING INFORMATICS IN MEDICINE 2025; 38:1496-1508. [PMID: 39390287 DOI: 10.1007/s10278-024-01255-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 02/20/2024] [Revised: 07/31/2024] [Accepted: 08/19/2024] [Indexed: 10/12/2024]
Abstract
The parotid glands are the largest of the major salivary glands. They can harbour both benign and malignant tumours. Preoperative work-up relies on MR images and fine needle aspiration biopsy, but these diagnostic tools have low sensitivity and specificity, often leading to surgery for diagnostic purposes. The aim of this paper is (1) to develop a machine learning algorithm based on MR images characteristics to automatically classify parotid gland tumours and (2) compare its results with the diagnoses of junior and senior radiologists in order to evaluate its utility in routine practice. While automatic algorithms applied to parotid tumours classification have been developed in the past, we believe that our study is one of the first to leverage four different MRI sequences and propose a comparison with clinicians. In this study, we leverage data coming from a cohort of 134 patients treated for benign or malignant parotid tumours. Using radiomics extracted from the MR images of the gland, we train a random forest and a logistic regression to predict the corresponding histopathological subtypes. On the test set, the best results are given by the random forest: we obtain a 0.720 accuracy, a 0.860 specificity, and a 0.720 sensitivity over all histopathological subtypes, with an average AUC of 0.838. When considering the discrimination between benign and malignant tumours, the algorithm results in a 0.760 accuracy and a 0.769 AUC, both on test set. Moreover, the clinical experiment shows that our model helps to improve diagnostic abilities of junior radiologists as their sensitivity and accuracy raised by 6 % when using our proposed method. This algorithm may be useful for training of physicians. Radiomics with a machine learning algorithm may help improve discrimination between benign and malignant parotid tumours, decreasing the need for diagnostic surgery. Further studies are warranted to validate our algorithm for routine use.
Collapse
Affiliation(s)
- Samy Ammari
- Biomaps, UMR1281 INSERM, CEA, CNRS, Université Paris-Saclay, 94805, Villejuif, France
- Department of Imaging, Gustave Roussy Cancer Campus, Université Paris Saclay, 94805, Villejuif, France
| | - Arnaud Quillent
- Centre de Vision Numérique, OPIS, CentraleSupélec, Inria, Université Paris-Saclay, 91190, Gif-sur-Yvette, France
| | - Víctor Elvira
- School of Mathematics, University of Edinburgh, Edinburgh, EH9 3FD, UK
| | - François Bidault
- Biomaps, UMR1281 INSERM, CEA, CNRS, Université Paris-Saclay, 94805, Villejuif, France
- Department of Imaging, Gustave Roussy Cancer Campus, Université Paris Saclay, 94805, Villejuif, France
| | - Gabriel C T E Garcia
- Department of Imaging, Gustave Roussy Cancer Campus, Université Paris Saclay, 94805, Villejuif, France
| | - Dana M Hartl
- Department of Otolaryngology Head and Neck Surgery, Gustave Roussy Cancer Campus, Université Paris Saclay, 94805, Villejuif, France
| | - Corinne Balleyguier
- Biomaps, UMR1281 INSERM, CEA, CNRS, Université Paris-Saclay, 94805, Villejuif, France
- Department of Imaging, Gustave Roussy Cancer Campus, Université Paris Saclay, 94805, Villejuif, France
| | - Nathalie Lassau
- Biomaps, UMR1281 INSERM, CEA, CNRS, Université Paris-Saclay, 94805, Villejuif, France
- Department of Imaging, Gustave Roussy Cancer Campus, Université Paris Saclay, 94805, Villejuif, France
| | - Émilie Chouzenoux
- Centre de Vision Numérique, OPIS, CentraleSupélec, Inria, Université Paris-Saclay, 91190, Gif-sur-Yvette, France.
| |
Collapse
|
26
|
Sage A. Performance analysis of 2D and 3D image features for computer-assisted speech diagnosis of dental sibilants in Polish children. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2025; 264:108716. [PMID: 40133017 DOI: 10.1016/j.cmpb.2025.108716] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/07/2024] [Revised: 02/25/2025] [Accepted: 03/06/2025] [Indexed: 03/27/2025]
Abstract
BACKGROUND AND OBJECTIVE Sigmatism is a speech disorder concerning sibilants, and its diagnosis affects many Polish children of preschool age. The success of therapy often depends on early and accurate diagnosis. This paper presents research findings on using 2D and 3D (time-related) visual features to analyze the place of articulation, sibilance (the character of a gap between teeth that allows the articulation of sibilant sounds), and tongue positioning in four of twelve Polish sibilants:/s/,/z/,/ʦ/, and/dz/. METHODS A dedicated data acquisition system captured the stereovision stream during the speech therapy examination (201 speakers aged 4-8). The material contains 23 words and four logatomes. This study introduces 3D texture and shape features extracted for the mouth, lips, and tongue. The third dimension is the time of articulation, and the volumes reflect the movements of speech organs. The research compares the usability of 3D mode to a 2D approach (mouth texture features; mouth, lips, and tongue shape parameters) described in previous works. The statistical analysis includes Mann-Whitney U test to indicate the significant differences between selected articulation patterns for each sibilant and pronunciation aspect (considering p<0.05). RESULTS Overall outcomes suggest the dominance of 3D time-related statistically significant features, especially describing the shape of a tongue. Analysis considering features with at least medium effect size showed that 3D features differentiate dental and interdental articulation in case of/s/,/z/, and/ʦ/, while in case of/dz/ significant parameters were 2D. The 3D mode prevails also in terms of sibilance: analysis of sounds/z/ and/ʦ/ results in 3D features only, but for/s/ and/dz/ outcomes include both 3D and 2D parameters. Analysis of the tongue positioning during articulation in terms of at least moderate effect size suggests a presence of features only in the case of affricates:/ʦ/ (3D features) and/dz/ (2D features). All parameters with at least medium effect size describe the shape of the tongue. CONCLUSIONS This research proves the potential of visual data in building computer-aided speech diagnosis systems using non-contact recording tools. It highlights the usability of a 3D approach introduced in this paper. Results also emphasize the importance of tongue movement analysis.
Collapse
Affiliation(s)
- Agata Sage
- Faculty of Biomedical Engineering, Silesian University of Technology, Roosevelta 40, Zabrze, 41-800, Silesia, Poland.
| |
Collapse
|
27
|
Balagurunathan Y, Choi JW, Thompson Z, Jain M, Locke FL. Radiomic Features Prognosticate Treatment Response in CAR-T Cell Therapy. Cancers (Basel) 2025; 17:1832. [PMID: 40507312 PMCID: PMC12153729 DOI: 10.3390/cancers17111832] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/15/2025] [Revised: 05/22/2025] [Accepted: 05/27/2025] [Indexed: 06/16/2025] Open
Abstract
Background: Diffuse large B-cell lymphomas (DLBCLs) are the most common, aggressive disease form that accounts for 30% of all lymphoma cases. Identifying patients who will respond to these advanced cell-based therapies is an unaddressed challenge. Methods: We propose to develop a radiomics- (quantitative image metric) based signature on the patients' imaging scans (positron emission tomography/computed tomography, PET/CT) and use these metrics to prognosticate response to axi-cel (axicabtagene ciloleucel), autologous CD19 chimeric antigen receptor (CAR) T-cell (CAR-T) therapy. We curated a cohort of 155 patients with relapsed/refractory (R/R) DLBCL who were treated with axi-cel. Using their baseline image scan (PET/CT), the largest lesions related to nodal/extra-nodal disease were identified and characterized using imaging metrics (radiomics). We used principal component (PC) analysis to reduce the dimensionality of these features across the functional categories (size, shape, and texture). We evaluated the prognostic ability of radiomic-based PC to treatment response (1-year), measured by overall survival (OS) and progression-free survival (PFS). Results: We found that radiomic PC was prognostic of overall survival (Shape-PC, q < 0.013/0.0108, Size-PC, q < 0.003/0.0088), in CT/PET, respectively. In comparison, the metabolic tumor volume (MTV) was prognostic (q < 0.0002/0.0007). The radiomic PCs across the functional categories showed moderate to weak correlation with MTV, Spearman's ρ of 0.44/0.35/0.27, and 0.45/0.36/0.55 for Size/Shape/Texture-PC1 obtained on PET and CT, respectively. Conclusions: We found radiomic PC based on size and shape metrics that are able to prognosticate treatment response to CAR-T therapy.
Collapse
Affiliation(s)
- Yoganand Balagurunathan
- Department of Machine Learning, H Lee Moffitt Cancer Center, Tampa, FL 33612, USA
- Department of Diagnostic & Interventional Radiology, H Lee Moffitt Cancer Center, Tampa, FL 33612, USA;
| | - Jung W. Choi
- Department of Diagnostic & Interventional Radiology, H Lee Moffitt Cancer Center, Tampa, FL 33612, USA;
| | - Zachary Thompson
- Department of Biostatistics & Bioinformatics, H Lee Moffitt Cancer Center, Tampa, FL 33612, USA;
| | - Michael Jain
- Department of Blood and Marrow Transplant, H Lee Moffitt Cancer Center, Tampa, FL 33612, USA;
| | - Frederick L. Locke
- Department of Blood and Marrow Transplant, H Lee Moffitt Cancer Center, Tampa, FL 33612, USA;
| |
Collapse
|
28
|
Zhang M, Zhang Q, Wang X, Peng X, Chen J, Yang H. Prediction of clinical stages of cervical cancer via machine learning integrated with clinical features and ultrasound-based radiomics. Sci Rep 2025; 15:18862. [PMID: 40442164 PMCID: PMC12122849 DOI: 10.1038/s41598-025-03170-w] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/25/2024] [Accepted: 05/19/2025] [Indexed: 06/02/2025] Open
Abstract
To investigate the prediction of a model constructed by combining machine learning (ML) with clinical features and ultrasound radiomics in the clinical staging of cervical cancer. General clinical and ultrasound data of 227 patients with cervical cancer who received transvaginal ultrasonography were retrospectively analyzed. The region of interest (ROI) radiomics profiles of the original image and derived image were retrieved and profile screening was performed. The chosen profiles were employed in radiomics model and Radscore formula construction. Prediction models were developed utilizing several ML algorithms by Python based on an integrated dataset of clinical features and ultrasound radiomics. Model performances were evaluated via AUC. Plot calibration curves and clinical decision curves were used to assess model efficacy. The model developed by support vector machine (SVM) emerged as the superior model. Integrating clinical characteristics with ultrasound radiomics, it showed notable performance metrics in both the training and validation datasets. Specifically, in the training set, the model obtained an AUC of 0.88 (95% Confidence Interval (CI): 0.83-0.93), alongside a 0.84 accuracy, 0.68 sensitivity, and 0.91 specificity. When validated, the model maintained an AUC of 0.77 (95% CI: 0.63-0.88), with 0.77 accuracy, 0.62 sensitivity, and 0.83 specificity. The calibration curve aligned closely with the perfect calibration line. Additionally, based on the clinical decision curve analysis, the model offers clinical utility over wide-ranging threshold possibilities. The clinical- and radiomics-based SVM model provides a noninvasive tool for predicting cervical cancer stage, integrating ultrasound radiomics and key clinical factors (age, abortion history) to improve risk stratification. This approach could guide personalized treatment (surgery vs. chemoradiation) and optimize staging accuracy, particularly in resource-limited settings where advanced imaging is scarce.
Collapse
Affiliation(s)
- Maochun Zhang
- Affiliated Hospital, Jinan University, Guangzhou, 510630, China
- Department of Health Management Center, Affiliated Hospital of North Sichuan Medical College, Nanchong, 637000, China
| | - Qing Zhang
- Department of Ultrasound, Affiliated Hospital of North Sichuan Medical College, Nanchong, 637000, China
| | - Xueying Wang
- Department of Ultrasound, Affiliated Hospital of North Sichuan Medical College, Nanchong, 637000, China
| | - Xiaoli Peng
- Department of Ultrasound, Affiliated Hospital of North Sichuan Medical College, Nanchong, 637000, China
| | - Jiao Chen
- Department of Obstetrics and Gynecology, Affiliated Hospital of North Sichuan Medical College, Nanchong, 637000, China
| | - Hanfeng Yang
- Affiliated Hospital, Jinan University, Guangzhou, 510630, China.
- Department of Radiology, Affiliated Hospital of North Sichuan Medical College, Nanchong, 637000, China.
| |
Collapse
|
29
|
Kumar R, Sporn K, Khanna A, Paladugu P, Gowda C, Ngo A, Jagadeesan R, Zaman N, Tavakkoli A. Integrating Radiogenomics and Machine Learning in Musculoskeletal Oncology Care. Diagnostics (Basel) 2025; 15:1377. [PMID: 40506947 PMCID: PMC12155258 DOI: 10.3390/diagnostics15111377] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/04/2025] [Revised: 05/21/2025] [Accepted: 05/23/2025] [Indexed: 06/16/2025] Open
Abstract
Musculoskeletal tumors present a diagnostic challenge due to their rarity, histological diversity, and overlapping imaging features. Accurate characterization is essential for effective treatment planning and prognosis, yet current diagnostic workflows rely heavily on invasive biopsy and subjective radiologic interpretation. This review explores the evolving role of radiogenomics and machine learning in improving diagnostic accuracy for bone and soft tissue tumors. We examine integrating quantitative imaging features from MRI, CT, and PET with genomic and transcriptomic data to enable non-invasive tumor profiling. AI-powered platforms employing convolutional neural networks (CNNs) and radiomic texture analysis show promising results in tumor grading, subtype differentiation (e.g., Osteosarcoma vs. Ewing sarcoma), and predicting mutation signatures (e.g., TP53, RB1). Moreover, we highlight the use of liquid biopsy and circulating tumor DNA (ctDNA) as emerging diagnostic biomarkers, coupled with point-of-care molecular assays, to enable early and accurate detection in low-resource settings. The review concludes by discussing translational barriers, including data harmonization, regulatory challenges, and the need for multi-institutional datasets to validate AI-based diagnostic frameworks. This article synthesizes current advancements and provides a forward-looking view of precision diagnostics in musculoskeletal oncology.
Collapse
Affiliation(s)
- Rahul Kumar
- Department of Biochemistry and Molecular Biology, University of Miami Miller School of Medicine, Miami, FL 33136, USA; (C.G.); (A.N.)
| | - Kyle Sporn
- Norton College of Medicine, Upstate Medical University, Syracuse, NY 13210, USA;
| | - Akshay Khanna
- Sidney Kimmel Medical College, Thomas Jefferson University, Philadelphia, PA 19107, USA; (A.K.); (P.P.)
| | - Phani Paladugu
- Sidney Kimmel Medical College, Thomas Jefferson University, Philadelphia, PA 19107, USA; (A.K.); (P.P.)
- Brigham and Women’s Hospital, Boston, MA 02115, USA
| | - Chirag Gowda
- Department of Biochemistry and Molecular Biology, University of Miami Miller School of Medicine, Miami, FL 33136, USA; (C.G.); (A.N.)
| | - Alex Ngo
- Department of Biochemistry and Molecular Biology, University of Miami Miller School of Medicine, Miami, FL 33136, USA; (C.G.); (A.N.)
| | - Ram Jagadeesan
- Whiting School of Engineering, Johns Hopkins University, Baltimore, MD 21218, USA;
- Cisco AI Systems, Cisco Inc., San Jose, CA 95134, USA
| | - Nasif Zaman
- Department of Computer Science, University of Nevada Reno, Reno, NV 89557, USA; (N.Z.); (A.T.)
| | - Alireza Tavakkoli
- Department of Computer Science, University of Nevada Reno, Reno, NV 89557, USA; (N.Z.); (A.T.)
| |
Collapse
|
30
|
Khosla D, Singh G, Thakur V, Kapoor R, Gupta R, Kumar D, Madan R, Goyal S, Oinam AS, Rana SS. Survival prediction using CT-based radiomic features in patients of pancreatic cancer treated with chemotherapy followed by SBRT. J Cancer Res Ther 2025:01363817-990000000-00110. [PMID: 40413786 DOI: 10.4103/jcrt.jcrt_1595_24] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/20/2024] [Accepted: 01/29/2025] [Indexed: 05/27/2025]
Abstract
PURPOSE Owing to the heterogeneous nature of pancreatic cancer, clinical prediction models are not sufficient for prognostication. Radiomics is quantitative noninvasive assessment performed from imaging which by means of mathematical models can decode tumor phenotype and further predict disease and treatment outcomes. This pilot study aims to investigate the association of CT-based radiomic features with overall survival (OS) in pancreatic cancer patients treated with stereotactic body radiation therapy (SBRT). MATERIALS AND METHODS This study was conducted in patients of borderline resectable and locally advanced pancreatic cancer at our institute from January 2021 to December 2022. Ten patients underwent neoadjuvant chemotherapy, followed by SBRT with doses ranging from 33 Gy to 42 Gy administered in 5-6 fractions. Subsequent treatment included additional chemotherapy and evaluation for potential surgery. Radiomic features were extracted from planning CT images, and statistical analysis was performed using R software. RESULTS Out of 10 patients receiving neoadjuvant chemotherapy followed by SBRT, three underwent surgery. The duration of median follow-up was 15 months, and the median OS was 25 months. A total of 851 radiomic features including 107 original images features and 93 × 8 wavelet-based features were extracted. Using Lasso Cox regression, four wavelet-based features were found to influence the overall survival. CONCLUSIONS The present study demonstrates that CT-based radiomic features can be a promising tool in predicting survival and in addition to clinical parameters can provide detailed prognostic information that can facilitate personalized patient care. However, clinical implications of this radiomic analysis need a larger number of patients to validate the results.
Collapse
Affiliation(s)
- Divya Khosla
- Department of Radiotherapy and Oncology, Regional Cancer Centre, Postgraduate Institute of Medical Education and Research (PGIMER), Chandigarh, India
| | - Gaganpreet Singh
- Department of Radiotherapy and Oncology, Regional Cancer Centre, Postgraduate Institute of Medical Education and Research (PGIMER), Chandigarh, India
| | - Vandana Thakur
- Department of Radiotherapy and Oncology, Regional Cancer Centre, Postgraduate Institute of Medical Education and Research (PGIMER), Chandigarh, India
| | - Rakesh Kapoor
- Department of Radiotherapy and Oncology, Regional Cancer Centre, Postgraduate Institute of Medical Education and Research (PGIMER), Chandigarh, India
| | - Rajesh Gupta
- Department of GI Surgery, HPB, and Liver Transplantation, Postgraduate Institute of Medical Education and Research (PGIMER), Chandigarh, India
| | - Divyesh Kumar
- Department of Radiotherapy and Oncology, Regional Cancer Centre, Postgraduate Institute of Medical Education and Research (PGIMER), Chandigarh, India
| | - Renu Madan
- Department of Radiotherapy and Oncology, Regional Cancer Centre, Postgraduate Institute of Medical Education and Research (PGIMER), Chandigarh, India
| | - Shikha Goyal
- Department of Radiotherapy and Oncology, Regional Cancer Centre, Postgraduate Institute of Medical Education and Research (PGIMER), Chandigarh, India
| | - Arun S Oinam
- Department of Radiotherapy and Oncology, Regional Cancer Centre, Postgraduate Institute of Medical Education and Research (PGIMER), Chandigarh, India
| | - Surinder S Rana
- Department of Gastroenterology, Postgraduate Institute of Medical Education and Research (PGIMER), Chandigarh, India
| |
Collapse
|
31
|
Cui J, Wang P, Zhang X, Zhang P, Yin Y, Bai R. Noninvasive prediction of failure of the conservative treatment in lateral epicondylitis by clinicoradiological features and elbow MRI radiomics based on interpretable machine learning: a multicenter cohort study. J Orthop Surg Res 2025; 20:503. [PMID: 40410921 PMCID: PMC12103030 DOI: 10.1186/s13018-025-05901-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/19/2025] [Accepted: 05/09/2025] [Indexed: 05/25/2025] Open
Abstract
OBJECTIVES To develop and validate an interpretable machine learning model based on clinicoradiological features and radiomic features based on magnetic resonance imaging (MRI) to predict the failure of conservative treatment in lateral epicondylitis (LE). METHODS This retrospective study included 420 patients with LE from three hospitals, divided into a training cohort (n = 245), an internal validation cohort (n = 115), and an external validation cohort (n = 60). Patients were categorized into conservative treatment failure (n = 133) and conservative treatment success (n = 287) groups based on the outcome of conservative treatment. We developed two predictive models: one utilizing clinicoradiological features, and another integrating clinicoradiological and radiomic features. Seven machine learning algorithms were evaluated to determine the optimal model for predicting the failure of conservative treatment. Model performance was assessed using ROC, and model interpretability was examined using SHapley Additive exPlanations (SHAP). RESULTS The LightGBM algorithm was selected as the optimal model because of its superior performance. The combined model demonstrated enhanced predictive accuracy with an area under the ROC curve (AUC) of 0.96 (95% CI: 0.91, 0.99) in the external validation cohort. SHAP analysis identified the radiological feature "CET coronal tear size" and the radiomic feature "AX_log-sigma-1-0-mm-3D_glszm_SmallAreaEmphasis" as key predictors of conservative treatment failure. CONCLUSIONS We developed and validated an interpretable LightGBM machine learning model that integrates clinicoradiological and radiomic features to predict the failure of conservative treatment in LE. The model demonstrates high predictive accuracy and offers valuable insights into key prognostic factors.
Collapse
Affiliation(s)
- Jianing Cui
- Department of Radiology, Beijing Jishuitan Hospital, Capital Medical University, Beijing, 100035, China
| | - Ping Wang
- Department of Radiology, Beijing Jishuitan Hospital, Capital Medical University, Beijing, 100035, China
| | - Xiaodong Zhang
- Department of Radiology, The Third Affiliated Hospital, Southern Medical University, Zhongshan Avenue West, Tianhe District, Guangzhou, 510515, China
| | - Ping Zhang
- Department of Radiology, Beijing Geriatric Hospital, Beijing, 100095, China
| | - Yuming Yin
- Department of Radiology, Pomona Valley Hospital Medical Center, Pomona, CA, 91767, USA
| | - Rongjie Bai
- Department of Radiology, Beijing Jishuitan Hospital, Capital Medical University, Beijing, 100035, China.
| |
Collapse
|
32
|
Yuan E, Chen Y, Ye L, He B, He C, Ma J, Yang T, Zeng H, Yang L, Yao J, Song B. Enhanced staging of renal cell carcinoma using tumor morphology features: model development and multi-source validation. NPJ Digit Med 2025; 8:305. [PMID: 40413285 PMCID: PMC12103548 DOI: 10.1038/s41746-025-01723-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/06/2025] [Accepted: 05/15/2025] [Indexed: 05/27/2025] Open
Abstract
Preoperative detection of pT3a invasion in non-metastatic renal cell carcinoma (RCC) remains challenging with CT. This study developed and validated radiomic models using preoperative CT to identify pT3a invasions. Six models were trained and internally validated via nested cross-validation on 999 patients from one hospital. External validation included 313 patients from two hospitals and 204 patients from four TCIA datasets. A multi-reader multi-case study with seven radiologists evaluated the model's incremental value. The morphology model achieved the highest internal AUC (0.867, 95% CI: 0.866-0.869) and maintained performance in external validations (AUC = 0.895 and 0.842). When used as a second reader, it significantly improved junior radiologists' sensitivity and discrimination (AUC: 0.790 vs. 0.831, p < 0.001) without compromising specificity. This study demonstrates that CT-based radiomic models, particularly the morphology model, can reliably detect pT3a invasion and enhance diagnostic accuracy for junior radiologists, offering potential clinical utility in preoperative staging.
Collapse
Affiliation(s)
- Enyu Yuan
- Department of Radiology, West China Hospital, Sichuan University, Chengdu, 610041, China
| | - Yuntian Chen
- Department of Radiology, West China Hospital, Sichuan University, Chengdu, 610041, China
| | - Lei Ye
- Department of Radiology, West China Hospital, Sichuan University, Chengdu, 610041, China
| | - Ben He
- Department of Urology, The Third People's Hospital of Chengdu/The Affiliated Hospital of Southwest Jiaotong University, Chengdu, 610014, China
| | - ChunLei He
- Department of Radiology, West China Hospital, Sichuan University, Chengdu, 610041, China
- Department of Radiology, Sanya People's Hospital, Sanya, China
| | - Junchao Ma
- Department of Radiology, West China Hospital, Sichuan University, Chengdu, 610041, China
| | - Ting Yang
- Department of Radiology, West China Hospital, Sichuan University, Chengdu, 610041, China
| | - Hao Zeng
- Department of Urology, West China Hospital, Sichuan University, Chengdu, 610041, China
| | - Ling Yang
- Department of Radiology, West China Hospital, Sichuan University, Chengdu, 610041, China.
| | - Jin Yao
- Department of Radiology, West China Hospital, Sichuan University, Chengdu, 610041, China.
| | - Bin Song
- Department of Radiology, West China Hospital, Sichuan University, Chengdu, 610041, China.
- Department of Radiology, Sanya People's Hospital, Sanya, China.
| |
Collapse
|
33
|
Xiang Z, Yu X, Lin S, Wang D, Huang W, Fu W, Zhu X, Shao L, Wu J, Zheng Q, Ai Y, Yang X, Guo M, Jin X. Deep learning dosiomics for the pretreatment prediction of radiation dermatitis in nasopharyngeal carcinoma patients treated with radiotherapy. Radiother Oncol 2025; 209:110951. [PMID: 40412532 DOI: 10.1016/j.radonc.2025.110951] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/11/2024] [Revised: 05/11/2025] [Accepted: 05/21/2025] [Indexed: 05/27/2025]
Abstract
PURPOSE To develop a combined dosiomics and deep learning (DL) model for predicting radiation dermatitis (RD) of grade ≥ 2 in patients with nasopharyngeal carcinoma (NPC) after radiation therapy (RT) based on radiation dose distribution. MATERIALS AND METHODS A retrospective study was performed with 290 NPC patients treated with RT from two medical centers. The patients were categorized into three groups: a training set (n = 167), an internal validation set (n = 72), and an external validation set (n = 51), respectively. Dosiomic features, in conjunction with DL features derived from convolutional neural networks, were extracted and analyzed from the radiation dose distribution to construct an end-to-end model and facilitate the prediction of RD. The efficacy of the developed models was assessed and compared using the area under curve (AUC) of the receiver operating characteristic (ROC) curves. RESULTS The XGBoost model with finally screened 25 dosiomic features achieved the best AUC of 0.751 and 0.746 in the internal and external validation sets, respectively. DL model with ResNet-34 achieved the best AUC of 0.820 and 0.812 in the internal and external validation sets, respectively. Combining DL and dosiomic features improved the AUC to 0.863 and 0.832 in the internal and external validation sets, respectively. Nomogram integrating DL, dosiomic features, and clinical factors achieved an AUC of 0.945, 0.916, and 0.832 in the training, internal, and external validation sets, respectively. CONCLUSION The integration of DL, dosiomics and clinical features is feasible and effective for predicting RD, thereby enhancing the management of NPC patients treated with RT.
Collapse
Affiliation(s)
- Ziqing Xiang
- Medical Engineering and Equipment Department, 2nd Affiliated Hospital of Wenzhou Medical University, Wenzhou 325000, China; Department of Radiotherapy Center, 1st Affiliated Hospital of Wenzhou Medical University, Wenzhou 325000, China
| | - Xianwen Yu
- Department of Radiotherapy Center, 1st Affiliated Hospital of Wenzhou Medical University, Wenzhou 325000, China; Cixi Biomedical Research Institute, Wenzhou Medical University, Zhejiang 315000, China
| | - Sunzhong Lin
- Medical Engineering and Equipment Department, 2nd Affiliated Hospital of Wenzhou Medical University, Wenzhou 325000, China
| | - Dong Wang
- Department of Radiotherapy Center, 1st Affiliated Hospital of Wenzhou Medical University, Wenzhou 325000, China
| | - Weiqian Huang
- Department of Radiotherapy Center, 1st Affiliated Hospital of Wenzhou Medical University, Wenzhou 325000, China
| | - Wen Fu
- Department of Radiotherapy Center, 1st Affiliated Hospital of Wenzhou Medical University, Wenzhou 325000, China
| | - Xuanxuan Zhu
- Department of Radiotherapy Center, 1st Affiliated Hospital of Wenzhou Medical University, Wenzhou 325000, China
| | - Li Shao
- Department of Radiotherapy Center, 1st Affiliated Hospital of Wenzhou Medical University, Wenzhou 325000, China
| | - Jianping Wu
- Department of Radiotherapy Center, 1st Affiliated Hospital of Wenzhou Medical University, Wenzhou 325000, China; Department of Radiotherapy, The Quzhou Affiliated Hospital of Wenzhou Medical University, Quzhou People's Hospital, Quzhou 324000, China
| | - Qiao Zheng
- Department of Radiotherapy Center, 1st Affiliated Hospital of Wenzhou Medical University, Wenzhou 325000, China
| | - Yao Ai
- Department of Radiotherapy Center, 1st Affiliated Hospital of Wenzhou Medical University, Wenzhou 325000, China
| | - Xujing Yang
- Department of Radiotherapy Center, 1st Affiliated Hospital of Wenzhou Medical University, Wenzhou 325000, China.
| | - Mingrou Guo
- Department of Radiotherapy Center, 1st Affiliated Hospital of Wenzhou Medical University, Wenzhou 325000, China.
| | - Xiance Jin
- Department of Radiotherapy Center, 1st Affiliated Hospital of Wenzhou Medical University, Wenzhou 325000, China; School of Basic Medical Science, Wenzhou Medical University, Wenzhou 325000, China.
| |
Collapse
|
34
|
Wang ZD, Nan HJ, Li SX, Li LH, Liu ZC, Guo HH, Li L, Liu SY, Li H, Bai YL, Dang XW. Development and validation of a radiomics-based prediction model for variceal bleeding in patients with Budd-Chiari syndrome-related gastroesophageal varices. World J Gastroenterol 2025; 31:104563. [DOI: 10.3748/wjg.v31.i19.104563] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 12/24/2024] [Revised: 03/24/2025] [Accepted: 04/27/2025] [Indexed: 05/21/2025] Open
Abstract
BACKGROUND Budd-Chiari syndrome (BCS) is caused by obstruction of the hepatic veins or suprahepatic inferior vena cava, leading to portal hypertension and the development of gastroesophageal varices (GEVs), which are associated with an increased risk of bleeding. Existing risk models for variceal bleeding in cirrhotic patients have limited applicability to BCS due to differences in pathophysiology. Radiomics, as a noninvasive technique, holds promise as a tool for more accurate prediction of bleeding risk in BCS-related GEVs.
AIM To develop and validate a personalized risk model for predicting variceal bleeding in BCS patients with GEVs.
METHODS We retrospectively analyzed clinical data from 444 BCS patients with GEVs in two centers. Radiomic features were extracted from portal venous phase computed tomography (CT) scans. A training cohort of 334 patients was used to develop the model, with 110 patients serving as an external validation cohort. LASSO Cox regression was used to select radiomic features for constructing a radiomics score (Radscore). Univariate and multivariate Cox regression identified independent clinical predictors. A combined radiomics + clinical (R + C) model was developed using stepwise regression. Model performance was assessed using the area under the receiver operating characteristic curve (AUC), calibration plots, and decision curve analysis (DCA), with external validation to evaluate generalizability.
RESULTS The Radscore comprised four hepatic and six splenic CT features, which predicted the risk of variceal bleeding. Multivariate analysis identified invasive treatment to relieve hepatic venous outflow obstruction, anticoagulant therapy, and hemoglobin levels as independent clinical predictors. The R + C model achieved C-indices of 0.906 (training) and 0.859 (validation), outperforming the radiomics and clinical models alone (AUC: training 0.936 vs 0.845 vs 0.823; validation 0.876 vs 0.712 vs 0.713). DCA showed higher clinical net benefit across the thresholds. The model stratified patients into low-, medium- and high-risk groups with significant differences in bleeding rates (P < 0.001). An online tool is available at https://bcsvh.shinyapps.io/BCS_Variceal_Bleeding_Risk_Tool/.
CONCLUSION We developed and validated a novel radiomics-based model that noninvasively and conveniently predicted risk of variceal bleeding in BCS patients with GEVs, aiding early identification and management of high-risk patients.
Collapse
Affiliation(s)
- Ze-Dong Wang
- Department of Hepatopancreatobiliary Surgery, The First Affiliated Hospital of Zhengzhou University, Zhengzhou 450052, Henan Province, China
- Key Laboratory of Precision Diagnosis and Treatment in General Surgical (Hepatobiliary and Pancreatic) Diseases of Health Commission of Henan Province, The First Affiliated Hospital of Zhengzhou University, Zhengzhou 450052, Henan Province, China
- Henan Province Engineering Research Center of Minimally Invasive Diagnosis and Treatment of Hepatobiliary and Pancreatic Diseases, The First Affiliated Hospital of Zhengzhou University, Zhengzhou 450052, Henan Province, China
- Budd-Chiari Syndrome Diagnosis and Treatment Center of Henan Province, The First Affiliated Hospital of Zhengzhou University, Zhengzhou 450052, Henan Province, China
| | - Hui-Jie Nan
- Department of Hematology, Zhengzhou University People's Hospital and Henan Provincial People's Hospital, Zhengzhou 450003, Henan Province, China
| | - Su-Xin Li
- Department of Hepatopancreatobiliary Surgery, The First Affiliated Hospital of Zhengzhou University, Zhengzhou 450052, Henan Province, China
- Key Laboratory of Precision Diagnosis and Treatment in General Surgical (Hepatobiliary and Pancreatic) Diseases of Health Commission of Henan Province, The First Affiliated Hospital of Zhengzhou University, Zhengzhou 450052, Henan Province, China
- Henan Province Engineering Research Center of Minimally Invasive Diagnosis and Treatment of Hepatobiliary and Pancreatic Diseases, The First Affiliated Hospital of Zhengzhou University, Zhengzhou 450052, Henan Province, China
- Budd-Chiari Syndrome Diagnosis and Treatment Center of Henan Province, The First Affiliated Hospital of Zhengzhou University, Zhengzhou 450052, Henan Province, China
| | - Lu-Hao Li
- Department of Hepatopancreatobiliary Surgery, The First Affiliated Hospital of Zhengzhou University, Zhengzhou 450052, Henan Province, China
- Key Laboratory of Precision Diagnosis and Treatment in General Surgical (Hepatobiliary and Pancreatic) Diseases of Health Commission of Henan Province, The First Affiliated Hospital of Zhengzhou University, Zhengzhou 450052, Henan Province, China
- Henan Province Engineering Research Center of Minimally Invasive Diagnosis and Treatment of Hepatobiliary and Pancreatic Diseases, The First Affiliated Hospital of Zhengzhou University, Zhengzhou 450052, Henan Province, China
- Budd-Chiari Syndrome Diagnosis and Treatment Center of Henan Province, The First Affiliated Hospital of Zhengzhou University, Zhengzhou 450052, Henan Province, China
| | - Zhao-Chen Liu
- Department of Hepatopancreatobiliary Surgery, The First Affiliated Hospital of Zhengzhou University, Zhengzhou 450052, Henan Province, China
- Key Laboratory of Precision Diagnosis and Treatment in General Surgical (Hepatobiliary and Pancreatic) Diseases of Health Commission of Henan Province, The First Affiliated Hospital of Zhengzhou University, Zhengzhou 450052, Henan Province, China
- Henan Province Engineering Research Center of Minimally Invasive Diagnosis and Treatment of Hepatobiliary and Pancreatic Diseases, The First Affiliated Hospital of Zhengzhou University, Zhengzhou 450052, Henan Province, China
- Budd-Chiari Syndrome Diagnosis and Treatment Center of Henan Province, The First Affiliated Hospital of Zhengzhou University, Zhengzhou 450052, Henan Province, China
| | - Hua-Hu Guo
- Department of Hepatopancreatobiliary Surgery, The First Affiliated Hospital of Zhengzhou University, Zhengzhou 450052, Henan Province, China
- Key Laboratory of Precision Diagnosis and Treatment in General Surgical (Hepatobiliary and Pancreatic) Diseases of Health Commission of Henan Province, The First Affiliated Hospital of Zhengzhou University, Zhengzhou 450052, Henan Province, China
- Henan Province Engineering Research Center of Minimally Invasive Diagnosis and Treatment of Hepatobiliary and Pancreatic Diseases, The First Affiliated Hospital of Zhengzhou University, Zhengzhou 450052, Henan Province, China
- Budd-Chiari Syndrome Diagnosis and Treatment Center of Henan Province, The First Affiliated Hospital of Zhengzhou University, Zhengzhou 450052, Henan Province, China
| | - Lin Li
- Department of Hepatopancreatobiliary Surgery, The First Affiliated Hospital of Zhengzhou University, Zhengzhou 450052, Henan Province, China
- Key Laboratory of Precision Diagnosis and Treatment in General Surgical (Hepatobiliary and Pancreatic) Diseases of Health Commission of Henan Province, The First Affiliated Hospital of Zhengzhou University, Zhengzhou 450052, Henan Province, China
- Henan Province Engineering Research Center of Minimally Invasive Diagnosis and Treatment of Hepatobiliary and Pancreatic Diseases, The First Affiliated Hospital of Zhengzhou University, Zhengzhou 450052, Henan Province, China
- Budd-Chiari Syndrome Diagnosis and Treatment Center of Henan Province, The First Affiliated Hospital of Zhengzhou University, Zhengzhou 450052, Henan Province, China
| | - Sheng-Yan Liu
- Department of Hepatopancreatobiliary Surgery, The First Affiliated Hospital of Zhengzhou University, Zhengzhou 450052, Henan Province, China
- Key Laboratory of Precision Diagnosis and Treatment in General Surgical (Hepatobiliary and Pancreatic) Diseases of Health Commission of Henan Province, The First Affiliated Hospital of Zhengzhou University, Zhengzhou 450052, Henan Province, China
- Henan Province Engineering Research Center of Minimally Invasive Diagnosis and Treatment of Hepatobiliary and Pancreatic Diseases, The First Affiliated Hospital of Zhengzhou University, Zhengzhou 450052, Henan Province, China
- Budd-Chiari Syndrome Diagnosis and Treatment Center of Henan Province, The First Affiliated Hospital of Zhengzhou University, Zhengzhou 450052, Henan Province, China
| | - Hai Li
- Department of Hepatopancreatobiliary Surgery, Zhengzhou University People's Hospital and Henan Provincial People's Hospital, Zhengzhou 450003, Henan Province, China
| | - Yan-Liang Bai
- Department of Hematology, Zhengzhou University People's Hospital and Henan Provincial People's Hospital, Zhengzhou 450003, Henan Province, China
| | - Xiao-Wei Dang
- Department of Hepatopancreatobiliary Surgery, The First Affiliated Hospital of Zhengzhou University, Zhengzhou 450052, Henan Province, China
- Key Laboratory of Precision Diagnosis and Treatment in General Surgical (Hepatobiliary and Pancreatic) Diseases of Health Commission of Henan Province, The First Affiliated Hospital of Zhengzhou University, Zhengzhou 450052, Henan Province, China
- Henan Province Engineering Research Center of Minimally Invasive Diagnosis and Treatment of Hepatobiliary and Pancreatic Diseases, The First Affiliated Hospital of Zhengzhou University, Zhengzhou 450052, Henan Province, China
- Budd-Chiari Syndrome Diagnosis and Treatment Center of Henan Province, The First Affiliated Hospital of Zhengzhou University, Zhengzhou 450052, Henan Province, China
| |
Collapse
|
35
|
Tasci E, Zhuge Y, Zhang L, Ning H, Cheng JY, Miller RW, Camphausen K, Krauze AV. Radiomics and AI-Based Prediction of MGMT Methylation Status in Glioblastoma Using Multiparametric MRI: A Hybrid Feature Weighting Approach. Diagnostics (Basel) 2025; 15:1292. [PMID: 40428285 PMCID: PMC12110254 DOI: 10.3390/diagnostics15101292] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/24/2025] [Revised: 05/12/2025] [Accepted: 05/16/2025] [Indexed: 05/29/2025] Open
Abstract
Background/Objectives: Glioblastoma (GBM) is a highly aggressive primary central nervous system tumor with a median survival of 14 months. MGMT (O6-methylguanine-DNA methyltransferase) promoter methylation status is a key biomarker as a prognostic indicator and a predictor of chemotherapy response in GBM. Patients with MGMT methylated disease progress later and survive longer (median survival rate 22 vs. 15 months, respectively) as compared to patients with MGMT unmethylated disease. Patients with GBM undergo an MRI of the brain prior to diagnosis and following surgical resection for radiation therapy planning and ongoing follow-up. There is currently no imaging biomarker for GBM. Studies have attempted to connect MGMT methylation status to MRI imaging appearance to determine if brain MRI can be leveraged to provide MGMT status information non-invasively and more expeditiously. Methods: Artificial intelligence (AI) can identify MRI features that are not distinguishable to the human eye and can be linked to MGMT status. We employed the UPenn-GBM dataset patients for whom methylation status was available (n = 146), employing a novel radiomic method grounded in hybrid feature selection and weighting to predict MGMT methylation status. Results: The best MGMT classification and feature selection result obtained resulted in a mean accuracy rate value of 81.6% utilizing 101 selected features and five-fold cross-validation. Conclusions: This compared favorably with similar studies in the literature. Validation with external datasets remains critical to enhance generalizability and propagate robust results while reducing bias. Future directions include multi-channel data integration with radiomic features and deep and ensemble learning methods to improve predictive performance.
Collapse
Affiliation(s)
| | | | | | | | | | | | | | - Andra V. Krauze
- Radiation Oncology Branch, Center for Cancer Research, National Cancer Institute, National Institutes of Health, 9000 Rockville Pike, Building 10, CRC, Bethesda, MD 20892, USA; (E.T.); (Y.Z.); (L.Z.); (H.N.); (J.Y.C.); (R.W.M.); (K.C.)
| |
Collapse
|
36
|
Paetkau O, Tchistiakova E, Kirkby C. Multi-omic feature reliability of deformable image registration-based images. Biomed Phys Eng Express 2025; 11:037005. [PMID: 40354790 DOI: 10.1088/2057-1976/add73f] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/31/2025] [Accepted: 05/12/2025] [Indexed: 05/14/2025]
Abstract
Purpose. To evaluate the reliability of radiomic and dosiomic (multi-omic) features extracted from synthetic CT images generated using two commercially available deformable image registration workflows.Materials and Methods. Multi-omic features were extracted from organs at risk (OAR) contoured on a cohort of 58 head and neck (HN) radiotherapy patients. The contours were propagated from the planning CT to synthetic CTs of the final fraction cone-beam CT (CBCT) anatomy using MIM and Velocity deformable image registration workflows. The workflows were validated using radiation oncologist contours on the planning CT and final fraction CBCT according to TG-132 guidelines. The OAR volumes and mean dose on the synthetic CTs from two workflows were compared using a signed Wilcoxon rank test. In addition, the dose distributions were evaluated using a gamma analysis using clinical criteria. The multi-omic features were extracted using region-of-interest extraction on the OAR with the original and wavelet filters. The feature reliability was evaluated for four OAR: spinal cord, parotid glands, submandibular glands, and pharyngeal constrictors. The reliability was evaluated using the intraclass correlation coefficient (ICC) with features exceeding 0.75 considered moderately reliable.Results. The volume and mean OAR dose were found to be statistically similar between the MIM and Velocity synthetic CT workflows. In addition, the gamma analysis resulted in 83% of plans exceeding 95% gamma passing rate at 3%/3 mm criteria. Across all HN OAR multi-omic features, fewer radiomic features (21%) were found to be moderately reliable compared to dosiomic features (59%) between the two synthetic CT workflows. The HN OAR with the most moderately reliable features was the spinal cord (46% radiomic, 85% dosiomic).Conclusion. Radiomics features presented worse reliability compared to dosiomic features across different synthetic CT deformable image registration workflows. Care should be taken when implementing predictive models using features extracted from different synthetic CT workflows.
Collapse
Affiliation(s)
- Owen Paetkau
- Department of Physics and Astronomy University of Calgary, 2500, University Dr NW, Calgary, AB, T2N 1N4, Canada
| | - Ekaterina Tchistiakova
- Department of Physics and Astronomy University of Calgary, 2500, University Dr NW, Calgary, AB, T2N 1N4, Canada
| | - Charles Kirkby
- Department of Physics and Astronomy University of Calgary, 2500, University Dr NW, Calgary, AB, T2N 1N4, Canada
| |
Collapse
|
37
|
Pfaehler E, Schindele A, Dierks A, Busse C, Brumberg J, Kübler AC, Buck AK, Linz C, Lapa C, Brands RC, Kertels O. Value of PET radiomic features for diagnosis and reccurence prediction of newly diagnosed oral squamous cell carcinoma. Sci Rep 2025; 15:17475. [PMID: 40394092 DOI: 10.1038/s41598-025-02305-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/03/2024] [Accepted: 05/13/2025] [Indexed: 05/22/2025] Open
Abstract
Oral Squamous Cell Carcinoma (OSCC) represents more than 90% of oral cancers. The usefulness of radiomic features extracted from PET images of OSCC patients to predict tumor characteristics such as primary tumor stage (T-stage), or tumor grade has not been investigated yet. In this prospective study, 112 patients with newly diagnosed, treatment-naïve OSCC were included. Tumor segmentation was performed using three strategies, the majority vote of these segmentations was used to calculate 445 radiomic features. Features instable over segmentation methods and features highly correlated with volume, SUVmax, and SUVmean were eliminated. A Random Forest classifier was trained to predict T-stage, tumor grade, lymph node involvement, and tumor recurrence. Stratified 10-fold cross-validation was performed. Evaluation metrics such as accuracy and area under the curve (AUC) were reported. SHAP dependence plots were generated to understand classifier decisions. The classifier reached a mean cross-validation AUC of 0.83 for predicting T-stage, an AUC of 0.56 for the grading of the primary tumor, a mean AUC of 0.64 for lymph node involvement, and a mean AUC of 0.63 for recurrence. In patients with newly-diagnosed OSCC, radiomics might have some potential to predict T-stage. These results need to be validated in a larger patient cohort.
Collapse
Affiliation(s)
- Elisabeth Pfaehler
- Nuclear Medicine, Faculty of Medicine, University of Augsburg, Augsburg, Germany
| | - Andreas Schindele
- Nuclear Medicine, Faculty of Medicine, University of Augsburg, Augsburg, Germany
| | - Alexander Dierks
- Nuclear Medicine, Faculty of Medicine, University of Augsburg, Augsburg, Germany
| | - Cornelius Busse
- Department of Oral and Maxillofacial Plastic Surgery, University Hospital of Würzburg, Würzburg, Germany
| | - Joachim Brumberg
- Department of Nuclear Medicine, University Hospital of Freiburg, Freiburg, Germany
| | - Alexander C Kübler
- Department of Oral and Maxillofacial Plastic Surgery, University Hospital of Würzburg, Würzburg, Germany
| | - Andreas K Buck
- Department of Nuclear Medicine, University Hospital of Würzburg, Würzburg, Germany
| | - Christian Linz
- Department of Oral and Maxillofacial Plastic Surgery, University Hospital of Würzburg, Würzburg, Germany
- Department of Oral and Maxillofacial Plastic Surgery, University Hospital of Cologne, Cologne, Germany
| | - Constantin Lapa
- Nuclear Medicine, Faculty of Medicine, University of Augsburg, Augsburg, Germany.
- Bavarian Cancer Research Center, Erlangen, Germany.
| | - Roman C Brands
- Department of Oral and Maxillofacial Plastic Surgery, University Hospital of Würzburg, Würzburg, Germany
| | - Olivia Kertels
- Institute of Diagnostic and Interventional Neuroradiology, Klinikum rechts der Isar, School of Medicine and Health, Technical University of Munich, Munich, Germany
| |
Collapse
|
38
|
Nabavizadeh A, Familiar AM. Enhancing RAPNO: the need for standardized imaging heuristics and volumetric assessment. Neuroradiology 2025:10.1007/s00234-025-03641-x. [PMID: 40377668 DOI: 10.1007/s00234-025-03641-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/22/2025] [Accepted: 05/05/2025] [Indexed: 05/18/2025]
Affiliation(s)
- Ali Nabavizadeh
- University of Pennsylvania, Philadelphia, USA.
- Children's Hospital of Philadelphia, Philadelphia, USA.
| | | |
Collapse
|
39
|
Ho WLJ, Fetisov N, Hall LO, Goldgof D, Schabath MB. Utilizing Clinicopathological and Radiomic Features for Risk Stratification of Lung Cancer Recurrence. Acad Radiol 2025:S1076-6332(25)00415-5. [PMID: 40379589 DOI: 10.1016/j.acra.2025.04.062] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/09/2025] [Revised: 04/21/2025] [Accepted: 04/24/2025] [Indexed: 05/19/2025]
Abstract
RATIONALE AND OBJECTIVES To predict recurrence risk in patients with surgically resected non-small cell lung cancer (NSCLC) using radiomic analysis and clinicopathological factors. MATERIALS AND METHODS 293 patients with surgically resected stage IA-IIIA NSCLC were analyzed. Patients were randomly stratified into development and test cohorts. The development cohort was further divided into training and validation subsets for feature selection and model building, then applied to the test cohort. Pre-treatment computed tomography were segmented and 107 pyRadiomics features were extracted from intratumoral and peritumoral regions. Feature selection was performed using the maximum relevance minimum redundancy algorithm and Lasso regression. Clinical covariates were selected using univariable Cox regression. Radiomic, clinical, and radiomic-clinical models were constructed using a logistic regression classifier and evaluated using area under the curve (AUC). Kaplan-Meier curves for 3-year recurrence-free survival were compared between high-risk and low-risk groups using the log-rank test. RESULTS 20 percent of patients experienced recurrence within 3 years. The radiomic-clinical model (AUC 0.77) outperformed the radiomic, clinical, and TNM stage models (AUC 0.76, 0.71, and 0.70, respectively) on the test set. Recurrence risk was five times higher in the high-risk group than the low-risk group (p<0.01) after stratification with the radiomic-clinical model. The most important features were regional lymph node metastases, the "GLDM Large Dependence Emphasis" texture, and the "Elongation" shape feature. CONCLUSION Radiomics analysis can be used in combination with clinicopathological features for effective recurrence risk stratification in patients with surgically resected NSCLC.
Collapse
Affiliation(s)
- Wai Lone J Ho
- University of South Florida, Morsani College of Medicine, Tampa, Florida (W.L.J.H.)
| | - Nikolai Fetisov
- Department of Computer Science and Engineering, University of South Florida, Tampa, Florida (N.F., L.O.H., D.G.)
| | - Lawrence O Hall
- Department of Computer Science and Engineering, University of South Florida, Tampa, Florida (N.F., L.O.H., D.G.)
| | - Dmitry Goldgof
- Department of Computer Science and Engineering, University of South Florida, Tampa, Florida (N.F., L.O.H., D.G.)
| | - Matthew B Schabath
- Department of Cancer Epidemiology, H. Lee Moffitt Cancer Center & Research Institute, Tampa, Florida (M.B.S.).
| |
Collapse
|
40
|
Hu C, Xu C, Chen J, Huang Y, Meng Q, Lin Z, Huang X, Chen L. Deep learning MRI-based radiomic models for predicting recurrence in locally advanced nasopharyngeal carcinoma after neoadjuvant chemoradiotherapy: a multi-center study. Clin Exp Metastasis 2025; 42:30. [PMID: 40369240 PMCID: PMC12078437 DOI: 10.1007/s10585-025-10349-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/25/2024] [Accepted: 04/28/2025] [Indexed: 05/16/2025]
Abstract
Local recurrence and distant metastasis were a common manifestation of locoregionally advanced nasopharyngeal carcinoma (LA-NPC) after neoadjuvant chemoradiotherapy (NACT). To validate the clinical value of MRI radiomic models based on deep learning for predicting the recurrence of LA-NPC patients. A total of 328 NPC patients from four hospitals were retrospectively included and divided into the training(n = 229) and validation (n = 99) cohorts randomly. Extracting 975 traditional radiomic features and 1000 deep radiomic features from contrast enhanced T1-weighted (T1WI + C) and T2-weighted (T2WI) sequences, respectively. Least absolute shrinkage and selection operator (LASSO) was applied for feature selection. Five machine learning classifiers were conducted to develop three models for LA-NPC prediction in training cohort, namely Model I: traditional radiomic features, Model II: combined the deep radiomic features with Model I, and Model III: combined Model II with clinical features. The predictive performance of these models were evaluated by receive operating characteristic (ROC) curve analysis, area under the curve (AUC), accuracy, sensitivity and specificity in both cohorts. The clinical characteristics in two cohorts showed no significant differences. Choosing 15 radiomic features and 6 deep radiomic features from T1WI + C. Choosing 9 radiomic features and 6 deep radiomic features from T2WI. In T2WI, the Model II based on Random forest (RF) (AUC = 0.87) performed best compared with other models in validation cohort. Traditional radiomic model combined with deep radiomic features shows excellent predictive performance. It could be used assist clinical doctors to predict curative effect for LA-NPC patients after NACT.
Collapse
Affiliation(s)
- Chunmiao Hu
- Department of Radiology, Clinical Oncology School of Fujian Medical University, Fujian Cancer Hospital, Fuzhou Fujian, 350014, China
| | - Congrui Xu
- Department of Clinical Medicine, Fujian Medical University, Fuzhou, 350122, Fujian, China
| | - Jiaxin Chen
- Department of Clinical Medicine, Fujian Medical University, Fuzhou, 350122, Fujian, China
| | - Yiling Huang
- Department of Clinical Medicine, Fujian Medical University, Fuzhou, 350122, Fujian, China
| | - Qingcheng Meng
- Department of Radiology, The Affiliated Tumor Hospital of Zhengzhou University & Henan Tumor Hospital, Zhengzhou Henan, 450000, China
| | - Zhian Lin
- Department of Radiation Oncology, Zhongshang Hospital Xiamen University, Xiamen Fujian, 361000, China
| | - Xinming Huang
- Department of Radiology, Fujian Medical University Union Hospital, Fuzhou Fujian, 350001, China
| | - Li Chen
- Department of Mathematics and Computer, School of Arts and Sciences, Fujian Medical University, University Town, No 1 North Xuefu Road, Fuzhou Fujian,, 350122, China.
| |
Collapse
|
41
|
Wu Q, Qiang W, Pan L, Cha T, Li Q, Gao Y, Qiu K, Xing W. Performance of MRI-based radiomics for prediction of residual disease status in patients with nasopharyngeal carcinoma after radical radiotherapy. Sci Rep 2025; 15:16758. [PMID: 40368928 PMCID: PMC12078595 DOI: 10.1038/s41598-025-00186-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/09/2024] [Accepted: 04/25/2025] [Indexed: 05/16/2025] Open
Abstract
The purpose of this study was to determine if habitat radiomic features extracted from pretherapy multi-sequence MRI predict residual status in patients with Nasopharyngeal Carcinoma (NPC) after radical radiotherapy. The retrospective study enrolled 179 primary NPC patients, divided into training and validation cohorts at a 7:3 ratio. K-means clustering was employed to segment T2WI, CE-T1WI and FSCE-T1WI images, creating habitats within the volume of interest. Identify relevant features that can recognize NPC residuals. In the training cohort, support vector machine (SVM) models were developed utilizing the radiomic features extracted from each habitat and the entire tumor, selecting the most predictive features for each sequence. SVM models were constructed by combining the optimal radiomic features from each sequences with clinical data. Model performance was compared and validated using receiver operating characteristic (ROC) curves, calibration curves and decision curve analysis (DCA), and differences between models were assessed using the DeLong test. The optimal clustering results revealed 4 habitats in FSCE-T1WI, while 2 habitats in both CE-T1WI and T2WI sequences. In the training cohort, we compared the predictive accuracy of SVM models based on different habitats and total tumor characteristics from three sequences, and found that the features from T2 Hab2, CE-T1 Hab1, and FSCE-T1 Hab4 images showed higher performance. Incorporation of habitat-based radiomic features and clinical variables significantly enhanced the predictive performance. The integrated model exhibits the optimal predictive performance, with the area under the curve (AUC) values of 0.921 (SEN = 0.821, SPE = 0.830) in the training cohort and 0.811 (SEN = 0.778, SPE = 0.722) in the validation cohort. Compared to conventional radiomics, habitat imaging features that distinguish intratumoral heterogeneity have higher predictive value, making them potential non-invasive biomarkers for assessing NPC residual after radiotherapy. Integration of multi-sequence MRI habitat radiomic with clinical parameters further improved predictive accuracy.
Collapse
Affiliation(s)
- Qinqin Wu
- Department of Radiology, The Third Affiliated Hospital of Soochow University, Changzhou First People's Hospital, Changzhou, 213003, Jiangsu, China
- Department of Radiology, Changzhou Xinbei District Sanjing People's Hospital, Changzhou, 213200, Jiangsu, China
| | - Weiguang Qiang
- Department of Oncology, The Third Affiliated Hospital of Soochow University, Changzhou First People's Hospital, Changzhou, 213003, Jiangsu, China
| | - Liang Pan
- Department of Radiology, The Third Affiliated Hospital of Soochow University, Changzhou First People's Hospital, Changzhou, 213003, Jiangsu, China
| | - Tingting Cha
- Department of Radiology, The Third Affiliated Hospital of Soochow University, Changzhou First People's Hospital, Changzhou, 213003, Jiangsu, China
| | - Qilin Li
- Department of Radiotherapy, The Third Affiliated Hospital of Soochow University, Changzhou First People's Hospital, Changzhou, 213003, Jiangsu, China
| | - Yang Gao
- Department of Radiology, Changzhou Xinbei District Sanjing People's Hospital, Changzhou, 213200, Jiangsu, China
| | - Kaiyang Qiu
- Department of Radiology, Changzhou Xinbei District Sanjing People's Hospital, Changzhou, 213200, Jiangsu, China
| | - Wei Xing
- Department of Radiology, The Third Affiliated Hospital of Soochow University, Changzhou First People's Hospital, Changzhou, 213003, Jiangsu, China.
| |
Collapse
|
42
|
Zhang P, Wei L, Nie Z, Hu P, Zheng J, Lv J, Cui T, Liu C, Lan X. Research on the developments of artificial intelligence in radiomics for oncology over the past decade: a bibliometric and visualized analysis. Discov Oncol 2025; 16:763. [PMID: 40366503 PMCID: PMC12078899 DOI: 10.1007/s12672-025-02590-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/21/2025] [Accepted: 05/06/2025] [Indexed: 05/15/2025] Open
Abstract
OBJECTIVE To assess the publications' bibliographic features and look into how the advancement of artificial intelligence (AI) and its subfields in radiomics has affected the growth of oncology. METHODS The researchers conducted a search in the Web of Science (WoS) for scientific publications in cancer pertaining to AI and radiomics, published in English from 1 January 2015 to 31 December 2024.The research included a scientometric methodology and comprehensive data analysis utilising scientific visualization tools, including the Bibliometrix R software package, VOSviewer, and CiteSpace. Bibliometric techniques utilised were co-authorship, co-citation, co-occurrence, citation burst, and performance Analysis. RESULTS The final study encompassed 4,127 publications authored by 5,026 individuals and published across 597 journals. China (2087;50.57%) and USA (850;20.6%) were the two most productive countries. The authors with the highest publication counts were Tian Jie (60) and Cuocolo Renato (30). Fudan University (169;4.09%) and Sun Yat-sen University (162;3.93%) were the most active institutions. The foremost journals were Frontiers in Oncology and Cancer. The predominant author keywords were radiomics, artificial intelligence, and oncology research. CONCLUSION Investigations into the integration of AI with radiomics in oncology remain nascent, with numerous studies concentrating on biology, diagnosis, treatment, and cancer risk evaluation.
Collapse
Affiliation(s)
- Pengyu Zhang
- Department of Urology, Qingdao Central Hospital, University of Health and Rehabilitation Sciences, Qingdao, 266042, People's Republic of China
- School of Qingdao Medical College, Qingdao University, 308 Ningxia Road, Qingdao, 266071, China
| | - Lili Wei
- Department of Urology, Qingdao Central Hospital, University of Health and Rehabilitation Sciences, Qingdao, 266042, People's Republic of China
| | - Zonglong Nie
- Department of Urology, Qingdao Central Hospital, University of Health and Rehabilitation Sciences, Qingdao, 266042, People's Republic of China
| | - Pengcheng Hu
- Department of Urology, Qingdao Central Hospital, University of Health and Rehabilitation Sciences, Qingdao, 266042, People's Republic of China
| | - Jilu Zheng
- Department of Urology, Qingdao Central Hospital, University of Health and Rehabilitation Sciences, Qingdao, 266042, People's Republic of China
| | - Ji Lv
- Department of Urology, Qingdao Central Hospital, University of Health and Rehabilitation Sciences, Qingdao, 266042, People's Republic of China.
| | - Tao Cui
- Department of Urology, Qingdao Central Hospital, University of Health and Rehabilitation Sciences, Qingdao, 266042, People's Republic of China.
| | - Chunlei Liu
- Department of Urology, Qingdao Central Hospital, University of Health and Rehabilitation Sciences, Qingdao, 266042, People's Republic of China.
| | - Xiaopeng Lan
- Department of Urology, Qingdao Central Hospital, University of Health and Rehabilitation Sciences, Qingdao, 266042, People's Republic of China.
| |
Collapse
|
43
|
Lussana F, Lanzarone E, Villa G, Mastropietro A, Caroli A, Scalco E. Reliability of radiomic analysis on multiparametric MRI for patients affected by autosomal dominant polycystic kidney disease. Sci Rep 2025; 15:16526. [PMID: 40360663 PMCID: PMC12075844 DOI: 10.1038/s41598-025-99982-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/06/2024] [Accepted: 04/24/2025] [Indexed: 05/15/2025] Open
Abstract
Autosomal dominant polycystic kidney disease (ADPKD) is a prevalent hereditary disorder characterized by the development and growth of fluid-filled cysts, resulting in a decline in kidney function. Beyond total kidney and cyst volume quantification, non-cystic tissue characterization by multi-parametric MRI (mp-MRI) and radiomics holds promise. We conducted a radiomic analysis based on reproducible and informative features extracted from non-cystic tissue on mp-MRI in ADPKD patients. T2-weighted (T2-w), T1-weighted MRI (T1-w), and IntraVoxel Incoherent Motion (IVIM) maps from Diffusion Weighted Imaging (DWI) were considered. The reliability of radiomic features was evaluated using five different segmentation methods. The impact of segmentation variability on radiomic reproducibility was assessed through Intraclass Correlation Coefficients (ICC), and a preliminary correlation analysis with relevant clinical parameters, such as age and eGFR, was also performed. The results from 14 patients indicate that radiomic features derived from IVIM maps exhibit greater reliability compared to features from T1-w and T2-w for characterizing non-cystic tissue in ADPKD patients, also showing a moderate correlation with age and eGFR. Additionally, lower-order features, including those computed from histograms and co-occurrence matrices, demonstrate higher reproducibility than other texture features.
Collapse
Affiliation(s)
- Francesca Lussana
- Department of Management, Information and Production Engineering, University of Bergamo, 24044, Dalmine, BG, Italy
| | - Ettore Lanzarone
- Department of Management, Information and Production Engineering, University of Bergamo, 24044, Dalmine, BG, Italy
| | - Giulia Villa
- Bioengineering Department, Istituto di Ricerche Farmacologiche Mario Negri IRCCS, 24020, Ranica, BG, Italy
| | - Alfonso Mastropietro
- Institute of Intelligent Industrial Technologies and Systems, Italian National Research Council (STIIMA-CNR), 20133, Milan, Italy
| | - Anna Caroli
- Bioengineering Department, Istituto di Ricerche Farmacologiche Mario Negri IRCCS, 24020, Ranica, BG, Italy
| | - Elisa Scalco
- Institute of Biomedical Technologies, Italian National Research Council (ITB-CNR), 20054, Segrate, MI, Italy.
| |
Collapse
|
44
|
Shin HB, Sheen H, Oh JH, Choi YE, Sung K, Kim HJ. Evaluating feature extraction reproducibility across image biomarker standardization initiative-compliant radiomics platforms using a digital phantom. J Appl Clin Med Phys 2025:e70110. [PMID: 40353843 DOI: 10.1002/acm2.70110] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/22/2024] [Revised: 03/27/2025] [Accepted: 04/07/2025] [Indexed: 05/14/2025] Open
Abstract
BACKGROUND The aim of this study was to thoroughly analyze the reproducibility of radiomics feature extraction across three Image Biomarker Standardization Initiative (IBSI)-compliant platforms using a digital phantom for benchmarking. It uncovers high consistency among common features while also pointing out the necessity for standardization in computational algorithms and mathematical definitions due to unique platform-specific features. METHODS We selected three widely used radiomics platforms: LIFEx, Computational Environment for Radiological Research (CERR), and PyRadiomics. Using the IBSI digital phantom, we performed a comparative analysis to extract and benchmark radiomics features. The study design included testing each platform's ability to consistently reproduce radiomics features, with statistical analyses to assess the variability and agreement among the platforms. RESULTS The results indicated varying levels of feature reproducibility across the platforms. Although some features showed high consistency, others varied significantly, highlighting the need for standardized computational algorithms. Specifically, LIFEx and PyRadiomics performed consistently well across many features, whereas CERR showed greater variability in certain feature categories than LIFEx and PyRadiomics. CONCLUSION The study findings highlight the need for harmonized feature calculation methods to enhance the reliability and clinical usefulness of radiomics. Additionally, this study recommends incorporating clinical data and establishing benchmarking procedures in future studies to enhance the role of radiomics in personalized medicine.
Collapse
Affiliation(s)
- Han-Back Shin
- Department of Radiation Oncology, Gachon University Gil Medical Center, Incheon, Republic of Korea
| | - Heesoon Sheen
- Department of Health Sciences and Technology, Samsung Advanced Institute for Health Sciences & Technology, Sungkyunkwan University, Seoul, Republic of Korea
- High-Energy Physics Center, Chung-Ang University, Seoul, Republic of Korea
| | - Jang-Hoon Oh
- Department of Radiology, Kyung Hee University Hospital, Kyung Hee University College of Medicine, Seoul, Republic of Korea
| | - Young Eun Choi
- Department of Radiation Oncology, Gachon University Gil Medical Center, Incheon, Republic of Korea
| | - Kihoon Sung
- Department of Radiation Oncology, Gil Medical Center, Gachon University College of Medicine, Incheon, Republic of Korea
| | - Hyun Ju Kim
- Department of Radiation Oncology, Gil Medical Center, Gachon University College of Medicine, Incheon, Republic of Korea
| |
Collapse
|
45
|
Kang H, Liu Z, Huang B, Liang S, Yang K, Liu H, Lu M, Yan R, Chen X, Xu E. Can Intra-Operative Ablation-Specific Features Based on Ultrasound Fusion Imaging be Used to Predict Early Recurrence of Hepatocellular Carcinoma After Microwave Ablation: A Proof-of-Concept Study. J Hepatocell Carcinoma 2025; 12:949-960. [PMID: 40386108 PMCID: PMC12084815 DOI: 10.2147/jhc.s512926] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/18/2024] [Accepted: 05/03/2025] [Indexed: 05/20/2025] Open
Abstract
Purpose Intra-operative factors are crucial to early recurrence of hepatocellular carcinoma (HCC) after microwave ablation (MWA), but few models have been developed based on intra-operative data to predict HCC recurrence after MWA. To quantify the intra-operative factors associated with MWA and establish an artificial intelligence (AI) model for predicting early recurrence of HCC after ablation based on contrast-enhanced ultrasound (CEUS) fusion imaging. Patients and Methods 79 hCC patients, who underwent MWA with one-year follow-up and intraoperative CEUS fusion imaging assessment were retrospectively included. Three classifiers (support vector machine (SVM), random forest (RF), and multilayer perceptron (MLP)) were developed to predict early HCC recurrence from CEUS fusion images. Thirteen ablation-specific features were defined and screened using minimum redundancy maximum relevance (mRMR), and leave-one-out cross-validation (LOOCV) was adopted for performance evaluation. Comparative analyses were conducted among classifiers and between a senior interventional doctor and the best classifier in terms of the area under the receiver operating characteristic curve (AUC). Results Of 79 eligible patients who were included, 22 were in the early-recurrence (age 60.18 ± 10.97; 20 males) and 57 were in the non-early recurrence (age 58.81 ± 10.89; 50 males). Six features were selected out by mRMR for early recurrence prediction and AUCs of three models were 0.84 (95% CI: 0.74, 0.94) 0.79 (95% CI: 0.69, 0.89) and 0.77 (95% CI: 0.67, 0.88) (p = 0.20 and 0.23 for SVM and RF, respectively), which was significantly better than that achieved by senior doctor's assessment (AUC, 0.56; 95% CI: 0.44, 0.68; p = 0.002 for MLP). Conclusion The prediction model based on ablation-specific features using intra-operative ultrasound fusion imaging data was feasible to predict early recurrence of HCC after MWA and showed great potential in guiding the real-time adjustment of the intra-operative ablation strategy so as to achieve precise ablation.
Collapse
Affiliation(s)
- Haiyu Kang
- Department of Medical Ultrasonics, The Eighth Affiliated Hospital of Sun Yat-sen University, Shenzhen, Guangdong Province, People’s Republic of China
| | - Zhong Liu
- National-Regional Key Technology Engineering Laboratory for Medical Ultrasound, Guangdong Key Laboratory for Biomedical Measurements and Ultrasound Imaging, School of Biomedical Engineering, Shenzhen University Medical School, Shenzhen, Guangdong Province, People’s Republic of China
| | - Bin Huang
- National-Regional Key Technology Engineering Laboratory for Medical Ultrasound, Guangdong Key Laboratory for Biomedical Measurements and Ultrasound Imaging, School of Biomedical Engineering, Shenzhen University Medical School, Shenzhen, Guangdong Province, People’s Republic of China
| | - Shuang Liang
- Department of Medical Ultrasonics, The Eighth Affiliated Hospital of Sun Yat-sen University, Shenzhen, Guangdong Province, People’s Republic of China
| | - Kai Yang
- National-Regional Key Technology Engineering Laboratory for Medical Ultrasound, Guangdong Key Laboratory for Biomedical Measurements and Ultrasound Imaging, School of Biomedical Engineering, Shenzhen University Medical School, Shenzhen, Guangdong Province, People’s Republic of China
| | - Huahui Liu
- Department of Medical Ultrasonics, The Eighth Affiliated Hospital of Sun Yat-sen University, Shenzhen, Guangdong Province, People’s Republic of China
| | - Minhua Lu
- National-Regional Key Technology Engineering Laboratory for Medical Ultrasound, Guangdong Key Laboratory for Biomedical Measurements and Ultrasound Imaging, School of Biomedical Engineering, Shenzhen University Medical School, Shenzhen, Guangdong Province, People’s Republic of China
| | - Ronghua Yan
- Department of Radiology, Peking University Shenzhen Hospital, Shenzhen, Guangdong Province, People’s Republic of China
| | - Xin Chen
- National-Regional Key Technology Engineering Laboratory for Medical Ultrasound, Guangdong Key Laboratory for Biomedical Measurements and Ultrasound Imaging, School of Biomedical Engineering, Shenzhen University Medical School, Shenzhen, Guangdong Province, People’s Republic of China
| | - Erjiao Xu
- Department of Medical Ultrasonics, The Eighth Affiliated Hospital of Sun Yat-sen University, Shenzhen, Guangdong Province, People’s Republic of China
| |
Collapse
|
46
|
Agnes A, Boldrini L, Perillo F, Tran HE, Brizi MG, Ricci R, Lenkowicz J, Votta C, Biondi A, Manfredi R, Valentini V, D'Ugo DM, Persiani R. Radiomic-based models are able to predict the pathologic response to different neoadjuvant chemotherapy regimens in patients with gastric and gastroesophageal cancer: a cohort study. World J Surg Oncol 2025; 23:183. [PMID: 40350424 PMCID: PMC12067740 DOI: 10.1186/s12957-025-03828-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/03/2025] [Accepted: 04/25/2025] [Indexed: 05/14/2025] Open
Abstract
BACKGROUND There is a clinical need to identify early predictors for response to neoadjuvant chemotherapy (NAC) in patients with gastric and gastroesophageal junction cancer (GC and GEJC). Radiomics involves extracting quantitative features from medical images. This study aimed to apply radiomics to build prediction models for the response to NAC. METHODS All consecutive patients with non-metastatic GC and GEJC undergoing NAC and surgical resection in an Italian high-volume referral center between 2005 and 2021 were considered eligible. In patients selected, the CT scans performed upon staging were reviewed to segment the tumor and extract radiomic features using MODDICOM. The primary endpoint was to develop and validate radiomic-based predictive models to identify major responders (MR: tumor regression grade TRG 1-2) and non-responders (NR: TRG 4-5) to NAC. Following an initial feature selection, radiomic and combined radiomic-clinicopathologic prediction models were built for the MR or NR status based on logistic regressions. Internal validation was performed for each model. Radiomic models (in the entire case series and according to NAC regimens) were evaluated using the receiver operating characteristic area under the curve (AUC), sensitivity, and negative predictive value (NPV). RESULTS The study included 77 patients undergoing NAC and subsequent tumor resection. The MR prediction model after all types of NAC (AUC of 0.876, CI 95% 0.786 - 0.966, sensitivity 83%, and NPV 96%) was based on a statistical feature. The models predicting NR among patients undergoing epirubicin with cisplatin and fluorouracil (ECF), epirubicin with oxaliplatin and capecitabin (EOX), or fluorouracil with oxaliplatin and docetaxel (FLOT) (AUC 0.760, CI 95% 0.639-0.882), oxaliplatin-based chemotherapy (AUC 0.810, CI 95% 0.692-0.928), and FLOT (AUC 0.907, CI 95% 0.818 - 0.995) were based on statistical, morphological and textural features. CONCLUSIONS The developed radiomic models resulted promising in predicting the response to different neoadjuvant chemotherapy strategies. Once further implemented on larger datasets, they could be valuable and cost-effective instruments to target multimodal treatment in patients with GC.
Collapse
Affiliation(s)
- Annamaria Agnes
- Catholic University of the Sacred Heart, Largo F. Vito n.1, Rome, 00168, Italy
- Department of Medical and Surgical Sciences, Fondazione Policlinico Universitario Agostino Gemelli IRCCS, Largo A. Gemelli n. 8, Rome, 00168, Italy
| | - Luca Boldrini
- Catholic University of the Sacred Heart, Largo F. Vito n.1, Rome, 00168, Italy
- Department of Diagnostic Imaging, Oncological Radiotherapy and Hematology, Fondazione Policlinico Universitario "A. Gemelli" IRCCS, Largo A. Gemelli n. 8, Rome, 00168, Italy
| | - Federica Perillo
- Catholic University of the Sacred Heart, Largo F. Vito n.1, Rome, 00168, Italy
| | - Huong Elena Tran
- Department of Diagnostic Imaging, Oncological Radiotherapy and Hematology, Fondazione Policlinico Universitario "A. Gemelli" IRCCS, Largo A. Gemelli n. 8, Rome, 00168, Italy
| | - Maria Gabriella Brizi
- Catholic University of the Sacred Heart, Largo F. Vito n.1, Rome, 00168, Italy
- Department of Diagnostic Imaging, Oncological Radiotherapy and Hematology, Fondazione Policlinico Universitario "A. Gemelli" IRCCS, Largo A. Gemelli n. 8, Rome, 00168, Italy
| | - Riccardo Ricci
- Catholic University of the Sacred Heart, Largo F. Vito n.1, Rome, 00168, Italy
- Department of Women, Children and Public Health Sciences, Fondazione Policlinico Universitario Agostino Gemelli IRCCS, Largo A. Gemelli n. 8, Rome, 00168, Italy
| | - Jacopo Lenkowicz
- Department of Diagnostic Imaging, Oncological Radiotherapy and Hematology, Fondazione Policlinico Universitario "A. Gemelli" IRCCS, Largo A. Gemelli n. 8, Rome, 00168, Italy
| | - Claudio Votta
- Department of Diagnostic Imaging, Oncological Radiotherapy and Hematology, Fondazione Policlinico Universitario "A. Gemelli" IRCCS, Largo A. Gemelli n. 8, Rome, 00168, Italy
| | - Alberto Biondi
- Catholic University of the Sacred Heart, Largo F. Vito n.1, Rome, 00168, Italy.
- Department of Medical and Surgical Sciences, Fondazione Policlinico Universitario Agostino Gemelli IRCCS, Largo A. Gemelli n. 8, Rome, 00168, Italy.
| | - Riccardo Manfredi
- Catholic University of the Sacred Heart, Largo F. Vito n.1, Rome, 00168, Italy
- Department of Diagnostic Imaging, Oncological Radiotherapy and Hematology, Fondazione Policlinico Universitario "A. Gemelli" IRCCS, Largo A. Gemelli n. 8, Rome, 00168, Italy
| | - Vincenzo Valentini
- Catholic University of the Sacred Heart, Largo F. Vito n.1, Rome, 00168, Italy
- Department of Diagnostic Imaging, Oncological Radiotherapy and Hematology, Fondazione Policlinico Universitario "A. Gemelli" IRCCS, Largo A. Gemelli n. 8, Rome, 00168, Italy
| | - Domenico M D'Ugo
- Catholic University of the Sacred Heart, Largo F. Vito n.1, Rome, 00168, Italy
- Department of Medical and Surgical Sciences, Fondazione Policlinico Universitario Agostino Gemelli IRCCS, Largo A. Gemelli n. 8, Rome, 00168, Italy
| | - Roberto Persiani
- Catholic University of the Sacred Heart, Largo F. Vito n.1, Rome, 00168, Italy
- Department of Medical and Surgical Sciences, Fondazione Policlinico Universitario Agostino Gemelli IRCCS, Largo A. Gemelli n. 8, Rome, 00168, Italy
| |
Collapse
|
47
|
Mali SA, Rad NM, Woodruff HC, Depeursinge A, Andrearczyk V, Lambin P. Harmonizing CT scanner acquisition variability in an anthropomorphic phantom: A comparative study of image-level and feature-level harmonization using GAN, ComBat, and their combination. PLoS One 2025; 20:e0322365. [PMID: 40344028 PMCID: PMC12063804 DOI: 10.1371/journal.pone.0322365] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/26/2024] [Accepted: 03/20/2025] [Indexed: 05/11/2025] Open
Abstract
PURPOSE Radiomics allows for the quantification of medical images and facilitates precision medicine. Many radiomic features derived from computed tomography (CT) are sensitive to variations across scanners, reconstruction settings, and acquisition protocols. In this phantom study, eight different CT reconstruction parameters were varied to explore image- and feature-level harmonization approaches to improve tissue classification. METHODS Varying reconstructions of an anthropomorphic radiopaque phantom containing three lesion categories (metastasis, hemangioma, and benign cyst) and normal liver tissue were used for evaluating two harmonization methods and their combination: (i) generative adversarial networks (GANs) at the image level; (ii) ComBat at the feature level, and (iii) a combination of (i) and (ii). A total of 93 texture and intensity features were extracted from each tissue class before and after image-level harmonization and were also harmonized at the feature level. Reproducibility and stability were assessed via the Concordance Correlation Coefficient (CCC) and pairwise comparisons using paired stability tests. The ability of features to discriminate between tissue classes was assessed by measuring the area under the receiver operating characteristic curve. The global reproducibility and discriminative power were assessed by averaging over the entire dataset and across all tissue types. RESULTS ComBat improved reproducibility by 31.58% and stability by 5.24%, while GAN increased reproducibility by 8% it reduced stability by 4.33%. Classification analysis revealed that ComBat increased average AUC by 15.19%, whereas GAN decreased AUC by 2.56%. CONCLUSION While GAN qualitatively enhances image harmonization, ComBat provides superior statistical improvements in feature stability and classification performance, highlighting the importance of robust feature-level harmonization in radiomics.
Collapse
Affiliation(s)
- Shruti Atul Mali
- The D-Lab, Department of Precision Medicine, GROW- Research Institute for Oncology and Reproduction, Maastricht University, Maastricht, Netherlands
| | - Nastaran Mohammadian Rad
- The D-Lab, Department of Precision Medicine, GROW- Research Institute for Oncology and Reproduction, Maastricht University, Maastricht, Netherlands
| | - Henry C. Woodruff
- The D-Lab, Department of Precision Medicine, GROW- Research Institute for Oncology and Reproduction, Maastricht University, Maastricht, Netherlands
- Department of Radiology and Nuclear Medicine, GROW- Research Institute School for Oncology and Reproduction, Maastricht University Medical Centre+, Maastricht, Netherlands
| | - Adrien Depeursinge
- Institute of Information Systems, University of Applied Sciences and Arts Western Switzerland, Sierre, Switzerland
- Department of Nuclear Medicine and Molecular Imaging, Centre Hospitalier Universitaire Vaudois (CHUV), Lausanne, Switzerland
| | - Vincent Andrearczyk
- Institute of Information Systems, University of Applied Sciences and Arts Western Switzerland, Sierre, Switzerland
| | - Philippe Lambin
- The D-Lab, Department of Precision Medicine, GROW- Research Institute for Oncology and Reproduction, Maastricht University, Maastricht, Netherlands
- Department of Radiology and Nuclear Medicine, GROW- Research Institute School for Oncology and Reproduction, Maastricht University Medical Centre+, Maastricht, Netherlands
| |
Collapse
|
48
|
Shivwanshi RR, Nirala NS. A hybrid AI method for lung cancer classification using explainable AI techniques. Phys Med 2025; 134:104985. [PMID: 40344954 DOI: 10.1016/j.ejmp.2025.104985] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 05/28/2024] [Revised: 04/14/2025] [Accepted: 04/23/2025] [Indexed: 05/11/2025] Open
Abstract
PURPOSE The use of Artificial Intelligence (AI) methods for the analysis of CT (computed tomography) images has greatly contributed to the development of an effective computer-assisted diagnosis (CAD) system for lung cancer (LC). However, complex structures, multiple radiographic interrelations, and the dynamic locations of abnormalities within lung CT images make extracting relevant information to process and implement LC CAD systems difficult. These prominent problems are addressed in this paper by presenting a hybrid method of LC malignancy classification, which may help researchers and experts properly engineer the model's performance by observing how the model makes decisions. METHODS The proposed methodology is named IncCat-LCC: Explainer (Inception Net Cat Boost LC Classification: Explainer), which consists of feature extraction (FE) using the handcrafted radiomic Feature (HcRdF) extraction technique, InceptionNet CNN Feature (INCF) extraction, Vision Transformer Feature (ViTF) extraction, and XGBOOST (XGB)-based feature selection, and the GPU based CATBOOST (CB) classification technique. RESULTS The proposed framework achieves better and highest performance scores for lung nodule multiclass malignancy classification when evaluated using metrics such as accuracy, precision, recall, f-1 score, specificity, and area under the roc curve as 96.74 %, 93.68 %, 96.74 %, 95.19 %, 98.47 % and 99.76 % consecutively for classifying highly normal class. CONCLUSION Observing the explainable artificial intelligence (XAI) explanations will help readers understand the model performance and the statistical outcomes of the evaluation parameter. The work presented in this article may improve the existing LC CAD system and help assess the important parameters using XAI to recognize the factors contributing to enhanced performance and reliability.
Collapse
Affiliation(s)
- Resham Raj Shivwanshi
- Department of Biomedical Engineering, National Institute of Technology Raipur, 492010, India.
| | - Neelam Shobha Nirala
- Department of Biomedical Engineering, National Institute of Technology Raipur, 492010, India.
| |
Collapse
|
49
|
Noortman WA, Vriens D, Bussink J, Meijer TWH, Aarntzen EHJG, Deroose CM, Lhommel R, Aide N, Le Tourneau C, de Koster EJ, Oyen WJG, Triemstra L, Ruurda JP, Vegt E, de Geus-Oei LF, van Velden FHP. Multicollinearity and redundancy of the PET radiomic feature set. Eur Radiol 2025:10.1007/s00330-025-11637-7. [PMID: 40332568 DOI: 10.1007/s00330-025-11637-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/18/2024] [Revised: 04/02/2025] [Accepted: 04/07/2025] [Indexed: 05/08/2025]
Abstract
INTRODUCTION The aim of this study was to map multicollinearity of the radiomic feature set in five independent [18F]FDG-PET cohorts with different tumour types and identify generalizable non-redundant features. METHODS Five [18F]FDG-PET radiomic cohorts were analysed: non-small cell lung carcinomas (N = 35), pheochromocytomas and paragangliomas (N = 40), head and neck squamous cell carcinomas (N = 54), [18F]FDG-positive thyroid nodules with indeterminate cytology (N = 84), and gastric carcinomas (N = 206). Lesions were delineated, and 105 radiomic features were extracted using PyRradiomics. In every cohort, Spearman's rank correlation coefficient (ρ) matrices of features were calculated to determine which features showed (very) strong (ρ > 0.7 and ρ > 0.9) correlations with any other feature in all five cohorts. Cluster analysis of an averaged correlation matrix for all cohorts was performed at a threshold of ρ = 0.7 and ρ = 0.9. For each cluster, a representative, non-redundant feature was selected. RESULTS Seventy-two and 90 out of 105 features showed a (very) strong correlation with another feature in the correlation matrix in all five cohorts. Cluster analysis resulted in 35 and 15 non-redundant features at thresholds of ρ = 0.9 and ρ = 0.7, including 6 and 3 shape features, 4 and 2 intensity features, and 25 and 10 texture features, respectively. Seventy or 90 redundant features could be omitted at these thresholds, respectively. CONCLUSION At least two-thirds of the radiomic feature set could be omitted because of strong multicollinearity in multiple independent cohorts. More redundant features could be identified using a less conservative threshold. Future research should indicate whether multicollinearity of the radiomic feature set is similar for other radiopharmaceuticals and imaging modalities. KEY POINTS Question Radiomic feature sets contain many strongly correlating features, which results in statistical challenges. Findings Analysis of the correlation matrices showed that the same radiomic features were strongly correlated in five independent [18F]FDG-PET cohorts with different tumour types. Clinical relevance At least two-thirds of the radiomic feature set could be omitted, because of strong multicollinearity. More redundant features could be identified using a less conservative threshold.
Collapse
Affiliation(s)
- Wyanne A Noortman
- Department of Radiology, Section of Nuclear Medicine, Leiden University Medical Center, Leiden, The Netherlands.
- Department of Medical Oncology, University Medical Center Groningen, Groningen, The Netherlands.
| | - Dennis Vriens
- Department of Medical Imaging, Radboud University Medical Center, Nijmegen, The Netherlands
| | - Johan Bussink
- Department of Radiation Oncology, Radboud University Medical Center, Nijmegen, The Netherlands
| | - Tineke W H Meijer
- Department of Radiation Oncology, University Medical Center Groningen, Groningen, The Netherlands
| | - Erik H J G Aarntzen
- Department of Medical Imaging, Radboud University Medical Center, Nijmegen, The Netherlands
- Department of Nuclear Medicine and Molecular Imaging, University Medical Center Groningen, Groningen, The Netherlands
- Department of Nuclear Medicine, Eberhard Karls University, Tuebingen, Germany
| | | | - Renaud Lhommel
- Division of Nuclear Medicine and Institut de Recherche Clinique, Cliniques Universitaires Saint Luc (UCLouvain), Brussels, Belgium
| | - Nicolas Aide
- INSERM ANTICIPE U1086, François Baclesse Cancer Centre, Caen, France
| | - Christophe Le Tourneau
- Department of Drug Development and Innovation, Institut Curie, Paris-Saclay University, Paris, France
| | - Elizabeth J de Koster
- Department of Radiology, Section of Nuclear Medicine, Leiden University Medical Center, Leiden, The Netherlands
- Department of Medical Imaging, Radboud University Medical Center, Nijmegen, The Netherlands
| | - Wim J G Oyen
- Department of Medical Imaging, Radboud University Medical Center, Nijmegen, The Netherlands
- Department of Radiology and Nuclear Medicine, Rijnstate Hospital, Arnhem, The Netherlands
- Department of Biomedical Sciences and Humanitas Clinical and Research Centre, Department of Nuclear Medicine, Humanitas University, Milan, Italy
| | - Lianne Triemstra
- Department of Radiology, Section of Nuclear Medicine, Leiden University Medical Center, Leiden, The Netherlands
- Department of Surgery, University Medical Center Utrecht, Utrecht, The Netherlands
| | - Jelle P Ruurda
- Department of Surgery, University Medical Center Utrecht, Utrecht, The Netherlands
| | - Erik Vegt
- Department of Radiology and Nuclear Medicine, Erasmus MC University Medical Center Rotterdam, Rotterdam, The Netherlands
| | - Lioe-Fee de Geus-Oei
- Department of Radiology, Section of Nuclear Medicine, Leiden University Medical Center, Leiden, The Netherlands
- Biomedical Photonic Imaging Group, University of Twente, Enschede, The Netherlands
| | - Floris H P van Velden
- Department of Radiology, Section of Nuclear Medicine, Leiden University Medical Center, Leiden, The Netherlands
| |
Collapse
|
50
|
Wong LM, Ai QYH, Leung HS, So TYT, Hung KF, Chan YT, King AD. Decoding the Rotation Effect: A Retrospective Analysis of Lesion Orientation and Its Impact on Wavelet-Based Radiomics Feature Extraction and Lung Cancer Classification. JOURNAL OF IMAGING INFORMATICS IN MEDICINE 2025:10.1007/s10278-025-01520-8. [PMID: 40329153 DOI: 10.1007/s10278-025-01520-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/15/2024] [Revised: 04/19/2025] [Accepted: 04/21/2025] [Indexed: 05/08/2025]
Abstract
Wavelet decomposition (WD), widely used in radiomics, redistributes information among derived wavelet components when the input is rotated. This redistribution may alter predictions for the same lesion when scanned at different angles. Despite its potential significance, this vulnerability has frequently been overlooked in radiomic studies while its impact remains poorly understood. Therefore, this study aims to investigate how variations in lesion orientation affect both WD and non-WD radiomic feature values, and subsequently, model performance. We analyzed CT radiomics of primary non-small-cell lung cancer (NSCLC). Prior to feature extraction, we introduced random rotations ranging from 5° to 80° to the tumors. Their effects were quantified by evaluating the percentage difference ( % Δ ) between the rotated and unrotated feature values, and validated using Spearman's rank test. Additionally, radiomics models were trained to discriminate between three histological subtypes of NSCLC using the original features, and then tested on rotated inputs. The correlation between the model accuracies and the degree of rotation was again evaluated using Spearman's rank test. Four-hundred nineteen NSCLC patients (mean age: 68.1 ± 10.1, 289 men) were evaluated. Significant correlations between feature values and rotations (Spearman's correlation [CC] magnitude ≥ 0.1, p < .05) were found in 23.7% (176/744) of the WD and 0.5% (5/930) of the non-WD texture features. Significant association between performance and rotation was observed in WD-based models built to discriminate between NSCLC histological subtypes (CC = - 0.44, p < .001) but not in non-WD-based models (CC = 0.03, p = 0.07). Input lesion orientation affects radiomic feature values and model reproducibility. WD features exhibited significantly greater instability to orientation variations compared to non-WD features.
Collapse
Affiliation(s)
- Lun Matthew Wong
- Department of Imaging and Interventional Radiology, Prince of Wales Hospital, The Chinese University of Hong Kong, LG/F, Cancer Centre, Shatin, New Territory, HKSAR, China.
| | - Qi-Yong Hemis Ai
- Department of Imaging and Interventional Radiology, Prince of Wales Hospital, The Chinese University of Hong Kong, LG/F, Cancer Centre, Shatin, New Territory, HKSAR, China
- Department of Diagnostic Radiology, School of Clinical Medicine, The University of Hong Kong, HKSAR, China
| | - Ho Sang Leung
- Department of Imaging and Interventional Radiology, Prince of Wales Hospital, The Hospital Authority - New Territory East Cluster, HKSAR, China
| | - Tifffany Yuen-Tung So
- Department of Imaging and Interventional Radiology, Prince of Wales Hospital, The Chinese University of Hong Kong, LG/F, Cancer Centre, Shatin, New Territory, HKSAR, China
| | - Kuo Feng Hung
- Department of Applied Oral Sciences & Community Dental Care, Faculty of Dentistry, The University of Hong Kong, HKSAR, China
| | - Yuet-Ting Chan
- Department of Imaging and Interventional Radiology, Prince of Wales Hospital, The Chinese University of Hong Kong, LG/F, Cancer Centre, Shatin, New Territory, HKSAR, China
| | - Ann Dorothy King
- Department of Imaging and Interventional Radiology, Prince of Wales Hospital, The Chinese University of Hong Kong, LG/F, Cancer Centre, Shatin, New Territory, HKSAR, China
| |
Collapse
|