|
1
|
Nakajo M, Hirahara D, Jinguji M, Idichi T, Hirahara M, Tani A, Takumi K, Kamimura K, Ohtsuka T, Yoshiura T. Machine learning-based prognostic modeling in gallbladder cancer using clinical data and pre-treatment [ 18F]-FDG-PET-radiomic features. Jpn J Radiol 2025; 43:864-874. [PMID: 39730929 PMCID: PMC12053127 DOI: 10.1007/s11604-024-01722-0] [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: 09/26/2024] [Accepted: 12/12/2024] [Indexed: 12/29/2024]
Abstract
OBJECTIVES This study evaluates the effectiveness of machine learning (ML) models that incorporate clinical and 2-deoxy-2-[18F]fluoro-D-glucose ([18F]-FDG)-positron emission tomography (PET)-radiomic features for predicting outcomes in gallbladder cancer patients. MATERIALS AND METHODS The study analyzed 52 gallbladder cancer patients who underwent pre-treatment [18F]-FDG-PET/CT scans between January 2011 and December 2021. Twenty-seven patients were assigned to the training cohort between January 2011 and January 2018, and the data randomly split into training (70%) and validation (30%) sets. The independent test cohort consisted of 25 patients between February 2018 and December 2021. Eight clinical features (T stage, N stage, M stage, Union for International Cancer Control [UICC] stage, histology, tumor size, carcinoembryonic antigen level, and carbohydrate antigen 19-9 level) and 49 radiomic features were used to forecast progression-free survival (PFS). Three feature selection methods were applied including the univariate statistical feature selection test method, least absolute shrinkage and selection operator Cox regression method and recursive feature elimination method, and two ML algorithms (Cox proportional hazard and random survival forest [RSF]) were employed. Predictive performance was assessed using the concordance index (C-index). RESULTS Two clinical variables (UICC stage, N stage) and three radiomic features (total lesion glycolysis, grey-level size-zone matrix_grey level non-uniformity and grey-level run-length matrix_run-length non-uniformity) were identified by the statistical feature selection method as significant for PFS prediction. The RSF model incorporating these features demonstrated strong predictive performance, with C-indices above 0.80 in both training and testing sets (training 0.81, testing 0.89). This model almost closely matched the actual and predicted progression timelines with a low mean absolute error of 1.435, a median absolute error of 0.082, and a root mean square error of 2.359. CONCLUSION This study highlights the potential of using ML approaches with clinical and pre-treatment [18F]-FDG-PET radiomic data for predicting the prognosis of gallbladder cancer.
Collapse
Affiliation(s)
- Masatoyo Nakajo
- Department of Radiology, Graduate School of Medical and Dental Sciences, Kagoshima University, 8-35-1 Sakuragaoka, Kagoshima, 890-8544, Japan.
| | - Daisuke Hirahara
- Department of Management Planning Division, Harada Academy, 2-54-4 Higashitaniyama, Kagoshima, 890-0113, Japan
| | - Megumi Jinguji
- Department of Radiology, Nanpuh Hospital, 14-3 Nagata, Kagoshima, 892-8512, Japan
| | - Tetsuya Idichi
- Department of Digestive Surgery, Graduate School of Medical and Dental Sciences, 8-35-1 Sakuragaoka, Kagoshima, 890-8544, Japan
| | - Mitsuho Hirahara
- Department of Radiology, Graduate School of Medical and Dental Sciences, Kagoshima University, 8-35-1 Sakuragaoka, Kagoshima, 890-8544, Japan
| | - Atsushi Tani
- Department of Radiology, Graduate School of Medical and Dental Sciences, Kagoshima University, 8-35-1 Sakuragaoka, Kagoshima, 890-8544, Japan
| | - Koji Takumi
- Department of Radiology, Graduate School of Medical and Dental Sciences, Kagoshima University, 8-35-1 Sakuragaoka, Kagoshima, 890-8544, Japan
| | - Kiyohisa Kamimura
- Department of Advanced Radiological Imaging, Graduate School of Medical and Dental Sciences, Kagoshima University, 8-35-1 Sakuragaoka, Kagoshima, 890-8544, Japan
| | - Takao Ohtsuka
- Department of Digestive Surgery, Graduate School of Medical and Dental Sciences, 8-35-1 Sakuragaoka, Kagoshima, 890-8544, Japan
| | - Takashi Yoshiura
- Department of Radiology, Graduate School of Medical and Dental Sciences, Kagoshima University, 8-35-1 Sakuragaoka, Kagoshima, 890-8544, Japan
| |
Collapse
|
|
2
|
Yang L, Xuan R, Xu D, Sang A, Zhang J, Zhang Y, Ye X, Li X. Comprehensive integration of diagnostic biomarker analysis and immune cell infiltration features in sepsis via machine learning and bioinformatics techniques. Front Immunol 2025; 16:1526174. [PMID: 40129981 PMCID: PMC11931141 DOI: 10.3389/fimmu.2025.1526174] [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: 11/11/2024] [Accepted: 02/14/2025] [Indexed: 03/26/2025] Open
Abstract
Introduction Sepsis, a critical medical condition resulting from an irregular immune response to infection, leads to life-threatening organ dysfunction. Despite medical advancements, the critical need for research into dependable diagnostic markers and precise therapeutic targets. Methods We screened out five gene expression datasets (GSE69063, GSE236713, GSE28750, GSE65682 and GSE137340) from the Gene Expression Omnibus. First, we merged the first two datasets. We then identified differentially expressed genes (DEGs), which were subjected to KEGG and GO enrichment analyses. Following this, we integrated the DEGs with the genes from key modules as determined by Weighted Gene Co-expression Network Analysis (WGCNA), identifying 262 overlapping genes. 12 core genes were subsequently selected using three machine-learning algorithms: random forest (RF), Least Absolute Shrinkage and Selection Operator (LASSO), and Support Vector Machine-Recursive Feature Elimination (SVW-RFE). The utilization of the receiver operating characteristic curve in conjunction with the nomogram model served to authenticate the discriminatory strength and efficacy of the key genes. CIBERSORT was utilized to evaluate the inflammatory and immunological condition of sepsis. Astragalus, Salvia, and Safflower are the primary elements of Xuebijing, commonly used in the clinical treatment of sepsis. Using the Traditional Chinese Medicine Systems Pharmacology Database and Analysis Platform (TCMSP), we identified the chemical constituents of these three herbs and their target genes. Results We found that CD40LG is not only one of the 12 core genes we identified, but also a common target of the active components quercetin, luteolin, and apigenin in these herbs. We extracted the common chemical structure of these active ingredients -flavonoids. Through docking analysis, we further validated the interaction between flavonoids and CD40LG. Lastly, blood samples were collected from healthy individuals and sepsis patients, with and without the administration of Xuebijing, for the extraction of peripheral blood mononuclear cells (PBMCs). By qPCR and WB analysis. We observed significant differences in the expression of CD40LG across the three groups. In this study, we pinpointed candidate hub genes for sepsis and constructed a nomogram for its diagnosis. Discussion This research not only provides potential diagnostic evidence for peripheral blood diagnosis of sepsis but also offers insights into the pathogenesis and disease progression of sepsis.
Collapse
Affiliation(s)
- Liuqing Yang
- Department of Anesthesiology, Zhongnan Hospital of Wuhan University, Wuhan, Hubei, China
- Department of Anesthesiology, Hubei Provincial Engineering Research Center of Minimally Invasive Cardiovascular Sugery, Wuhan, China
- Department of Anesthesiology, Wuhan Clinical Research Center for Minimally Invasive Treatment of Structural Heart Disease, Wuhan, China
| | - Rui Xuan
- Department of Anesthesiology, Zhongnan Hospital of Wuhan University, Wuhan, Hubei, China
- Department of Anesthesiology, Hubei Provincial Engineering Research Center of Minimally Invasive Cardiovascular Sugery, Wuhan, China
- Department of Anesthesiology, Wuhan Clinical Research Center for Minimally Invasive Treatment of Structural Heart Disease, Wuhan, China
| | - Dawei Xu
- Department of Anesthesiology, Zhongnan Hospital of Wuhan University, Wuhan, Hubei, China
- Department of Anesthesiology, Hubei Provincial Engineering Research Center of Minimally Invasive Cardiovascular Sugery, Wuhan, China
- Department of Anesthesiology, Wuhan Clinical Research Center for Minimally Invasive Treatment of Structural Heart Disease, Wuhan, China
| | - Aming Sang
- Department of Anesthesiology, Zhongnan Hospital of Wuhan University, Wuhan, Hubei, China
- Department of Anesthesiology, Hubei Provincial Engineering Research Center of Minimally Invasive Cardiovascular Sugery, Wuhan, China
- Department of Anesthesiology, Wuhan Clinical Research Center for Minimally Invasive Treatment of Structural Heart Disease, Wuhan, China
| | - Jing Zhang
- Department of Anesthesiology, Zhongnan Hospital of Wuhan University, Wuhan, Hubei, China
- Department of Anesthesiology, Hubei Provincial Engineering Research Center of Minimally Invasive Cardiovascular Sugery, Wuhan, China
- Department of Anesthesiology, Wuhan Clinical Research Center for Minimally Invasive Treatment of Structural Heart Disease, Wuhan, China
| | - Yanfang Zhang
- Department of Geriatrics, Zhongnan Hospital of Wuhan University, Wuhan, Hubei, China
| | - Xujun Ye
- Department of Geriatrics, Zhongnan Hospital of Wuhan University, Wuhan, Hubei, China
| | - Xinyi Li
- Department of Anesthesiology, Zhongnan Hospital of Wuhan University, Wuhan, Hubei, China
- Department of Anesthesiology, Hubei Provincial Engineering Research Center of Minimally Invasive Cardiovascular Sugery, Wuhan, China
- Department of Anesthesiology, Wuhan Clinical Research Center for Minimally Invasive Treatment of Structural Heart Disease, Wuhan, China
| |
Collapse
|
|
3
|
Nakajo M, Hirahara D, Jinguji M, Hirahara M, Tani A, Nagano H, Takumi K, Kamimura K, Kanzaki F, Yamashita M, Yoshiura T. Applying deep learning-based ensemble model to [ 18F]-FDG-PET-radiomic features for differentiating benign from malignant parotid gland diseases. Jpn J Radiol 2025; 43:91-100. [PMID: 39254903 PMCID: PMC11717794 DOI: 10.1007/s11604-024-01649-6] [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: 07/19/2024] [Accepted: 08/26/2024] [Indexed: 09/11/2024]
Abstract
OBJECTIVES To develop and identify machine learning (ML) models using pretreatment 2-deoxy-2-[18F]fluoro-D-glucose ([18F]-FDG)-positron emission tomography (PET)-based radiomic features to differentiate benign from malignant parotid gland diseases (PGDs). MATERIALS AND METHODS This retrospective study included 62 patients with 63 PGDs who underwent pretreatment [18F]-FDG-PET/computed tomography (CT). The lesions were assigned to the training (n = 44) and testing (n = 19) cohorts. In total, 49 [18F]-FDG-PET-based radiomic features were utilized to differentiate benign from malignant PGDs using five different conventional ML algorithmic models (random forest, neural network, k-nearest neighbors, logistic regression, and support vector machine) and the deep learning (DL)-based ensemble ML model. In the training cohort, each conventional ML model was constructed using the five most important features selected by the recursive feature elimination method with the tenfold cross-validation and synthetic minority oversampling technique. The DL-based ensemble ML model was constructed using the five most important features of the bagging and multilayer stacking methods. The area under the receiver operating characteristic curves (AUCs) and accuracies were used to compare predictive performances. RESULTS In total, 24 benign and 39 malignant PGDs were identified. Metabolic tumor volume and four GLSZM features (GLSZM_ZSE, GLSZM_SZE, GLSZM_GLNU, and GLSZM_ZSNU) were the five most important radiomic features. All five features except GLSZM_SZE were significantly higher in malignant PGDs than in benign ones (each p < 0.05). The DL-based ensemble ML model had the best performing classifier in the training and testing cohorts (AUC = 1.000, accuracy = 1.000 vs AUC = 0.976, accuracy = 0.947). CONCLUSIONS The DL-based ensemble ML model using [18F]-FDG-PET-based radiomic features can be useful for differentiating benign from malignant PGDs. The DL-based ensemble ML model using [18F]-FDG-PET-based radiomic features can overcome the previously reported limitation of [18F]-FDG-PET/CT scan for differentiating benign from malignant PGDs. The DL-based ensemble ML approach using [18F]-FDG-PET-based radiomic features can provide useful information for managing PGD.
Collapse
Affiliation(s)
- Masatoyo Nakajo
- Department of Radiology, Graduate School of Medical and Dental Sciences, Kagoshima University, 8-35-1 Sakuragaoka, Kagoshima, 890-8544, Japan.
| | - Daisuke Hirahara
- Department of Management Planning Division, Harada Academy, 2-54-4 Higashitaniyama, Kagoshima, 890-0113, Japan
| | - Megumi Jinguji
- Department of Radiology, Nanpuh Hospital, 14-3 Nagata, Kagoshima, 892-8512, Japan
| | - Mitsuho Hirahara
- Department of Radiology, Graduate School of Medical and Dental Sciences, Kagoshima University, 8-35-1 Sakuragaoka, Kagoshima, 890-8544, Japan
| | - Atsushi Tani
- Department of Radiology, Graduate School of Medical and Dental Sciences, Kagoshima University, 8-35-1 Sakuragaoka, Kagoshima, 890-8544, Japan
| | - Hiromi Nagano
- Department of Otolaryngology Head and Neck Surgery, Graduate School of Medical and Dental Sciences, Kagoshima University, 8-35-1 Sakuragaoka, Kagoshima, 890-8544, Japan
| | - Koji Takumi
- Department of Radiology, Graduate School of Medical and Dental Sciences, Kagoshima University, 8-35-1 Sakuragaoka, Kagoshima, 890-8544, Japan
| | - Kiyohisa Kamimura
- Department of Advanced Radiological Imaging, Graduate School of Medical and Dental Sciences, Kagoshima University, 8-35-1 Sakuragaoka, Kagoshima, 890-8544, Japan
| | - Fumiko Kanzaki
- Department of Radiology, Graduate School of Medical and Dental Sciences, Kagoshima University, 8-35-1 Sakuragaoka, Kagoshima, 890-8544, Japan
| | - Masaru Yamashita
- Department of Otolaryngology Head and Neck Surgery, Graduate School of Medical and Dental Sciences, Kagoshima University, 8-35-1 Sakuragaoka, Kagoshima, 890-8544, Japan
| | - Takashi Yoshiura
- Department of Radiology, Graduate School of Medical and Dental Sciences, Kagoshima University, 8-35-1 Sakuragaoka, Kagoshima, 890-8544, Japan
| |
Collapse
|
|
4
|
Wlosik J, Granjeaud S, Gorvel L, Olive D, Chretien AS. A beginner's guide to supervised analysis for mass cytometry data in cancer biology. Cytometry A 2024; 105:853-869. [PMID: 39486897 DOI: 10.1002/cyto.a.24901] [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: 06/10/2024] [Revised: 09/16/2024] [Accepted: 10/01/2024] [Indexed: 11/04/2024]
Abstract
Mass cytometry enables deep profiling of biological samples at single-cell resolution. This technology is more than relevant in cancer research due to high cellular heterogeneity and complexity. Downstream analysis of high-dimensional datasets increasingly relies on machine learning (ML) to extract clinically relevant information, including supervised algorithms for classification and regression purposes. In cancer research, they are used to develop predictive models that will guide clinical decision making. However, the development of supervised algorithms faces major challenges, such as sufficient validation, before being translated into the clinics. In this work, we provide a framework for the analysis of mass cytometry data with a specific focus on supervised algorithms and practical examples of their applications. We also raise awareness on key issues regarding good practices for researchers curious to implement supervised ML on their mass cytometry data. Finally, we discuss the challenges of supervised ML application to cancer research.
Collapse
Affiliation(s)
- Julia Wlosik
- Team 'Immunity and Cancer', Marseille Cancer Research Center, Inserm U1068, CNRS UMR7258, Paoli-Calmettes Institute, Aix-Marseille University UM105, Marseille, France
- Immunomonitoring Department, Paoli-Calmettes Institute, Marseille, France
| | - Samuel Granjeaud
- Systems Biology Platform, Marseille Cancer Research Center, Inserm U1068, CNRS UMR7258, Paoli-Calmettes Institute, Aix-Marseille University UM105, Marseille, France
| | - Laurent Gorvel
- Team 'Immunity and Cancer', Marseille Cancer Research Center, Inserm U1068, CNRS UMR7258, Paoli-Calmettes Institute, Aix-Marseille University UM105, Marseille, France
- Immunomonitoring Department, Paoli-Calmettes Institute, Marseille, France
| | - Daniel Olive
- Team 'Immunity and Cancer', Marseille Cancer Research Center, Inserm U1068, CNRS UMR7258, Paoli-Calmettes Institute, Aix-Marseille University UM105, Marseille, France
- Immunomonitoring Department, Paoli-Calmettes Institute, Marseille, France
| | - Anne-Sophie Chretien
- Team 'Immunity and Cancer', Marseille Cancer Research Center, Inserm U1068, CNRS UMR7258, Paoli-Calmettes Institute, Aix-Marseille University UM105, Marseille, France
- Immunomonitoring Department, Paoli-Calmettes Institute, Marseille, France
| |
Collapse
|
|
5
|
Restini FCF, Torfeh T, Aouadi S, Hammoud R, Al-Hammadi N, Starling MTM, Sousa CFPM, Mancini A, Brito LH, Yoshimoto FH, Lima-Júnior NF, Queiroz MM, Passos UL, Amancio CT, Takahashi JT, De Souza Delgado D, Hanna SA, Marta GN, Neves-Junior WFP. AI tool for predicting MGMT methylation in glioblastoma for clinical decision support in resource limited settings. Sci Rep 2024; 14:27995. [PMID: 39543155 PMCID: PMC11564566 DOI: 10.1038/s41598-024-78189-6] [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: 06/26/2024] [Accepted: 10/29/2024] [Indexed: 11/17/2024] Open
Abstract
Glioblastoma is an aggressive brain cancer with a poor prognosis. The O6-methylguanine-DNA methyltransferase (MGMT) gene methylation status is crucial for treatment stratification, yet economic constraints often limit access. This study aims to develop an artificial intelligence (AI) framework for predicting MGMT methylation. Diagnostic magnetic resonance (MR) images in public repositories were used for training. The algorithm created was validated in data from a single institution. All images were segmented according to widely used guidelines for radiotherapy planning and combined with clinical evaluations from neuroradiology experts. Radiomic features and clinical impressions were extracted, tabulated, and used for modeling. Feature selection methods were used to identify relevant phenotypes. A total of 100 patients were used for training and 46 for validation. A total of 343 features were extracted. Eight feature selection methods produced seven independent predictive frameworks. The top-performing ML model was a model post-Least Absolute Shrinkage and Selection Operator (LASSO) feature selection reaching accuracy (ACC) of 0.82, an area under the curve (AUC) of 0.81, a recall of 0.75, and a precision of 0.75. This study demonstrates that integrating clinical and radiotherapy-derived AI-driven phenotypes can predict MGMT methylation. The framework addresses constraints that limit molecular diagnosis access.
Collapse
Affiliation(s)
- Felipe Cicci Farinha Restini
- Department of Radiation Oncology, Hospital Sírio-Libanês, Rua Batataes, 523, Jardim Paulista, Distrito Federal, São Paulo, Brasília, 01423-010, Brazil.
| | - Tarraf Torfeh
- Department of Radiation Oncology, National Center for Cancer Care and Research, Doha, Qatar
| | - Souha Aouadi
- Department of Radiation Oncology, National Center for Cancer Care and Research, Doha, Qatar
| | - Rabih Hammoud
- Department of Radiation Oncology, National Center for Cancer Care and Research, Doha, Qatar
| | - Noora Al-Hammadi
- Department of Radiation Oncology, National Center for Cancer Care and Research, Doha, Qatar
| | | | | | - Anselmo Mancini
- Department of Radiation Oncology, Hospital Sírio-Libanês, São Paulo, Brazil
| | | | | | | | | | | | | | | | | | | | | | | |
Collapse
|
|
6
|
Yu Y, Chen R, Yi J, Huang K, Yu X, Zhang J, Song C. Non-invasive prediction of axillary lymph node dissection exemption in breast cancer patients post-neoadjuvant therapy: A radiomics and deep learning analysis on longitudinal DCE-MRI data. Breast 2024; 77:103786. [PMID: 39137488 PMCID: PMC11369401 DOI: 10.1016/j.breast.2024.103786] [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: 04/23/2024] [Revised: 07/15/2024] [Accepted: 08/08/2024] [Indexed: 08/15/2024] Open
Abstract
PURPOSE In breast cancer (BC) patients with clinical axillary lymph node metastasis (cN+) undergoing neoadjuvant therapy (NAT), precise axillary lymph node (ALN) assessment dictates therapeutic strategy. There is a critical demand for a precise method to assess the axillary lymph node (ALN) status in these patients. MATERIALS AND METHODS A retrospective analysis was conducted on 160 BC patients undergoing NAT at Fujian Medical University Union Hospital. We analyzed baseline and two-cycle reassessment dynamic contrast-enhanced MRI (DCE-MRI) images, extracting 3668 radiomic and 4096 deep learning features, and computing 1834 delta-radiomic and 2048 delta-deep learning features. Light Gradient Boosting Machine (LightGBM), Support Vector Machine (SVM), RandomForest, and Multilayer Perceptron (MLP) algorithms were employed to develop risk models and were evaluated using 10-fold cross-validation. RESULTS Of the patients, 61 (38.13 %) achieved ypN0 status post-NAT. Univariate and multivariable logistic regression analyses revealed molecular subtypes and Ki67 as pivotal predictors of achieving ypN0 post-NAT. The SVM-based "Data Amalgamation" model that integrates radiomic, deep learning features, and clinical data, exhibited an outstanding AUC of 0.986 (95 % CI: 0.954-1.000), surpassing other models. CONCLUSION Our study illuminates the challenges and opportunities inherent in breast cancer management post-NAT. By introducing a sophisticated, SVM-based "Data Amalgamation" model, we propose a way towards accurate, dynamic ALN assessments, offering potential for personalized therapeutic strategies in BC.
Collapse
Affiliation(s)
- Yushuai Yu
- Department of Breast Surgery, Fujian Medical University Union Hospital, Fuzhou, Fujian Province, 350001, China; Department of Breast Surgery, Clinical Oncology School of Fujian Medical University, Fujian Cancer Hospital, Fuzhou, Fujian Province, 350014, China
| | - Ruiliang Chen
- Department of Breast Surgery, Fujian Medical University Union Hospital, Fuzhou, Fujian Province, 350001, China
| | - Jialu Yi
- Department of Breast Surgery, Fujian Medical University Union Hospital, Fuzhou, Fujian Province, 350001, China
| | - Kaiyan Huang
- Department of Breast and Thyroid Surgery, The Second Affiliated Hospital of Fujian Medical University, Quanzhou, Fujian Province, 362000, China
| | - Xin Yu
- Department of Breast Surgery, Clinical Oncology School of Fujian Medical University, Fujian Cancer Hospital, Fuzhou, Fujian Province, 350014, China
| | - Jie Zhang
- Department of Breast Surgery, Fujian Medical University Union Hospital, Fuzhou, Fujian Province, 350001, China.
| | - Chuangui Song
- Department of Breast Surgery, Fujian Medical University Union Hospital, Fuzhou, Fujian Province, 350001, China; Department of Breast Surgery, Clinical Oncology School of Fujian Medical University, Fujian Cancer Hospital, Fuzhou, Fujian Province, 350014, China.
| |
Collapse
|
|
7
|
Chakraborty J, Midya A, Kurland BF, Welch ML, Gonen M, Moskowitz CS, Simpson AL. Use of Response Permutation to Measure an Imaging Dataset's Susceptibility to Overfitting by Selected Standard Analysis Pipelines. Acad Radiol 2024; 31:3590-3596. [PMID: 38614825 PMCID: PMC12034343 DOI: 10.1016/j.acra.2024.02.028] [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: 04/05/2023] [Revised: 02/14/2024] [Accepted: 02/16/2024] [Indexed: 04/15/2024]
Abstract
RATIONALE AND OBJECTIVES This study demonstrates a method for quantifying the impact of overfitting on the receiving operator characteristic curve (AUC) when using standard analysis pipelines to develop imaging biomarkers. We illustrate the approach using two publicly available repositories of radiology and pathology images for breast cancer diagnosis. MATERIALS AND METHODS For each dataset, we permuted the outcome (cancer diagnosis) values to eliminate any true association between imaging features and outcome. Seven types of classification models (logistic regression, linear discriminant analysis, Naïve Bayes, linear support vector machines, nonlinear support vector machine, random forest, and multi-layer perceptron) were fitted to each scrambled dataset and evaluated by each of four techniques (all data, hold-out, 10-fold cross-validation, and bootstrapping). After repeating this process for a total of 50 outcome permutations, we averaged the resulting AUCs. Any increase over a null AUC of 0.5 can be attributed to overfitting. RESULTS Applying this approach and varying sample size and the number of imaging features, we found that failing to control for overfitting could result in near-perfect prediction (AUC near 1.0). Cross-validation offered greater protection against overfitting than the other evaluation techniques, and for most classification algorithms a sample size of at least 200 was required to assess as few as 10 features with less than 0.05 AUC inflation attributable to overfitting. CONCLUSION This approach could be applied to any curated dataset to suggest the number of features and analysis approaches to limit overfitting.
Collapse
Affiliation(s)
- Jayasree Chakraborty
- Department of Surgery, Hepatopancreatobiliary Service, Memorial Sloan Kettering Cancer Center, New York, New York, USA
| | - Abhishek Midya
- Department of Surgery, Hepatopancreatobiliary Service, Memorial Sloan Kettering Cancer Center, New York, New York, USA
| | | | - Mattea L Welch
- Princess Margaret Data Science Program, University Health Network, Toronto, Ontario, Canada
| | - Mithat Gonen
- Department of Epidemiology and Biostatistics, Memorial Sloan Kettering Cancer Center, New York, New York, USA
| | - Chaya S Moskowitz
- Department of Epidemiology and Biostatistics, Memorial Sloan Kettering Cancer Center, New York, New York, USA
| | - Amber L Simpson
- School of Computing, Department of Biomedical and Molecular Sciences, Queen's University, Kingston, Ontario, Canada.
| |
Collapse
|
|
8
|
Ai H, Huang Y, Tai DI, Tsui PH, Zhou Z. Ultrasonic Assessment of Liver Fibrosis Using One-Dimensional Convolutional Neural Networks Based on Frequency Spectra of Radiofrequency Signals with Deep Learning Segmentation of Liver Regions in B-Mode Images: A Feasibility Study. SENSORS (BASEL, SWITZERLAND) 2024; 24:5513. [PMID: 39275424 PMCID: PMC11397918 DOI: 10.3390/s24175513] [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: 06/20/2024] [Revised: 08/22/2024] [Accepted: 08/23/2024] [Indexed: 09/16/2024]
Abstract
The early detection of liver fibrosis is of significant importance. Deep learning analysis of ultrasound backscattered radiofrequency (RF) signals is emerging for tissue characterization as the RF signals carry abundant information related to tissue microstructures. However, the existing methods only used the time-domain information of the RF signals for liver fibrosis assessment, and the liver region of interest (ROI) is outlined manually. In this study, we proposed an approach for liver fibrosis assessment using deep learning models on ultrasound RF signals. The proposed method consisted of two-dimensional (2D) convolutional neural networks (CNNs) for automatic liver ROI segmentation from reconstructed B-mode ultrasound images and one-dimensional (1D) CNNs for liver fibrosis stage classification based on the frequency spectra (amplitude, phase, and power) of the segmented ROI signals. The Fourier transform was used to obtain the three kinds of frequency spectra. Two classical 2D CNNs were employed for liver ROI segmentation: U-Net and Attention U-Net. ROI spectrum signals were normalized and augmented using a sliding window technique. Ultrasound RF signals collected (with a 3-MHz transducer) from 613 participants (Group A) were included for liver ROI segmentation and those from 237 participants (Group B) for liver fibrosis stage classification, with a liver biopsy as the reference standard (Fibrosis stage: F0 = 27, F1 = 49, F2 = 51, F3 = 49, F4 = 61). In the test set of Group A, U-Net and Attention U-Net yielded Dice similarity coefficients of 95.05% and 94.68%, respectively. In the test set of Group B, the 1D CNN performed the best when using ROI phase spectrum signals to evaluate liver fibrosis stages ≥F1 (area under the receive operating characteristic curve, AUC: 0.957; accuracy: 89.19%; sensitivity: 85.17%; specificity: 93.75%), ≥F2 (AUC: 0.808; accuracy: 83.34%; sensitivity: 87.50%; specificity: 78.57%), and ≥F4 (AUC: 0.876; accuracy: 85.71%; sensitivity: 77.78%; specificity: 94.12%), and when using the power spectrum signals to evaluate ≥F3 (AUC: 0.729; accuracy: 77.14%; sensitivity: 77.27%; specificity: 76.92%). The experimental results demonstrated the feasibility of both the 2D and 1D CNNs in liver parenchyma detection and liver fibrosis characterization. The proposed methods have provided a new strategy for liver fibrosis assessment based on ultrasound RF signals, especially for early fibrosis detection. The findings of this study shed light on deep learning analysis of ultrasound RF signals in the frequency domain with automatic ROI segmentation.
Collapse
Affiliation(s)
- Haiming Ai
- Faculty of Science and Technology, Beijing Open University, Beijing 100081, China;
| | - Yong Huang
- Department of Biomedical Engineering, College of Chemistry and Life Science, Beijing University of Technology, Beijing 100124, China;
| | - Dar-In Tai
- Department of Gastroenterology and Hepatology, Chang Gung Memorial Hospital at Linkou, Chang Gung University, Taoyuan 333423, Taiwan;
| | - Po-Hsiang Tsui
- Department of Medical Imaging and Radiological Sciences, College of Medicine, Chang Gung University, Taoyuan 333323, Taiwan
- Division of Pediatric Gastroenterology, Department of Pediatrics, Chang Gung Memorial Hospital at Linkou, Taoyuan 333423, Taiwan
- Liver Research Center, Chang Gung Memorial Hospital at Linkou, Taoyuan 333423, Taiwan
- Research Center for Radiation Medicine, Chang Gung University, Taoyuan 333323, Taiwan
| | - Zhuhuang Zhou
- Department of Biomedical Engineering, College of Chemistry and Life Science, Beijing University of Technology, Beijing 100124, China;
| |
Collapse
|
|
9
|
Nakajo M, Hirahara D, Jinguji M, Ojima S, Hirahara M, Tani A, Takumi K, Kamimura K, Ohishi M, Yoshiura T. Machine learning approach using 18F-FDG-PET-radiomic features and the visibility of right ventricle 18F-FDG uptake for predicting clinical events in patients with cardiac sarcoidosis. Jpn J Radiol 2024; 42:744-752. [PMID: 38491333 PMCID: PMC11217075 DOI: 10.1007/s11604-024-01546-y] [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: 12/20/2023] [Accepted: 02/05/2024] [Indexed: 03/18/2024]
Abstract
OBJECTIVES To investigate the usefulness of machine learning (ML) models using pretreatment 18F-FDG-PET-based radiomic features for predicting adverse clinical events (ACEs) in patients with cardiac sarcoidosis (CS). MATERIALS AND METHODS This retrospective study included 47 patients with CS who underwent 18F-FDG-PET/CT scan before treatment. The lesions were assigned to the training (n = 38) and testing (n = 9) cohorts. In total, 49 18F-FDG-PET-based radiomic features and the visibility of right ventricle 18F-FDG uptake were used to predict ACEs using seven different ML algorithms (namely, decision tree, random forest [RF], neural network, k-nearest neighbors, Naïve Bayes, logistic regression, and support vector machine [SVM]) with tenfold cross-validation and the synthetic minority over-sampling technique. The ML models were constructed using the top four features ranked by the decrease in Gini impurity. The AUCs and accuracies were used to compare predictive performances. RESULTS Patients who developed ACEs presented with a significantly higher surface area and gray level run length matrix run length non-uniformity (GLRLM_RLNU), and lower neighborhood gray-tone difference matrix_coarseness and sphericity than those without ACEs (each, p < 0.05). In the training cohort, all seven ML algorithms had a good classification performance with AUC values of > 0.80 (range: 0.841-0.944). In the testing cohort, the RF algorithm had the highest AUC and accuracy (88.9% [8/9]) with a similar classification performance between training and testing cohorts (AUC: 0.945 vs 0.889). GLRLM_RLNU was the most important feature of the modeling process of this RF algorithm. CONCLUSION ML analyses using 18F-FDG-PET-based radiomic features may be useful for predicting ACEs in patients with CS.
Collapse
Affiliation(s)
- Masatoyo Nakajo
- Department of Radiology, Graduate School of Medical and Dental Sciences, Kagoshima University, 8-35-1 Sakuragaoka, Kagoshima, 890-8544, Japan.
| | - Daisuke Hirahara
- Department of Management Planning Division, Harada Academy, 2-54-4 Higashitaniyama, Kagoshima, 890-0113, Japan
| | - Megumi Jinguji
- Department of Radiology, Graduate School of Medical and Dental Sciences, Kagoshima University, 8-35-1 Sakuragaoka, Kagoshima, 890-8544, Japan
| | - Satoko Ojima
- Department of Cardiovascular Medicine and Hypertension, Graduate School of Medical and Dental Sciences, Kagoshima University, 8-35-1 Sakuragaoka, Kagoshima, 890-8544, Japan
| | - Mitsuho Hirahara
- Department of Radiology, Graduate School of Medical and Dental Sciences, Kagoshima University, 8-35-1 Sakuragaoka, Kagoshima, 890-8544, Japan
| | - Atsushi Tani
- Department of Radiology, Graduate School of Medical and Dental Sciences, Kagoshima University, 8-35-1 Sakuragaoka, Kagoshima, 890-8544, Japan
| | - Koji Takumi
- Department of Radiology, Graduate School of Medical and Dental Sciences, Kagoshima University, 8-35-1 Sakuragaoka, Kagoshima, 890-8544, Japan
| | - Kiyohisa Kamimura
- Department of Radiology, Graduate School of Medical and Dental Sciences, Kagoshima University, 8-35-1 Sakuragaoka, Kagoshima, 890-8544, Japan
| | - Mitsuru Ohishi
- Department of Cardiovascular Medicine and Hypertension, Graduate School of Medical and Dental Sciences, Kagoshima University, 8-35-1 Sakuragaoka, Kagoshima, 890-8544, Japan
| | - Takashi Yoshiura
- Department of Radiology, Graduate School of Medical and Dental Sciences, Kagoshima University, 8-35-1 Sakuragaoka, Kagoshima, 890-8544, Japan
| |
Collapse
|
|
10
|
Daye D, Parker R, Tripathi S, Cox M, Brito Orama S, Valentin L, Bridge CP, Uppot RN. CASCADE: Context-Aware Data-Driven AI for Streamlined Multidisciplinary Tumor Board Recommendations in Oncology. Cancers (Basel) 2024; 16:1975. [PMID: 38893096 PMCID: PMC11171258 DOI: 10.3390/cancers16111975] [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: 05/06/2024] [Revised: 05/18/2024] [Accepted: 05/22/2024] [Indexed: 06/21/2024] Open
Abstract
This study addresses the potential of machine learning in predicting treatment recommendations for patients with hepatocellular carcinoma (HCC). Using an IRB-approved retrospective study of patients discussed at a multidisciplinary tumor board, clinical and imaging variables were extracted and used in a gradient-boosting machine learning algorithm, XGBoost. The algorithm's performance was assessed using confusion matrix metrics and the area under the Receiver Operating Characteristics (ROC) curve. The study included 140 patients (mean age 67.7 ± 8.9 years), and the algorithm was found to be predictive of all eight treatment recommendations made by the board. The model's predictions were more accurate than those based on published therapeutic guidelines by ESMO and NCCN. The study concludes that a machine learning model incorporating clinical and imaging variables can predict treatment recommendations made by an expert multidisciplinary tumor board, potentially aiding clinical decision-making in settings lacking subspecialty expertise.
Collapse
Affiliation(s)
- Dania Daye
- Massachusetts General Hospital, Boston, MA 02114, USA; (S.T.); (M.C.); (L.V.); (C.P.B.); (R.N.U.)
- Harvard Medical School, Boston, MA 02115, USA;
- Athinoula A. Martinos Center for Biomedical Imaging, Charlestown, MA 02129, USA
| | | | - Satvik Tripathi
- Massachusetts General Hospital, Boston, MA 02114, USA; (S.T.); (M.C.); (L.V.); (C.P.B.); (R.N.U.)
- Harvard Medical School, Boston, MA 02115, USA;
- Athinoula A. Martinos Center for Biomedical Imaging, Charlestown, MA 02129, USA
| | - Meredith Cox
- Massachusetts General Hospital, Boston, MA 02114, USA; (S.T.); (M.C.); (L.V.); (C.P.B.); (R.N.U.)
- Harvard Medical School, Boston, MA 02115, USA;
| | | | - Leonardo Valentin
- Massachusetts General Hospital, Boston, MA 02114, USA; (S.T.); (M.C.); (L.V.); (C.P.B.); (R.N.U.)
- Professional Hospital Guaynabo, Guaynabo 00971, Puerto Rico
| | - Christopher P. Bridge
- Massachusetts General Hospital, Boston, MA 02114, USA; (S.T.); (M.C.); (L.V.); (C.P.B.); (R.N.U.)
- Harvard Medical School, Boston, MA 02115, USA;
- Athinoula A. Martinos Center for Biomedical Imaging, Charlestown, MA 02129, USA
| | - Raul N. Uppot
- Massachusetts General Hospital, Boston, MA 02114, USA; (S.T.); (M.C.); (L.V.); (C.P.B.); (R.N.U.)
- Harvard Medical School, Boston, MA 02115, USA;
| |
Collapse
|
|
11
|
Stefanini B, Ielasi L, Pallotta DP, Penazza S, Marseglia M, Piscaglia F. Intermediate-stage hepatocellular carcinoma: refining substaging or shifting paradigm? JOURNAL OF LIVER CANCER 2024; 24:23-32. [PMID: 38468499 PMCID: PMC10990660 DOI: 10.17998/jlc.2024.02.21] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 01/30/2024] [Revised: 02/20/2024] [Accepted: 02/21/2024] [Indexed: 03/13/2024]
Abstract
This review explores the evolution of cancer staging, focusing on intermediate hepatocellular carcinoma (HCC), and the challenges faced by physicians. The Barcelona Clinic Liver Cancer (BCLC) staging system, introduced in 1999, was designed to address the limitations associated with providing accurate prognostic information for HCC and allocating specific treatments, to avoid overtreatment. However, criticism has emerged, particularly regarding the intermediate stage of HCC (BCLC-B) and its heterogeneous patient population. To overcome this limitation, various subclassification systems, such as the Bolondi and Kinki criteria, have been proposed. These systems are aimed at refining categorizations within the intermediate stage and have demonstrated varying degrees of success in predicting outcomes through external validation. This study discusses the shift in treatment paradigms, emphasizing the need for a more personalized approach rather than strictly adhering to cancer stages, without dismissing the relevance of staging systems. It assesses the available treatment options for intermediate-stage HCC, highlighting the importance of considering surgical and nonsurgical options alongside transarterial chemoembolization for optimal outcomes. In conclusion, the text advocates for a paradigm shift in staging systems prioritizing treatment suitability over cancer stage. This reflects the evolving landscape of HCC management, where a multidisciplinary approach is crucial for tailoring treatments to individual patients, ultimately aiming to improve overall survival.
Collapse
Affiliation(s)
- Bernardo Stefanini
- Department of Medical and Surgical Sciences, University of Bologna, Bologna, Italy
| | - Luca Ielasi
- Department of Internal Medicine, Ospedale degli Infermi, Faenza, Italy
| | - Dante Pio Pallotta
- Department of Medical and Surgical Sciences, University of Bologna, Bologna, Italy
| | - Sofia Penazza
- Divison of Hepatobiliary and Immunoallergic Diseases, Department of Internal Medicine, IRCCS Azienda Ospedaliero, Universitaria di Bologna, Bologna, Italy
| | - Mariarosaria Marseglia
- Divison of Hepatobiliary and Immunoallergic Diseases, Department of Internal Medicine, IRCCS Azienda Ospedaliero, Universitaria di Bologna, Bologna, Italy
| | - Fabio Piscaglia
- Department of Medical and Surgical Sciences, University of Bologna, Bologna, Italy
- Divison of Hepatobiliary and Immunoallergic Diseases, Department of Internal Medicine, IRCCS Azienda Ospedaliero, Universitaria di Bologna, Bologna, Italy
| |
Collapse
|
|
12
|
Wu Z, Chen H, Chen Q, Ge S, Yu N, Campi R, Gómez Rivas J, Autorino R, Rouprêt M, Psutka SP, Mehrazin R, Porpiglia F, Bensalah K, Black PC, Mir MC, Minervini A, Djaladat H, Margulis V, Bertolo R, Caliò A, Carbonara U, Amparore D, Borregales LD, Ciccarese C, Diana P, Erdem S, Marandino L, Marchioni M, Muselaers CHJ, Palumbo C, Pavan N, Pecoraro A, Roussel E, Warren H, Pandolfo SD, Chen R, Zhou W, Zhai W, He M, Li Y, Han B, Wan J, Zeng X, Yan J, Fu Y, Ji C, Fan X, Zhang G, Zhao C, Jing T, Wang A, Feng C, Zhao H, Sun D, Wang L, Tai S, Zhang C, Chen S, Liu Y, Xu Z, Wang H, Gao J, Wang F, Cheng J, Miao H, Rao Q, Wang J, Xu N, Wang G, Liang C, Liu Z, Xia D, Jiang J, Zu X, Chen M, Guo H, Qin W, Wang Z, Xue W, Shi B, Zhou X, Wang S, Zheng J, Ge J, Feng X, Li M, Chen C, Qu L, Wang L. Prognostic Significance of Grade Discrepancy Between Primary Tumor and Venous Thrombus in Nonmetastatic Clear-cell Renal Cell Carcinoma: Analysis of the REMEMBER Registry and Implications for Adjuvant Therapy. Eur Urol Oncol 2024; 7:112-121. [PMID: 37468393 DOI: 10.1016/j.euo.2023.06.006] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/17/2023] [Revised: 06/14/2023] [Accepted: 06/26/2023] [Indexed: 07/21/2023]
Abstract
BACKGROUND Further stratification of the risk of recurrence of clear-cell renal cell carcinoma (ccRCC) with venous tumor thrombus (VTT) will facilitate selection of candidates for adjuvant therapy. OBJECTIVE To assess the impact of tumor grade discrepancy (GD) between the primary tumor (PT) and VTT in nonmetastatic ccRCC on disease-free survival (DFS), overall survival (OS), and cancer-specific survival (CSS). DESIGN, SETTING, AND PARTICIPANTS This was a retrospective analysis of a multi-institutional nationwide data set for patients with pT3N0M0 ccRCC who underwent radical nephrectomy and thrombectomy. OUTCOMES MEASUREMENTS AND STATISTICAL ANALYSIS Pathology slides were centrally reviewed. GD, a bidirectional variable (upgrading or downgrading), was numerically defined as the VTT grade minus the PT grade. Multivariable models were built to predict DFS, OS, and CSS. RESULTS AND LIMITATIONS We analyzed data for 604 patients with median follow-up of 42 mo (excluding events). Tumor GD between VTT and PT was observed for 47% (285/604) of the patients and was an independent risk factor with incremental value in predicting the outcomes of interest (all p < 0.05). Incorporation of tumor GD significantly improved the performance of the ECOG-ACRIN 2805 (ASSURE) model. A GD-based model (PT grade, GD, pT stage, PT sarcomatoid features, fat invasion, and VTT consistency) had a c index of 0.72 for DFS. The hazard ratios were 8.0 for GD = +2 (p < 0.001), 1.9 for GD = +1 (p < 0.001), 0.57 for GD = -1 (p = 0.001), and 0.22 for GD = -2 (p = 0.003) versus GD = 0 as the reference. According to model-converted risk scores, DFS, OS, and CSS significantly differed between subgroups with low, intermediate, and high risk (all p < 0.001). CONCLUSIONS Routine reporting of VTT upgrading or downgrading in relation to the PT and use of our GD-based nomograms can facilitate more informed treatment decisions by tailoring strategies to an individual patient's risk of progression. PATIENT SUMMARY We developed a tool to improve patient counseling and guide decision-making on other therapies in addition to surgery for patients with the clear-cell type of kidney cancer and tumor invasion of a vein.
Collapse
Affiliation(s)
- Zhenjie Wu
- Department of Urology, Changhai Hospital, Naval Medical University, Shanghai, China; European Association of Urology Young Academic Urologists Renal Cancer Working Group, Arnhem, The Netherlands.
| | - Hui Chen
- Department of Pathology, Jinling Hospital, Clinical School of Nanjing University Medical College, Nanjing, China
| | - Qi Chen
- Department of Health Statistics, Naval Medical University, Shanghai, China
| | - Silun Ge
- Department of Urology, Jinling Hospital, Jinling School of Clinical Medicine, Nanjing Medical University, Nanjing, China
| | - Nengwang Yu
- Department of Urology, Qilu Hospital, Shandong University, Jinan, China
| | - Riccardo Campi
- European Association of Urology Young Academic Urologists Renal Cancer Working Group, Arnhem, The Netherlands; Unit of Urological Robotic Surgery and Renal Transplantation, Careggi Hospital, University of Florence, Florence, Italy; Department of Experimental and Clinical Medicine, University of Florence, Florence, Italy
| | - Juan Gómez Rivas
- Department of Urology, Hospital Clinico San Carlos, Madrid, Spain
| | - Riccardo Autorino
- Department of Urology, Rush University Medical Center, Chicago, IL, USA
| | - Morgan Rouprêt
- Department of Urology, GRC No. 5, Predictive ONCO-URO, Hospital Pitié-Salpêtrière, AP-HP, Sorbonne University, Paris, France
| | - Sarah P Psutka
- Department of Urology, University of Washington, Seattle Cancer Care Alliance, Seattle, WA, USA
| | - Reza Mehrazin
- Department of Urology, Icahn School of Medicine at Mount Sinai, New York, NY, USA
| | - Francesco Porpiglia
- Division of Urology, Department of Oncology, School of Medicine, San Luigi Hospital, University of Turin, Orbassano, Italy
| | - Karim Bensalah
- Department of Urology, University of Rennes, Rennes, France
| | - Peter C Black
- Department of Urologic Sciences, The University of British Columbia, Vancouver, British Columbia, Canada
| | - Maria C Mir
- Department of Urology; Hospital Universitario La Ribera; Valencia, Spain
| | - Andrea Minervini
- Departments of Urology and Experimental and Clinical Medicine, University of Florence, Florence, Italy
| | - Hooman Djaladat
- Institute of Urology, University of Southern California, Los Angeles, CA, USA
| | - Vitaly Margulis
- Department of Urology, University of Texas Southwestern Medical Center, Dallas, TX, USA
| | - Riccardo Bertolo
- European Association of Urology Young Academic Urologists Renal Cancer Working Group, Arnhem, The Netherlands; Urology Unit, San Carlo di Nancy Hospital, Rome, Italy
| | - Anna Caliò
- European Association of Urology Young Academic Urologists Renal Cancer Working Group, Arnhem, The Netherlands; Department of Diagnostic and Public Health, University of Verona, Verona, Italy
| | - Umberto Carbonara
- European Association of Urology Young Academic Urologists Renal Cancer Working Group, Arnhem, The Netherlands; Department of Emergency and Organ Transplantation-Urology, Andrology and Kidney Transplantation Unit, University of Bari, Bari, Italy
| | - Daniele Amparore
- European Association of Urology Young Academic Urologists Renal Cancer Working Group, Arnhem, The Netherlands; Division of Urology, Department of Oncology, School of Medicine, San Luigi Hospital, University of Turin, Orbassano, Italy
| | - Leonardo D Borregales
- European Association of Urology Young Academic Urologists Renal Cancer Working Group, Arnhem, The Netherlands; Department of Urology, Weill Cornell Medicine/New York-Presbyterian, New York, NY, USA
| | - Chiara Ciccarese
- European Association of Urology Young Academic Urologists Renal Cancer Working Group, Arnhem, The Netherlands; Medical Oncology Unit, Comprehensive Cancer Center, Fondazione Policlinico Universitario A. Gemelli IRCCS, Rome, Italy
| | - Pietro Diana
- European Association of Urology Young Academic Urologists Renal Cancer Working Group, Arnhem, The Netherlands; Department of Urology, Fundació Puigvert, Autonoma University of Barcelona, Barcelona, Spain
| | - Selcuk Erdem
- European Association of Urology Young Academic Urologists Renal Cancer Working Group, Arnhem, The Netherlands; Division of Urologic Oncology, Department of Urology, Istanbul University Faculty of Medicine, Istanbul, Turkey
| | - Laura Marandino
- European Association of Urology Young Academic Urologists Renal Cancer Working Group, Arnhem, The Netherlands; Department of Oncology, IRCCS Ospedale San Raffaele, Milan, Italy
| | - Michele Marchioni
- European Association of Urology Young Academic Urologists Renal Cancer Working Group, Arnhem, The Netherlands; Department of Medical, Oral and Biotechnological Sciences, Urology Unit, University G. d'Annunzio, Chieti, Italy
| | - Constantijn H J Muselaers
- European Association of Urology Young Academic Urologists Renal Cancer Working Group, Arnhem, The Netherlands; Department of Urology, Radboud University Medical Center, Nijmegen, The Netherlands
| | - Carlotta Palumbo
- European Association of Urology Young Academic Urologists Renal Cancer Working Group, Arnhem, The Netherlands; Division of Urology, Department of Translational Medicine, University of Eastern Piedmont, Maggiore della Carità Hospital, Novara, Italy
| | - Nicola Pavan
- European Association of Urology Young Academic Urologists Renal Cancer Working Group, Arnhem, The Netherlands; Urology Clinic, Department of Surgical, Oncological, and Oral Sciences, University of Palermo, Palermo, Italy
| | - Angela Pecoraro
- European Association of Urology Young Academic Urologists Renal Cancer Working Group, Arnhem, The Netherlands; Department of Urology, Pederzoli Hospital, Peschiera del Garda, Italy
| | - Eduard Roussel
- European Association of Urology Young Academic Urologists Renal Cancer Working Group, Arnhem, The Netherlands; Department of Urology, University Hospitals Leuven, Leuven, Belgium
| | - Hannah Warren
- European Association of Urology Young Academic Urologists Renal Cancer Working Group, Arnhem, The Netherlands; Division of Surgery and Interventional Science, University College London, London, UK
| | - Savio Domenico Pandolfo
- Department of Neurosciences, Reproductive Sciences and Odontostomatology, University of Naples Federico II, Naples, Italy
| | - Rui Chen
- Department of Urology, Changhai Hospital, Naval Medical University, Shanghai, China
| | - Wenquan Zhou
- Department of Urology, Jinling Hospital, Clinical School of Nanjing University Medical College, Nanjing, China
| | - Wei Zhai
- Department of Urology, Renji Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai, China
| | - Miaoxia He
- Department of Pathology, Changhai Hospital, Naval Medical University, Shanghai, China
| | - Yaoming Li
- Department of Urology, Daping Hospital, Army Medical University, Chongqing, China
| | - Bo Han
- Department of Pathology, Qilu Hospital, Shandong University, Jinan, China
| | - Jie Wan
- Department of Pathology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Xing Zeng
- Department of Urology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Junan Yan
- Department of Urology, Southwest Hospital, Army Medical University, Chongqing, China
| | - Yao Fu
- Department of Pathology, Drum Tower Hospital, Clinical School of Nanjing University Medical College, Nanjing, China
| | - Changwei Ji
- Department of Urology, Drum Tower Hospital, Clinical School of Nanjing University Medical College, Nanjing, China
| | - Xiang Fan
- Department of Pathology, Zhongda Hospital, Southeast University, Nanjing, China
| | - Guangyuan Zhang
- Department of Urology, Zhongda Hospital, Southeast University, Nanjing, China
| | - Cheng Zhao
- Department of Urology, Xiangya Hospital, Central South University, Changsha, China
| | - Taile Jing
- Department of Urology, The First Affiliated Hospital, School of Medicine, Zhejiang University, Hangzhou, China
| | - Anbang Wang
- Department of Urology, Changzheng Hospital, Naval Medical University, Shanghai, China
| | - Chenchen Feng
- Department of Urology, Huashan Hospital, Fudan University, Shanghai, China
| | - Hongwei Zhao
- Department of Urology, Affiliated Yantai Yuhuangding Hospital, Qingdao University, Yantai, China
| | - Di Sun
- Department of Pathology, Affiliated Yantai Yuhuangding Hospital, Qingdao University, Yantai, China
| | - Liang Wang
- Department of Urology, The Second Affiliated Hospital of Dalian Medical University, Dalian, China
| | - Sheng Tai
- Department of Urology, The First Affiliated Hospital of Anhui Medical University, Hefei, China
| | - Cheng Zhang
- Department of Urology, The First Affiliated Hospital of Nanchang University, Nanchang, China
| | - Shaohao Chen
- Department of Urology, Urology Research Institute, The First Affiliated Hospital, Fujian Medical University, Fuzhou, China
| | - Yixun Liu
- Department of Urology, Anhui Provincial Hospital/The First Hospital of the University of Science and Technology of China, Hefei, China
| | - Zhipeng Xu
- Department of Urology, The First Affiliated Hospital of Shandong First Medical University, Jinan, China
| | - Haifeng Wang
- Department of Urology, Shanghai East Hospital, Tongji University, Shanghai, China
| | - Jinli Gao
- Department of Pathology, Shanghai East Hospital, Tongji University, Shanghai, China
| | - Fubo Wang
- Center for Genomic and Personalized Medicine, Guangxi Medical University, Nanning, China
| | - Jiwen Cheng
- Department of Urology, The First Affiliated Hospital of Guangxi Medical University, Nanning, China
| | - He Miao
- Department of Urology, Jinling Hospital, Jinling School of Clinical Medicine, Nanjing Medical University, Nanjing, China
| | - Qiu Rao
- Department of Pathology, Jinling Hospital, Clinical School of Nanjing University Medical College, Nanjing, China
| | - Jianning Wang
- Department of Urology, The First Affiliated Hospital of Shandong First Medical University, Jinan, China
| | - Ning Xu
- Department of Urology, Urology Research Institute, The First Affiliated Hospital, Fujian Medical University, Fuzhou, China
| | - Gongxian Wang
- Department of Urology, The First Affiliated Hospital of Nanchang University, Nanchang, China
| | - Chaozhao Liang
- Department of Urology, The First Affiliated Hospital of Anhui Medical University, Hefei, China
| | - Zhiyu Liu
- Department of Urology, The Second Affiliated Hospital of Dalian Medical University, Dalian, China
| | - Dan Xia
- Department of Urology, The First Affiliated Hospital, School of Medicine, Zhejiang University, Hangzhou, China
| | - Jun Jiang
- Department of Urology, Daping Hospital, Army Medical University, Chongqing, China
| | - Xiongbing Zu
- Department of Urology, Xiangya Hospital, Central South University, Changsha, China
| | - Ming Chen
- Department of Urology, Zhongda Hospital, Southeast University, Nanjing, China
| | - Hongqian Guo
- Department of Urology, Drum Tower Hospital, Clinical School of Nanjing University Medical College, Nanjing, China
| | - Weijun Qin
- Department of Urology, Xijing Hospital, Fourth Military Medical University, Xi'an, China
| | - Zhe Wang
- Department of Pathology, Xijing Hospital, Fourth Military Medical University, Xi'an, China
| | - Wei Xue
- Department of Urology, Renji Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai, China
| | - Benkang Shi
- Department of Urology, Qilu Hospital, Shandong University, Jinan, China
| | - Xiaojun Zhou
- Department of Pathology, Jinling Hospital, Clinical School of Nanjing University Medical College, Nanjing, China
| | - Shaogang Wang
- Department of Urology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Junhua Zheng
- Department of Urology, Renji Hospital, School of Medicine, Shanghai Jiao Tong University, Shanghai, China
| | - Jingping Ge
- Department of Urology, Jinling Hospital, Clinical School of Nanjing University Medical College, Nanjing, China
| | - Xiang Feng
- Department of Urology, Changhai Hospital, Naval Medical University, Shanghai, China.
| | - Minming Li
- Department of Radiology, Changhai Hospital, Naval Medical University, Shanghai, China.
| | - Cheng Chen
- Department of Medical Oncology, Jinling Hospital, Clinical School of Nanjing University Medical College, Nanjing, China.
| | - Le Qu
- Department of Urology, Jinling Hospital, Clinical School of Nanjing University Medical College, Nanjing, China.
| | - Linhui Wang
- Department of Urology, Changhai Hospital, Naval Medical University, Shanghai, China.
| |
Collapse
|
|
13
|
Schönnagel L, Caffard T, Vu-Han TL, Zhu J, Nathoo I, Finos K, Camino-Willhuber G, Tani S, Guven AE, Haffer H, Muellner M, Arzani A, Chiapparelli E, Amoroso K, Shue J, Duculan R, Pumberger M, Zippelius T, Sama AA, Cammisa FP, Girardi FP, Mancuso CA, Hughes AP. Predicting postoperative outcomes in lumbar spinal fusion: development of a machine learning model. Spine J 2024; 24:239-249. [PMID: 37866485 DOI: 10.1016/j.spinee.2023.09.029] [Citation(s) in RCA: 10] [Impact Index Per Article: 10.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 06/08/2023] [Revised: 09/16/2023] [Accepted: 09/30/2023] [Indexed: 10/24/2023]
Abstract
BACKGROUND CONTEXT Degenerative lumbar spondylolisthesis (DLS) is a prevalent spinal disorder, often requiring surgical intervention. Accurately predicting surgical outcomes is crucial to guide clinical decision-making, but this is challenging due to the multifactorial nature of postoperative results. Traditional risk assessment tools have limitations, and with the advent of machine learning, there is potential to enhance the precision and comprehensiveness of preoperative evaluations. PURPOSE We aimed to develop a machine-learning algorithm to predict surgical outcomes in patients with degenerative lumbar spondylolisthesis (DLS) undergoing spinal fusion surgery, only using preoperative data. STUDY DESIGN Retrospective cross-sectional study. PATIENT SAMPLE Patients with DLS undergoing lumbar spinal fusion surgery. OUTCOME MEASURES This study aimed to predict the occurrence of lower back pain (LBP) ≥4 on the numeric analogue scale (NAS) 2 years after surgery. LBP was evaluated as the average pain patients experienced at rest in the week before questioning. NAS ranges from 0 to 10, 0 representing no pain and 10 representing the worst pain imaginable. METHODS We conducted a retrospective analysis of prospectively enrolled patients who underwent spinal fusion surgery for degenerative lumbar spondylolistheses at our institution in the United States between January 2016 and December 2018. The initial patient characteristics to be included in the training of the model were chosen by clinical expertise and through a literature review and included demographic characteristics, comorbidities, and radiologic features. The data was split into a training and validation datasets using a 60/40 split. Four different machine learning models were trained, including the modern XGBoost model, logistic regression, random-forest, and support vector machine (SVM). The models were evaluated according to the area under the curve (AUC) of the receiver operating characteristics (ROC) curve. An AUC of 0.7 to 0.8 was considered fair, 0.8 to 0.9 good, and ≥ 0.9 excellent. Additionally, a calibration plot and the Brier score were calculated for each model. RESULTS A total of 135 patients (66% female) were included. A total of 38 (28%) patients reported LBP ≥ 4 after 2 years, representing the positive class. The XGBoost model demonstrated the best performance in the validation set with an AUC of 0.81 (95% CI 0.67-0.95). The other machine learning models performed significantly worse: with an AUC of 0.52 (95% CI 0.37-0.68) for the SVM, 0.56 (95% CI 0.37-0.76) for the logistic regression and an AUC of 0.56 (95% CI 0.37-0.78) for the random forest. In the XGBoost model age, composition of the erector spinae, and severity of lumbar spinal stenosis as were identified as the most important features. CONCLUSIONS This study represents a novel approach to predicting surgical outcomes in spinal fusion patients. The XGBoost demonstrated a better performance compared with classical models and highlighted the potential contributions of age and paraspinal musculature atrophy as significant factors. These findings have important implications for enhancing patient care through the identification of high-risk individuals and modifiable risk factors. As the incorporation of machine learning algorithms into clinical decision-making continues to gain traction in research and clinical practice, our insights reinforce this trajectory by showcasing the potential of these techniques in forecasting surgical results.
Collapse
Affiliation(s)
- Lukas Schönnagel
- Spine Care Institute, Hospital for Special Surgery, 535 East 70th Street, New York, NY 10021, USA; Center for Musculoskeletal Surgery, Charité - Universitätsmedizin Berlin, Charitéplatz 1, 10117 Berlin, Germany
| | - Thomas Caffard
- Spine Care Institute, Hospital for Special Surgery, 535 East 70th Street, New York, NY 10021, USA; Universitätsklinikum Ulm, Klinik für Orthopädie, Oberer Eselsberg 45, 89081 Ulm, Germany
| | - Tu-Lan Vu-Han
- Center for Musculoskeletal Surgery, Charité - Universitätsmedizin Berlin, Charitéplatz 1, 10117 Berlin, Germany
| | - Jiaqi Zhu
- Biostatistics Core, Hospital for Special Surgery, 535 East 70th Street, New York, NY 10021, USA
| | - Isaac Nathoo
- Spine Care Institute, Hospital for Special Surgery, 535 East 70th Street, New York, NY 10021, USA
| | - Kyle Finos
- Spine Care Institute, Hospital for Special Surgery, 535 East 70th Street, New York, NY 10021, USA
| | - Gaston Camino-Willhuber
- Spine Care Institute, Hospital for Special Surgery, 535 East 70th Street, New York, NY 10021, USA
| | - Soji Tani
- Spine Care Institute, Hospital for Special Surgery, 535 East 70th Street, New York, NY 10021, USA; Department of Orthopaedic Surgery, School of Medicine, Showa University Hospital, 1-5-8 Hatanodai, Shinagawa-ku, Tokyo 142-8666, Japan
| | - Ali E Guven
- Spine Care Institute, Hospital for Special Surgery, 535 East 70th Street, New York, NY 10021, USA; Center for Musculoskeletal Surgery, Charité - Universitätsmedizin Berlin, Charitéplatz 1, 10117 Berlin, Germany
| | - Henryk Haffer
- Center for Musculoskeletal Surgery, Charité - Universitätsmedizin Berlin, Charitéplatz 1, 10117 Berlin, Germany
| | - Maximilian Muellner
- Center for Musculoskeletal Surgery, Charité - Universitätsmedizin Berlin, Charitéplatz 1, 10117 Berlin, Germany
| | - Artine Arzani
- Spine Care Institute, Hospital for Special Surgery, 535 East 70th Street, New York, NY 10021, USA
| | - Erika Chiapparelli
- Spine Care Institute, Hospital for Special Surgery, 535 East 70th Street, New York, NY 10021, USA
| | - Krizia Amoroso
- Spine Care Institute, Hospital for Special Surgery, 535 East 70th Street, New York, NY 10021, USA
| | - Jennifer Shue
- Spine Care Institute, Hospital for Special Surgery, 535 East 70th Street, New York, NY 10021, USA
| | - Roland Duculan
- Hospital for Special Surgery, 535 East 70th Street, New York, NY 10021, USA
| | - Matthias Pumberger
- Center for Musculoskeletal Surgery, Charité - Universitätsmedizin Berlin, Charitéplatz 1, 10117 Berlin, Germany
| | - Timo Zippelius
- Universitätsklinikum Ulm, Klinik für Orthopädie, Oberer Eselsberg 45, 89081 Ulm, Germany
| | - Andrew A Sama
- Spine Care Institute, Hospital for Special Surgery, 535 East 70th Street, New York, NY 10021, USA
| | - Frank P Cammisa
- Spine Care Institute, Hospital for Special Surgery, 535 East 70th Street, New York, NY 10021, USA
| | - Federico P Girardi
- Spine Care Institute, Hospital for Special Surgery, 535 East 70th Street, New York, NY 10021, USA
| | - Carol A Mancuso
- Hospital for Special Surgery, 535 East 70th Street, New York, NY 10021, USA
| | - Alexander P Hughes
- Spine Care Institute, Hospital for Special Surgery, 535 East 70th Street, New York, NY 10021, USA.
| |
Collapse
|
|
14
|
Fung PL, Al-Jaghbeer O, Pirjola L, Aaltonen H, Järvi L. Exploring the discrepancy between top-down and bottom-up approaches of fine spatio-temporal vehicular CO 2 emission in an urban road network. THE SCIENCE OF THE TOTAL ENVIRONMENT 2023; 901:165827. [PMID: 37517739 DOI: 10.1016/j.scitotenv.2023.165827] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 04/03/2023] [Revised: 07/23/2023] [Accepted: 07/25/2023] [Indexed: 08/01/2023]
Abstract
Road transport emissions of high spatial and temporal resolution are useful for greenhouse gas emission assessment in local action plans. However, estimating these high-resolution emissions is not straightforward, and different indirect approaches exist. The main aim of this study is to examine the differences in CO2 emissions obtained with different methods within a street canyon network in Helsinki, Finland, where a mobile laboratory campaign to quantify traffic emissions has been conducted. We compared three aerodynamic resistance based top-down methods (MOST1, MOST2 and BHT) and three activity based bottom-up microscopic emission models (NGM, HBEFAv4.2 and PHEMlight). The resulted CO2 fluxes using different methods could vary a few orders of magnitude. The combination of MOST1 and NGM model leads to the smallest discrepancy (sMAPE = 16.90 %) and the highest correlation coefficient (r = 0.78) among the rest. We evaluated the discrepancies in terms of different spatial (microenvrionments, local climate zones LCZs and grid sizes) and temporal features (seasons and periods of day). Measurements taken in LCZs of open high-rise regions and microenvironments of main road tend to have larger discrepancies between the two approaches. Using a coarser grid would lead to a relatively small discrepancy and high correlation in the wintertime, yet a loss in distinctive spatial variation. The discrepancies were also elevated on winter evenings. Among all explanatory variables, relative humidity shows the strongest relative importance for the discrepancy of the two approaches, followed by LCZs. Therefore, we stress the importance of choosing a suitable model for vehicular CO2 emission calculation based on meteorological conditions and LCZs. Such model comparison made on a local scale directly supports environmental organisations and cities' climate action plans where detailed information of CO2 emissions are needed.
Collapse
Affiliation(s)
- Pak Lun Fung
- Institute for Atmospheric and Earth System Research (INAR)/Physics, Faculty of Science, University of Helsinki, P.O. Box 64, Helsinki 00014, Finland; Helsinki Institute of Sustainability Science (HELSUS), Finland.
| | - Omar Al-Jaghbeer
- Institute for Atmospheric and Earth System Research (INAR)/Physics, Faculty of Science, University of Helsinki, P.O. Box 64, Helsinki 00014, Finland
| | - Liisa Pirjola
- Institute for Atmospheric and Earth System Research (INAR)/Physics, Faculty of Science, University of Helsinki, P.O. Box 64, Helsinki 00014, Finland; Department of Automotive and Mechanical Engineering, Metropolia Applied University, P.O. Box 4071, Vantaa 01600, Finland
| | - Hermanni Aaltonen
- Finnish Meteorological Institute, P.O. Box 503, Helsinki 00101, Finland
| | - Leena Järvi
- Institute for Atmospheric and Earth System Research (INAR)/Physics, Faculty of Science, University of Helsinki, P.O. Box 64, Helsinki 00014, Finland; Helsinki Institute of Sustainability Science (HELSUS), Finland
| |
Collapse
|
|
15
|
Kawaji K, Nakajo M, Shinden Y, Jinguji M, Tani A, Hirahara D, Kitazono I, Ohtsuka T, Yoshiura T. Application of Machine Learning Analyses Using Clinical and [ 18F]-FDG-PET/CT Radiomic Characteristics to Predict Recurrence in Patients with Breast Cancer. Mol Imaging Biol 2023; 25:923-934. [PMID: 37193804 DOI: 10.1007/s11307-023-01823-8] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/08/2022] [Revised: 03/20/2023] [Accepted: 04/28/2023] [Indexed: 05/18/2023]
Abstract
PURPOSE To develop and identify machine learning (ML) models using pretreatment clinical and 2-deoxy-2-[18F]fluoro-D-glucose positron emission tomography ([18F]-FDG-PET)-based radiomic characteristics to predict disease recurrences in patients with breast cancers who underwent surgery. PROCEDURES This retrospective study included 112 patients with 118 breast cancer lesions who underwent [18F]-FDG-PET/ X-ray computed tomography (CT) preoperatively, and these lesions were assigned to training (n=95) and testing (n=23) cohorts. A total of 12 clinical and 40 [18F]-FDG-PET-based radiomic characteristics were used to predict recurrences using 7 different ML algorithms, namely, decision tree, random forest (RF), neural network, k-nearest neighbors, naive Bayes, logistic regression, and support vector machine (SVM) with a 10-fold cross-validation and synthetic minority over-sampling technique. Three different ML models were created using clinical characteristics (clinical ML models), radiomic characteristics (radiomic ML models), and both clinical and radiomic characteristics (combined ML models). Each ML model was constructed using the top ten characteristics ranked by the decrease in Gini impurity. The areas under ROC curves (AUCs) and accuracies were used to compare predictive performances. RESULTS In training cohorts, all 7 ML algorithms except for logistic regression algorithm in the radiomics ML model (AUC = 0.760) achieved AUC values of >0.80 for predicting recurrences with clinical (range, 0.892-0.999), radiomic (range, 0.809-0.984), and combined (range, 0.897-0.999) ML models. In testing cohorts, the RF algorithm of combined ML model achieved the highest AUC and accuracy (95.7% (22/23)) with similar classification performance between training and testing cohorts (AUC: training cohort, 0.999; testing cohort, 0.992). The important characteristics for modeling process of this RF algorithm were radiomic GLZLM_ZLNU and AJCC stage. CONCLUSIONS ML analyses using both clinical and [18F]-FDG-PET-based radiomic characteristics may be useful for predicting recurrence in patients with breast cancers who underwent surgery.
Collapse
Affiliation(s)
- Kodai Kawaji
- Department of Radiology, Kagoshima University, Graduate School of Medical and Dental Sciences, 8-35-1 Sakuragaoka, Kagoshima, 890-8544, Japan
| | - Masatoyo Nakajo
- Department of Radiology, Kagoshima University, Graduate School of Medical and Dental Sciences, 8-35-1 Sakuragaoka, Kagoshima, 890-8544, Japan.
| | - Yoshiaki Shinden
- Department of Digestive Surgery, Breast and Thyroid Surgery, Kagoshima University, Graduate School of Medical and Dental Sciences, 8-35-1 Sakuragaoka, Kagoshima, 890-8544, Japan
| | - Megumi Jinguji
- Department of Radiology, Kagoshima University, Graduate School of Medical and Dental Sciences, 8-35-1 Sakuragaoka, Kagoshima, 890-8544, Japan
| | - Atsushi Tani
- Department of Radiology, Kagoshima University, Graduate School of Medical and Dental Sciences, 8-35-1 Sakuragaoka, Kagoshima, 890-8544, Japan
| | - Daisuke Hirahara
- Department of Management Planning Division, Harada Academy, 2-54-4 Higashitaniyama, Kagoshima, 890-0113, Japan
| | - Ikumi Kitazono
- Department of Pathology, Kagoshima University, Graduate School of Medical and Dental Sciences, 8-35-1 Sakuragaoka, Kagoshima, 890-8544, Japan
| | - Takao Ohtsuka
- Department of Digestive Surgery, Breast and Thyroid Surgery, Kagoshima University, Graduate School of Medical and Dental Sciences, 8-35-1 Sakuragaoka, Kagoshima, 890-8544, Japan
| | - Takashi Yoshiura
- Department of Radiology, Kagoshima University, Graduate School of Medical and Dental Sciences, 8-35-1 Sakuragaoka, Kagoshima, 890-8544, Japan
| |
Collapse
|
|
16
|
Nakajo M, Nagano H, Jinguji M, Kamimura Y, Masuda K, Takumi K, Tani A, Hirahara D, Kariya K, Yamashita M, Yoshiura T. The usefulness of machine-learning-based evaluation of clinical and pretreatment 18F-FDG-PET/CT radiomic features for predicting prognosis in patients with laryngeal cancer. Br J Radiol 2023; 96:20220772. [PMID: 37393538 PMCID: PMC10461278 DOI: 10.1259/bjr.20220772] [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: 08/12/2022] [Revised: 05/24/2023] [Accepted: 05/26/2023] [Indexed: 07/03/2023] Open
Abstract
OBJECTIVE To examine whether machine learning (ML) analyses involving clinical and 18F-FDG-PET-based radiomic features are helpful in predicting prognosis in patients with laryngeal cancer. METHODS This retrospective study included 49 patients with laryngeal cancer who underwent18F-FDG-PET/CT before treatment, and these patients were divided into the training (n = 34) and testing (n = 15) cohorts.Seven clinical (age, sex, tumor size, T stage, N stage, Union for International Cancer Control stage, and treatment) and 40 18F-FDG-PET-based radiomic features were used to predict disease progression and survival. Six ML algorithms (random forest, neural network, k-nearest neighbors, naïve Bayes, logistic regression, and support vector machine) were used for predicting disease progression. Two ML algorithms (cox proportional hazard and random survival forest [RSF] model) considering for time-to-event outcomes were used to assess progression-free survival (PFS), and prediction performance was assessed by the concordance index (C-index). RESULTS Tumor size, T stage, N stage, GLZLM_ZLNU, and GLCM_Entropy were the five most important features for predicting disease progression.In both cohorts, the naïve Bayes model constructed by these five features was the best performing classifier (training: AUC = 0.805; testing: AUC = 0.842). The RSF model using the five features (tumor size, GLZLM_ZLNU, GLCM_Entropy, GLRLM_LRHGE and GLRLM_SRHGE) exhibited the highest performance in predicting PFS (training: C-index = 0.840; testing: C-index = 0.808). CONCLUSION ML analyses involving clinical and 18F-FDG-PET-based radiomic features may help predict disease progression and survival in patients with laryngeal cancer. ADVANCES IN KNOWLEDGE ML approach using clinical and 18F-FDG-PET-based radiomic features has the potential to predict prognosis of laryngeal cancer.
Collapse
Affiliation(s)
- Masatoyo Nakajo
- Department of Radiology, Kagoshima University, Graduate School of Medical and Dental Sciences, Kagoshima, Japan
| | - Hiromi Nagano
- Department of Otolaryngology Head and Neck Surgery, Kagoshima University, Graduate School of Medical and Dental Sciences, Kagoshima, Japan
| | - Megumi Jinguji
- Department of Radiology, Kagoshima University, Graduate School of Medical and Dental Sciences, Kagoshima, Japan
| | - Yoshiki Kamimura
- Department of Radiology, Kagoshima University, Graduate School of Medical and Dental Sciences, Kagoshima, Japan
| | - Keiko Masuda
- Department of Radiology, Kagoshima University, Graduate School of Medical and Dental Sciences, Kagoshima, Japan
| | - Koji Takumi
- Department of Radiology, Kagoshima University, Graduate School of Medical and Dental Sciences, Kagoshima, Japan
| | - Atsushi Tani
- Department of Radiology, Kagoshima University, Graduate School of Medical and Dental Sciences, Kagoshima, Japan
| | - Daisuke Hirahara
- Department of Management Planning Division, Harada Academy, Kagoshima, Japan
| | - Keisuke Kariya
- Department of Radiology, Kagoshima University, Graduate School of Medical and Dental Sciences, Kagoshima, Japan
| | - Masaru Yamashita
- Department of Otolaryngology Head and Neck Surgery, Kagoshima University, Graduate School of Medical and Dental Sciences, Kagoshima, Japan
| | - Takashi Yoshiura
- Department of Radiology, Kagoshima University, Graduate School of Medical and Dental Sciences, Kagoshima, Japan
| |
Collapse
|
|
17
|
The Usefulness of Machine Learning-Based Evaluation of Clinical and Pretreatment [ 18F]-FDG-PET/CT Radiomic Features for Predicting Prognosis in Hypopharyngeal Cancer. Mol Imaging Biol 2023; 25:303-313. [PMID: 35864282 DOI: 10.1007/s11307-022-01757-7] [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: 04/12/2022] [Revised: 06/06/2022] [Accepted: 07/11/2022] [Indexed: 10/17/2022]
Abstract
PURPOSE To examine whether the machine learning (ML) analyses using clinical and pretreatment 2-deoxy-2-[18F]fluoro-D-glucose positron emission tomography ([18F]-FDG-PET)-based radiomic features were useful for predicting prognosis in patients with hypopharyngeal cancer. PROCEDURES This retrospective study included 100 patients with hypopharyngeal cancer who underwent [18F]-FDG-PET/X-ray computed tomography (CT) before treatment, and these patients were allocated to the training (n=80) and validation (n=20) cohorts. Eight clinical (age, sex, histology, T stage, N stage, M stage, UICC stage, and treatment) and 40 [18F]-FDG-PET-based radiomic features were used to predict disease progression. A feature reduction procedure based on the decrease of the Gini impurity was applied. Six ML algorithms (random forest, neural network, k-nearest neighbors, naïve Bayes, logistic regression, and support vector machine) were compared using the area under the receiver operating characteristic curve (AUC). Progression-free survival (PFS) was assessed using Cox regression analysis. RESULTS The five most important features for predicting disease progression were UICC stage, N stage, gray level co-occurrence matrix entropy (GLCM_Entropy), gray level run length matrix run length non-uniformity (GLRLM_RLNU), and T stage. Patients who experienced disease progression displayed significantly higher UICC stage, N stage, GLCM_Entropy, GLRLM_RLNU, and T stage than those without progression (each, p<0.001). In both cohorts, the logistic regression model constructed by these 5 features was the best performing classifier (training: AUC=0.860, accuracy=0.800; validation: AUC=0.803, accuracy=0.700). In the logistic regression model, 5-year PFS was significantly higher in patients with predicted non-progression than those with predicted progression (75.8% vs. 8.3%, p<0.001), and this model was only the independent factor for PFS in multivariate analysis (hazard ratio = 3.22; 95% confidence interval = 1.03-10.11; p=0.045). CONCLUSIONS The logistic regression model constructed by UICC, T and N stages and pretreatment [18F]-FDG-PET-based radiomic features, GLCM_Entropy, and GLRLM_RLNU may be the most important predictor of prognosis in patients with hypopharyngeal cancer.
Collapse
|
|
18
|
Patterson A, Elbasir A, Tian B, Auslander N. Computational Methods Summarizing Mutational Patterns in Cancer: Promise and Limitations for Clinical Applications. Cancers (Basel) 2023; 15:1958. [PMID: 37046619 PMCID: PMC10093138 DOI: 10.3390/cancers15071958] [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: 10/27/2022] [Revised: 02/24/2023] [Accepted: 03/09/2023] [Indexed: 03/29/2023] Open
Abstract
Since the rise of next-generation sequencing technologies, the catalogue of mutations in cancer has been continuously expanding. To address the complexity of the cancer-genomic landscape and extract meaningful insights, numerous computational approaches have been developed over the last two decades. In this review, we survey the current leading computational methods to derive intricate mutational patterns in the context of clinical relevance. We begin with mutation signatures, explaining first how mutation signatures were developed and then examining the utility of studies using mutation signatures to correlate environmental effects on the cancer genome. Next, we examine current clinical research that employs mutation signatures and discuss the potential use cases and challenges of mutation signatures in clinical decision-making. We then examine computational studies developing tools to investigate complex patterns of mutations beyond the context of mutational signatures. We survey methods to identify cancer-driver genes, from single-driver studies to pathway and network analyses. In addition, we review methods inferring complex combinations of mutations for clinical tasks and using mutations integrated with multi-omics data to better predict cancer phenotypes. We examine the use of these tools for either discovery or prediction, including prediction of tumor origin, treatment outcomes, prognosis, and cancer typing. We further discuss the main limitations preventing widespread clinical integration of computational tools for the diagnosis and treatment of cancer. We end by proposing solutions to address these challenges using recent advances in machine learning.
Collapse
Affiliation(s)
- Andrew Patterson
- Genomics and Computational Biology Graduate Group, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104, USA
- The Wistar Institute, Philadelphia, PA 19104, USA
| | | | - Bin Tian
- The Wistar Institute, Philadelphia, PA 19104, USA
| | - Noam Auslander
- The Wistar Institute, Philadelphia, PA 19104, USA
- Department of Cancer Biology, University of Pennsylvania, Philadelphia, PA 19104, USA
| |
Collapse
|
|
19
|
Garg N, Choudhry MS, Bodade RM. A review on Alzheimer's disease classification from normal controls and mild cognitive impairment using structural MR images. J Neurosci Methods 2023; 384:109745. [PMID: 36395961 DOI: 10.1016/j.jneumeth.2022.109745] [Citation(s) in RCA: 12] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/04/2022] [Revised: 10/04/2022] [Accepted: 11/11/2022] [Indexed: 11/16/2022]
Abstract
Alzheimer's disease (AD) is an irreversible neurodegenerative brain disorder that degrades the memory and cognitive ability in elderly people. The main reason for memory loss and reduction in cognitive ability is the structural changes in the brain that occur due to neuronal loss. These structural changes are most conspicuous in the hippocampus, cortex, and grey matter and can be assessed by using neuroimaging techniques viz. Positron Emission Tomography (PET), structural Magnetic Resonance Imaging (MRI) and functional MRI (fMRI), etc. Out of these neuroimaging techniques, structural MRI has evolved as the best technique as it indicates the best soft tissue contrast and high spatial resolution which is important for AD detection. Currently, the focus of researchers is on predicting the conversion of Mild Cognitive Impairment (MCI) into AD. MCI represents the transition state between expected cognitive changes with normal aging and Alzheimer's disease. Not every MCI patient progresses into Alzheimer's disease. MCI can develop into stable MCI (sMCI, patients are called non-converters) or into progressive MCI (pMCI, patients are diagnosed as MCI converters). This paper discusses the prognosis of MCI to AD conversion and presents a review of structural MRI-based studies for AD detection. AD detection framework includes feature extraction, feature selection, and classification process. This paper reviews the studies for AD detection based on different feature extraction methods and machine learning algorithms for classification. The performance of various feature extraction methods has been compared and it has been observed that the wavelet transform-based feature extraction method would give promising results for AD classification. The present study indicates that researchers are successful in classifying AD from Normal Controls (NrmC) but, it still requires a lot of work to be done for MCI/ NrmC and MCI/AD, which would help in detecting AD at its early stage.
Collapse
Affiliation(s)
- Neha Garg
- Delhi Technological University, Department of Electronics and Communication, Delhi 110042, India.
| | - Mahipal Singh Choudhry
- Delhi Technological University, Department of Electronics and Communication, Delhi 110042, India.
| | - Rajesh M Bodade
- Military College of Telecommunication Engineering (MCTE), Mhow, Indore 453441, Madhya Pradesh, India.
| |
Collapse
|
|
20
|
Huang Y, Zeng Y, Bin G, Ding Q, Wu S, Tai DI, Tsui PH, Zhou Z. Evaluation of Hepatic Fibrosis Using Ultrasound Backscattered Radiofrequency Signals and One-Dimensional Convolutional Neural Networks. Diagnostics (Basel) 2022; 12:2833. [PMID: 36428892 PMCID: PMC9689172 DOI: 10.3390/diagnostics12112833] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/24/2022] [Revised: 11/09/2022] [Accepted: 11/14/2022] [Indexed: 11/18/2022] Open
Abstract
The early detection of hepatic fibrosis is of critical importance. Ultrasound backscattered radiofrequency signals from the liver contain abundant information about its microstructure. We proposed a method for characterizing human hepatic fibrosis using one-dimensional convolutional neural networks (CNNs) based on ultrasound backscattered signals. The proposed CNN model was composed of four one-dimensional convolutional layers, four one-dimensional max-pooling layers, and four fully connected layers. Ultrasound radiofrequency signals collected from 230 participants (F0: 23; F1: 46; F2: 51; F3: 49; F4: 61) with a 3-MHz transducer were analyzed. Liver regions of interest (ROIs) that contained most of the liver ultrasound backscattered signals were manually delineated using B-mode images reconstructed from the backscattered signals. ROI signals were normalized and augmented by using a sliding window technique. After data augmentation, the radiofrequency signal segments were divided into training sets, validation sets and test sets at a ratio of 80%:10%:10%. In the test sets, the proposed algorithm produced an area under the receive operating characteristic curve of 0.933 (accuracy: 91.30%; sensitivity: 92.00%; specificity: 90.48%), 0.997 (accuracy: 94.29%; sensitivity: 94.74%; specificity: 93.75%), 0.818 (accuracy: 75.00%; sensitivity: 69.23%; specificity: 81.82%), and 0.934 (accuracy: 91.67%; sensitivity: 88.89%; specificity: 94.44%) for diagnosis liver fibrosis stage ≥F1, ≥F2, ≥F3, and ≥F4, respectively. Experimental results indicated that the proposed deep learning algorithm based on ultrasound backscattered signals yields a satisfying performance when diagnosing hepatic fibrosis stages. The proposed method may be used as a new quantitative ultrasound approach to characterizing hepatic fibrosis.
Collapse
Affiliation(s)
- Yong Huang
- Department of Biomedical Engineering, Faculty of Environment and Life, Beijing University of Technology, Beijing 100124, China
| | - Yan Zeng
- Department of Biomedical Engineering, Faculty of Environment and Life, Beijing University of Technology, Beijing 100124, China
| | - Guangyu Bin
- Department of Biomedical Engineering, Faculty of Environment and Life, Beijing University of Technology, Beijing 100124, China
| | - Qiying Ding
- Department of Ultrasound, BJUT Hospital, Beijing University of Technology, Beijing 100124, China
| | - Shuicai Wu
- Department of Biomedical Engineering, Faculty of Environment and Life, Beijing University of Technology, Beijing 100124, China
| | - Dar-In Tai
- Department of Gastroenterology and Hepatology, Chang Gung Memorial Hospital at Linkou, Chang Gung University, Taoyuan 333423, Taiwan
| | - Po-Hsiang Tsui
- Department of Medical Imaging and Radiological Sciences, College of Medicine, Chang Gung University, Taoyuan 333323, Taiwan
- Institute for Radiological Research, Chang Gung University, Taoyuan 333323, Taiwan
- Division of Pediatric Gastroenterology, Department of Pediatrics, Chang Gung Memorial Hospital at Linkou, Taoyuan 333423, Taiwan
| | - Zhuhuang Zhou
- Department of Biomedical Engineering, Faculty of Environment and Life, Beijing University of Technology, Beijing 100124, China
| |
Collapse
|
|
21
|
Li H, Ma HY, Zhang L, Liu P, Zhang YX, Zhang XX, Li ZF, Xing PF, Zhang YW, Li Q, Yang PF, Liu JM. Early diagnosis of intracranial atherosclerotic large vascular occlusion: A prediction model based on DIRECT-MT data. Front Neurol 2022; 13:1026815. [PMID: 36408511 PMCID: PMC9670732 DOI: 10.3389/fneur.2022.1026815] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/24/2022] [Accepted: 09/28/2022] [Indexed: 08/09/2023] Open
Abstract
AIMS This study aimed to build a prediction model to early diagnose intracranial atherosclerosis (ICAS)-related large vascular occlusion (LVO) in acute ischemic stroke patients before digital subtractive angiography. METHODS Patients enrolled in the DIRECT-MT trial (NCT03469206) were included in our secondary analysis and distributed into ICAS-LVO and non-ICAS-LVO groups. We also retrieved demographic data, medical histories, clinical characteristics, and pre-operative imaging data. Hypothesis testing was used to compare data of the two groups, and univariate logistic regression was used to identify the predictors of ICAS-LVO primarily. Then, we used multivariate logistic regression to determine the independent predictors and formulate the prediction model. Model efficacy was estimated by the area under the receiver operating characteristic (ROC) curve (AUC) and diagnostic parameters generated from internal and external validations. RESULTS The subgroup analysis included 45 cases in the ICAS-LVO group and 611 cases in the non-ICAS-LVO group. Variates with p < 0.1 in the comparative analysis were used as inputs in the univariate logistic regression. Next, variates with p < 0.1 in the univariate logistic regression were used as inputs in the multivariate logistic regression. The multivariate logistic regression indicated that the atrial fibrillation history, hypertension and smoking, occlusion located at the proximal M1 and M2, hyperdense artery sign, and clot burden score were related to the diagnosis of ICAS-LVO. Then, we constructed a prediction model based on multivariate logistics regression. The sensitivity and specificity of the model were 84.09 and 74.54% in internal validation and 73.11 and 71.53% in external validation. CONCLUSION Our current prediction model based on clinical data of patients from the DIRECT-MT trial might be a promising tool for predicting ICAS-LVO.
Collapse
Affiliation(s)
- He Li
- Emergency Room, Naval Hospital of Eastern Theater, Zhoushan, China
- Neurovascular Center, Changhai Hospital, Naval Medical University, Shanghai, China
| | - Hong-Yu Ma
- Neurovascular Center, Changhai Hospital, Naval Medical University, Shanghai, China
| | - Lei Zhang
- Neurovascular Center, Changhai Hospital, Naval Medical University, Shanghai, China
| | - Pei Liu
- Neurovascular Center, Changhai Hospital, Naval Medical University, Shanghai, China
| | - Yong-Xin Zhang
- Neurovascular Center, Changhai Hospital, Naval Medical University, Shanghai, China
| | - Xiao-Xi Zhang
- Neurovascular Center, Changhai Hospital, Naval Medical University, Shanghai, China
| | - Zi-Fu Li
- Neurovascular Center, Changhai Hospital, Naval Medical University, Shanghai, China
| | - Peng-Fei Xing
- Neurovascular Center, Changhai Hospital, Naval Medical University, Shanghai, China
| | - Yong-Wei Zhang
- Neurovascular Center, Changhai Hospital, Naval Medical University, Shanghai, China
| | - Qiang Li
- Neurovascular Center, Changhai Hospital, Naval Medical University, Shanghai, China
| | - Peng-Fei Yang
- Neurovascular Center, Changhai Hospital, Naval Medical University, Shanghai, China
| | - Jian-Min Liu
- Neurovascular Center, Changhai Hospital, Naval Medical University, Shanghai, China
| |
Collapse
|
|
22
|
Son H, Lee S, Kim K, Koo KI, Hwang CH. Deep learning-based quantitative estimation of lymphedema-induced fibrosis using three-dimensional computed tomography images. Sci Rep 2022; 12:15371. [PMID: 36100619 PMCID: PMC9470678 DOI: 10.1038/s41598-022-19204-6] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/28/2022] [Accepted: 08/25/2022] [Indexed: 11/09/2022] Open
Abstract
In lymphedema, proinflammatory cytokine-mediated progressive cascades always occur, leading to macroscopic fibrosis. However, no methods are practically available for measuring lymphedema-induced fibrosis before its deterioration. Technically, CT can visualize fibrosis in superficial and deep locations. For standardized measurement, verification of deep learning (DL)-based recognition was performed. A cross-sectional, observational cohort trial was conducted. After narrowing window width of the absorptive values in CT images, SegNet-based semantic segmentation model of every pixel into 5 classes (air, skin, muscle/water, fat, and fibrosis) was trained (65%), validated (15%), and tested (20%). Then, 4 indices were formulated and compared with the standardized circumference difference ratio (SCDR) and bioelectrical impedance (BEI) results. In total, 2138 CT images of 27 chronic unilateral lymphedema patients were analyzed. Regarding fibrosis segmentation, the mean boundary F1 score and accuracy were 0.868 and 0.776, respectively. Among 19 subindices of the 4 indices, 73.7% were correlated with the BEI (partial correlation coefficient: 0.420–0.875), and 13.2% were correlated with the SCDR (0.406–0.460). The mean subindex of Index 2 \documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{mathrsfs}
\usepackage{upgreek}
\setlength{\oddsidemargin}{-69pt}
\begin{document}$$\left( {\frac{{P_{Fibrosis\, in\, Affected} - P_{Fibrosis\, in\, Unaffected} }}{{P_{Limb\, in\, Unaffected} }}} \right)$$\end{document}PFibrosisinAffected-PFibrosisinUnaffectedPLimbinUnaffected presented the highest correlation. DL has potential applications in CT image-based lymphedema-induced fibrosis recognition. The subtraction-type formula might be the most promising estimation method.
Collapse
|
|
23
|
De Houwer J, Cummins J. Forwarding the ACBS Task Force recommendations: The case for the functional-cognitive framework and out-of-sample prediction. JOURNAL OF CONTEXTUAL BEHAVIORAL SCIENCE 2022. [DOI: 10.1016/j.jcbs.2022.09.005] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/30/2022]
|
|
24
|
Nakajo M, Takeda A, Katsuki A, Jinguji M, Ohmura K, Tani A, Sato M, Yoshiura T. The efficacy of 18F-FDG-PET-based radiomic and deep-learning features using a machine-learning approach to predict the pathological risk subtypes of thymic epithelial tumors. Br J Radiol 2022; 95:20211050. [PMID: 35312337 PMCID: PMC10996420 DOI: 10.1259/bjr.20211050] [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: 09/11/2021] [Revised: 02/28/2022] [Accepted: 03/14/2022] [Indexed: 11/05/2022] Open
Abstract
OBJECTIVE To examine whether the machine-learning approach using 18-fludeoxyglucose positron emission tomography (18F-FDG-PET)-based radiomic and deep-learning features is useful for predicting the pathological risk subtypes of thymic epithelial tumors (TETs). METHODS This retrospective study included 79 TET [27 low-risk thymomas (types A, AB and B1), 31 high-risk thymomas (types B2 and B3) and 21 thymic carcinomas] patients who underwent pre-therapeutic 18F-FDG-PET/CT. High-risk TETs (high-risk thymomas and thymic carcinomas) were 52 patients. The 107 PET-based radiomic features, including SUV-related parameters [maximum SUV (SUVmax), metabolic tumor volume (MTV), and total lesion glycolysis (TLG)] and 1024 deep-learning features extracted from the convolutional neural network were used to predict the pathological risk subtypes of TETs using six different machine-learning algorithms. The area under the curves (AUCs) were calculated to compare the predictive performances. RESULTS SUV-related parameters yielded the following AUCs for predicting thymic carcinomas: SUVmax 0.713, MTV 0.442, and TLG 0.479 or high-risk TETs: SUVmax 0.673, MTV 0.533, and TLG 0.539. The best-performing algorithm was the logistic regression model for predicting thymic carcinomas (AUC 0.900, accuracy 81.0%), and the random forest (RF) model for high-risk TETs (AUC 0.744, accuracy 72.2%). The AUC was significantly higher in the logistic regression model than three SUV-related parameters for predicting thymic carcinomas, and in the RF model than MTV and TLG for predicting high-risk TETs (each; p < 0.05). CONCLUSION 18F-FDG-PET-based radiomic analysis using a machine-learning approach may be useful for predicting the pathological risk subtypes of TETs. ADVANCES IN KNOWLEDGE Machine-learning approach using 18F-FDG-PET-based radiomic features has the potential to predict the pathological risk subtypes of TETs.
Collapse
Affiliation(s)
- Masatoyo Nakajo
- Department of Radiology, Kagoshima University, Graduate School
of Medical and Dental Sciences,
Kagoshima, Japan
| | - Aya Takeda
- Department of General Thoracic Surgery, Kagoshima University,
Graduate School of Medical and Dental Sciences,
Kagoshima, Japan
| | - Akie Katsuki
- Research and Development Department, GE Healthcare
Japan, Tokyo,
Japan
| | - Megumi Jinguji
- Department of Radiology, Kagoshima University, Graduate School
of Medical and Dental Sciences,
Kagoshima, Japan
| | - Kazuyuki Ohmura
- Research and Development Department, GE Healthcare
Japan, Tokyo,
Japan
| | - Atsushi Tani
- Department of Radiology, Kagoshima University, Graduate School
of Medical and Dental Sciences,
Kagoshima, Japan
| | - Masami Sato
- Department of General Thoracic Surgery, Kagoshima University,
Graduate School of Medical and Dental Sciences,
Kagoshima, Japan
| | - Takashi Yoshiura
- Department of Radiology, Kagoshima University, Graduate School
of Medical and Dental Sciences,
Kagoshima, Japan
| |
Collapse
|
|
25
|
Boshier PR, Swaray A, Vadhwana B, O’Sullivan A, Low DE, Hanna GB, Peters CJ. Systematic review and validation of clinical models predicting survival after oesophagectomy for adenocarcinoma. Br J Surg 2022; 109:418-425. [PMID: 35233634 PMCID: PMC10364693 DOI: 10.1093/bjs/znac044] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/14/2021] [Accepted: 01/10/2022] [Indexed: 08/02/2023]
Abstract
BACKGROUND Oesophageal adenocarcinoma poses a significant global health burden, yet the staging used to predict survival has limited ability to stratify patients by outcome. This study aimed to identify published clinical models that predict survival in oesophageal adenocarcinoma and to evaluate them using an independent international multicentre dataset. METHODS A systematic literature search (title and abstract) using the Ovid Embase and MEDLINE databases (from 1947 to 11 July 2020) was performed. Inclusion criteria were studies that developed or validated a clinical prognostication model to predict either overall or disease-specific survival in patients with oesophageal adenocarcinoma undergoing surgical treatment with curative intent. Published models were validated using an independent dataset of 2450 patients who underwent oesophagectomy for oesophageal adenocarcinoma with curative intent. RESULTS Seventeen articles were eligible for inclusion in the study. Eleven models were suitable for testing in the independent validation dataset and nine of these were able to stratify patients successfully into groups with significantly different survival outcomes. Area under the receiver operating characteristic curves for individual survival prediction models ranged from 0.658 to 0.705, suggesting poor-to-fair accuracy. CONCLUSION This study highlights the need to concentrate on robust methodologies and improved, independent, validation, to increase the likelihood of clinical adoption of survival predictions models.
Collapse
Affiliation(s)
- Piers R Boshier
- Department of Surgery and Cancer, Imperial College London, London, UK
| | - Alison Swaray
- Department of Surgery and Cancer, Imperial College London, London, UK
| | - Bhamini Vadhwana
- Department of Surgery and Cancer, Imperial College London, London, UK
| | - Arun O’Sullivan
- Department of Surgery and Cancer, Imperial College London, London, UK
| | - Donald E Low
- Department of Thoracic Surgery, Virginia Mason Medical Centre, Seattle, Washington, USA
| | - George B Hanna
- Department of Surgery and Cancer, Imperial College London, London, UK
| | | |
Collapse
|
|
26
|
Nakajo M, Jinguji M, Tani A, Yano E, Hoo CK, Hirahara D, Togami S, Kobayashi H, Yoshiura T. Machine learning based evaluation of clinical and pretreatment 18F-FDG-PET/CT radiomic features to predict prognosis of cervical cancer patients. Abdom Radiol (NY) 2022; 47:838-847. [PMID: 34821963 DOI: 10.1007/s00261-021-03350-y] [Citation(s) in RCA: 17] [Impact Index Per Article: 5.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/25/2021] [Revised: 05/25/2021] [Accepted: 11/09/2021] [Indexed: 01/22/2023]
Abstract
PURPOSE To examine the usefulness of machine learning to predict prognosis in cervical cancer using clinical and radiomic features of 2-deoxy-2-[18F]fluoro-D-glucose (18F-FDG) positron emission tomography/computed tomography (CT) (18F-FDG-PET/CT). METHODS This retrospective study included 50 cervical cancer patients who underwent 18F-FDG-PET/CT before treatment. Four clinical (age, histology, stage, and treatment) and 41 18F-FDG-PET-based radiomic features were ranked and a subset of useful features for association with disease progression was selected based on decrease of the Gini impurity. Six machine learning algorithms (random forest, neural network, k-nearest neighbors, naive Bayes, logistic regression, and support vector machine) were compared using the areas under the receiver operating characteristic curve (AUC). Progression-free survival (PFS) was assessed using Cox regression analysis. RESULTS The five top predictors of disease progression were: stage, surface area, metabolic tumor volume, gray-level run length non-uniformity (GLRLM_RLNU), and gray-level non-uniformity for run (GLRLM_GLNU). The naive Bayes model was the best-performing classifier for predicting disease progression (AUC = 0.872, accuracy = 0.780, F1 score = 0.781, precision = 0.788, and recall = 0.780). In the naive Bayes model, 5-year PFS was significantly higher in predicted non-progression than predicted progression (80.1% vs. 9.1%, p < 0.001) and was only the independent factor for PFS in multivariate analysis (HR, 6.89; 95% CI, 1.92-24.69; p = 0.003). CONCLUSION A machine learning approach based on clinical and pretreatment 18F-FDG PET-based radiomic features may be useful for predicting tumor progression in cervical cancer patients.
Collapse
Affiliation(s)
- Masatoyo Nakajo
- Department of Radiology, Kagoshima University, Graduate School of Medical and Dental Sciences, 8-35-1 Sakuragaoka, Kagoshima, 890-8544, Japan.
| | - Megumi Jinguji
- Department of Radiology, Kagoshima University, Graduate School of Medical and Dental Sciences, 8-35-1 Sakuragaoka, Kagoshima, 890-8544, Japan
| | - Atsushi Tani
- Department of Radiology, Kagoshima University, Graduate School of Medical and Dental Sciences, 8-35-1 Sakuragaoka, Kagoshima, 890-8544, Japan
| | - Erina Yano
- Department of Radiology, Kagoshima University, Graduate School of Medical and Dental Sciences, 8-35-1 Sakuragaoka, Kagoshima, 890-8544, Japan
| | - Chin Khang Hoo
- Department of Radiology, Kagoshima University, Graduate School of Medical and Dental Sciences, 8-35-1 Sakuragaoka, Kagoshima, 890-8544, Japan
| | - Daisuke Hirahara
- Department of Management Planning Division, Harada Academy, 2-54-4 Higashitaniyama, Kagoshima, 890-0113, Japan
| | - Shinichi Togami
- Department of Obstetrics and Gynecology, Kagoshima University, Graduate School of Medical and Dental Sciences, 8-35-1 Sakuragaoka, Kagoshima, 890-8544, Japan
| | - Hiroaki Kobayashi
- Department of Obstetrics and Gynecology, Kagoshima University, Graduate School of Medical and Dental Sciences, 8-35-1 Sakuragaoka, Kagoshima, 890-8544, Japan
| | - Takashi Yoshiura
- Department of Radiology, Kagoshima University, Graduate School of Medical and Dental Sciences, 8-35-1 Sakuragaoka, Kagoshima, 890-8544, Japan
| |
Collapse
|
|
27
|
Improving the Accuracy of Predictive Models for Outcomes of Antidepressants by Using an Ontological Adjustment Approach. APPLIED SCIENCES-BASEL 2022. [DOI: 10.3390/app12031479] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/10/2022]
Abstract
For patients with rare comorbidities, there are insufficient observations to accurately estimate the effectiveness of treatment. At the same time, all diagnosis, including rare diagnosis, are part of the International Classification of Disease (ICD). Grouping ICD into broader concepts (i.e., ontology adjustment) can not only increase accuracy of estimating antidepressant effectiveness for patients with rare conditions but also prevent overfitting in big data analysis. In this study, 3,678,082 depressed patients treated with antidepressants were obtained from OptumLabs® Data Warehouse (OLDW). For rare diagnoses, adjustments were made by using the likelihood ratio of the immediate broader concept in the ICD hierarchies. The accuracy of models in training (90%) and test (10%) sets was examined using the area under the receiver operating curves (AROC). The gap in training and test AROC shows how much random noise was modeled. If the gap is large, then the parameters of the model, including the reported effectiveness of the antidepressant for patients with rare conditions, are suspect. There was, on average, a 9.0% reduction in the AROC gap after using the ontological adjustment. Therefore, ontology adjustment can reduce model overfitting, leading to better parameter estimates from the training set.
Collapse
|
|
28
|
Huang Y, Jiang S, Li W, Fan Y, Leng Y, Gao C. Establishment and Effectiveness Evaluation of a Scoring System-RAAS (RDW, AGE, APACHE II, SOFA) for Sepsis by a Retrospective Analysis. J Inflamm Res 2022; 15:465-474. [PMID: 35082513 PMCID: PMC8786358 DOI: 10.2147/jir.s348490] [Citation(s) in RCA: 13] [Impact Index Per Article: 4.3] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/09/2021] [Accepted: 12/25/2021] [Indexed: 01/19/2023] Open
Abstract
Background Methods Results Conclusion
Collapse
Affiliation(s)
- Yingying Huang
- Emergency Department, Xinhua Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai, People’s Republic of China
| | - Shaowei Jiang
- Emergency Department, Xinhua Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai, People’s Republic of China
| | - Wenjie Li
- Emergency Department, Xinhua Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai, People’s Republic of China
| | - Yiwen Fan
- Department of Pathology Medicine Biology, The University Medical Center Groningen, Groningen, the Netherlands
| | - Yuxin Leng
- Critical Care Medicine Department, Peking University Third Hospital, Beijing, People’s Republic of China
| | - Chengjin Gao
- Emergency Department, Xinhua Hospital Affiliated to Shanghai Jiao Tong University School of Medicine, Shanghai, People’s Republic of China
- Correspondence: Chengjin Gao; Yuxin Leng Email ;
| |
Collapse
|
|
29
|
Wu Z, Chen Q, Djaladat H, Minervini A, Uzzo RG, Sundaram CP, Rha KH, Gonzalgo ML, Mehrazin R, Mazzone E, Marcus J, Danno A, Porter J, Asghar A, Ghali F, Guruli G, Douglawi A, Cacciamani G, Ghoreifi A, Simone G, Margulis V, Ferro M, Tellini R, Mari A, Srivastava A, Steward J, Al-Qathani A, Al-Mujalhem A, Bhattu AS, Mottrie A, Abdollah F, Eun DD, Derweesh I, Veccia A, Autorino R, Wang L. A Preoperative Nomogram to Predict Renal Function Insufficiency for Cisplatin-based Adjuvant Chemotherapy Following Minimally Invasive Radical Nephroureterectomy (ROBUUST Collaborative Group). Eur Urol Focus 2022; 8:173-181. [PMID: 33549537 DOI: 10.1016/j.euf.2021.01.014] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/26/2020] [Revised: 12/16/2020] [Accepted: 01/13/2021] [Indexed: 01/03/2023]
Abstract
BACKGROUND Postoperative renal function impairment represents a main limitation for delivering adjuvant chemotherapy after radical nephroureterectomy (RNU). OBJECTIVE To create a model predicting renal function decline after minimally invasive RNU. DESIGN, SETTING, AND PARTICIPANTS A total of 490 patients with nonmetastatic UTUC who underwent minimally invasive RNU were identified from a collaborative database including 17 institutions worldwide (February 2006 to March 2020). Renal function insufficiency for cisplatin-based regimen was defined as estimated glomerular filtration rate (eGFR) <50 ml/min/1.73 m2 at 3 mo after RNU. Patients with baseline eGFR >50 ml/min/1.73 m2 (n = 361) were geographically divided into a training set (n = 226) and an independent external validation set (n = 135) for further analysis. OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS Using transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD) guidelines, a nomogram to predict postoperative eGFR <50 ml/min/1.73 m2 was built based on the coefficients of the least absolute shrinkage and selection operation (LASSO) logistic regression. The discrimination, calibration, and clinical use of the nomogram were investigated. RESULTS AND LIMITATIONS The model that incorporated age, body mass index, preoperative eGFR, and hydroureteronephrosis was developed with an area under the curve of 0.771, which was confirmed to be 0.773 in the external validation set. The calibration curve demonstrated good agreement. Besides, the model was converted into a risk score with a cutoff value of 0.583, and the difference between the low- and high-risk groups both in overall death risk (hazard ratio [HR]: 4.59, p < 0.001) and cancer-specific death risk (HR: 5.19, p < 0.001) was statistically significant. The limitation mainly lies in its retrospective design. CONCLUSIONS A nomogram incorporating immediately available clinical variables can accurately predict renal insufficiency for cisplatin-based adjuvant chemotherapy after minimally invasive RNU and may serve as a tool facilitating patient selection. PATIENT SUMMARY We have developed a model for the prediction of renal function loss after radical nephroureterectomy to facilitate patient selection for perioperative chemotherapy.
Collapse
Affiliation(s)
- Zhenjie Wu
- Department of Urology, Changzheng Hospital, Naval Medical University, Shanghai, China
| | - Qi Chen
- Department of Health Statistics, Naval Medical University, Shanghai, China
| | - Hooman Djaladat
- Institute of Urology & Catherine and Joseph Aresty Department of Urology, Keck School of Medicine, University of Southern California, Los Angeles, CA, USA
| | - Andrea Minervini
- Department of Experimental and Clinical Medicine, University of Florence - Unit of Oncologic Minimally-Invasive Urology and Andrology, Careggi Hospital, Florence, Italy
| | - Robert G Uzzo
- Division of Urologic Oncology, Department of Surgical Oncology, Fox Chase Cancer Center, Philadelphia, PA, USA
| | | | - Koon H Rha
- Department of Urology, Urological Science Institute, Yonsei University College of Medicine, Seoul, Republic of Korea
| | - Mark L Gonzalgo
- Department of Urology, University of Miami Miller School of Medicine, Miami, FL, USA
| | - Reza Mehrazin
- Icahn School of Medicine at Mount Sinai, Department of Urology, New York, NY, USA
| | - Elio Mazzone
- OLV Hospital, Aalst, Belgium;ORSI Academy, Melle, Belgium
| | - Jamil Marcus
- Vattikuti Urology Institute, Henry Ford Hospital, Detroit, MI, USA
| | - Alyssa Danno
- Vattikuti Urology Institute, Henry Ford Hospital, Detroit, MI, USA
| | | | - Aeen Asghar
- Department of Urology, Temple University, Philadelphia, PA, USA
| | - Fady Ghali
- Department of Urology, UCSD, San Diego, CA, USA
| | | | - Antoin Douglawi
- Institute of Urology & Catherine and Joseph Aresty Department of Urology, Keck School of Medicine, University of Southern California, Los Angeles, CA, USA
| | - Giovanni Cacciamani
- Institute of Urology & Catherine and Joseph Aresty Department of Urology, Keck School of Medicine, University of Southern California, Los Angeles, CA, USA
| | - Alireza Ghoreifi
- Institute of Urology & Catherine and Joseph Aresty Department of Urology, Keck School of Medicine, University of Southern California, Los Angeles, CA, USA
| | - Giuseppe Simone
- Department of Urology, Regina Elena National Cancer Institute, Rome, Italy
| | - Vitaly Margulis
- Department of Urology, University of Texas Southwestern Medical Center, Dallas, TX, USA
| | - Matteo Ferro
- Division of Urology - European Institute of Oncology, IRCCS
| | - Riccardo Tellini
- Department of Experimental and Clinical Medicine, University of Florence - Unit of Oncologic Minimally-Invasive Urology and Andrology, Careggi Hospital, Florence, Italy
| | - Andrea Mari
- Department of Experimental and Clinical Medicine, University of Florence - Unit of Oncologic Minimally-Invasive Urology and Andrology, Careggi Hospital, Florence, Italy
| | - Abhishek Srivastava
- Division of Urologic Oncology, Department of Surgical Oncology, Fox Chase Cancer Center, Philadelphia, PA, USA
| | - James Steward
- Indiana University School of Medicine, Indianapolis, IN, USA
| | - Ali Al-Qathani
- Department of Urology, Urological Science Institute, Yonsei University College of Medicine, Seoul, Republic of Korea
| | - Ahmad Al-Mujalhem
- Department of Urology, Urological Science Institute, Yonsei University College of Medicine, Seoul, Republic of Korea
| | - Amit Satish Bhattu
- Department of Urology, University of Miami Miller School of Medicine, Miami, FL, USA
| | | | - Firas Abdollah
- Vattikuti Urology Institute, Henry Ford Hospital, Detroit, MI, USA
| | - Daniel D Eun
- Department of Urology, Temple University, Philadelphia, PA, USA
| | | | | | | | - Linhui Wang
- Department of Urology, Changzheng Hospital, Naval Medical University, Shanghai, China.
| |
Collapse
|
|
30
|
Zheng YM, Chen J, Xu Q, Zhao WH, Wang XF, Yuan MG, Liu ZJ, Wu ZJ, Dong C. Development and validation of an MRI-based radiomics nomogram for distinguishing Warthin's tumour from pleomorphic adenomas of the parotid gland. Dentomaxillofac Radiol 2021; 50:20210023. [PMID: 33950705 PMCID: PMC8474129 DOI: 10.1259/dmfr.20210023] [Citation(s) in RCA: 14] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/14/2021] [Revised: 03/20/2021] [Accepted: 04/14/2021] [Indexed: 02/07/2023] Open
Abstract
OBJECTIVE： Preoperative differentiation between parotid Warthin's tumor (WT) and pleomorphic adenoma (PMA) is crucial for treatment decisions. The purpose of this study was to establish and validate an MRI-based radiomics nomogram for preoperative differentiation between WT and PMA. METHODS AND MATERIALS A total of 127 patients with histological diagnosis of WT or PMA from two clinical centres were enrolled in training set (n = 75; WT = 34, PMA = 41) and external test set (n = 52; WT = 24, PMA = 28). Radiomics features were extracted from axial T1WI and fs-T2WI images. A radiomics signature was constructed, and a radiomics score (Rad-score) was calculated. A clinical factors model was built using demographics and MRI findings. A radiomics nomogram combining the independent clinical factors and Rad-score was constructed. The receiver operating characteristic analysis was used to assess the performance levels of the nomogram, radiomics signature and clinical model. RESULTS The radiomics nomogram incorporating the age and radiomics signature showed favourable predictive value for differentiating parotid WT from PMA, with AUCs of 0.953 and 0.918 for the training set and test set, respectively. CONCLUSIONS The MRI-based radiomics nomogram had good performance in distinguishing parotid WT from PMA, which could optimize clinical decision-making.
Collapse
Affiliation(s)
- Ying-mei Zheng
- Health Management Center, The Affiliated Hospital of Qingdao University, Qingdao, China
| | - Jiao Chen
- Department of Radiology, Yantai Yuhuangding Hospital, Yantai, China
| | - Qi Xu
- Department of Radiology, The Affiliated Hospital of Qingdao University, Qingdao, China
| | - Wen-hui Zhao
- Health Management Center, The Affiliated Hospital of Qingdao University, Qingdao, China
| | - Xin-feng Wang
- Health Management Center, The Affiliated Hospital of Qingdao University, Qingdao, China
| | - Ming-gang Yuan
- Department of Nuclear Medicine, Affiliated Qingdao Central Hospital, Qingdao Universtity, Qingdao, China
| | - Zong-jing Liu
- Department of Pediatric Hematology, The Affiliated Hospital of Qingdao University, Qingdao, China
| | - Zeng-jie Wu
- Department of Radiology, The Affiliated Hospital of Qingdao University, Qingdao, China
| | - Cheng Dong
- Department of Radiology, The Affiliated Hospital of Qingdao University, Qingdao, China
| |
Collapse
|
|
31
|
Chong Y, Wu Y, Liu J, Han C, Gong L, Liu X, Liang N, Li S. Clinicopathological models for predicting lymph node metastasis in patients with early-stage lung adenocarcinoma: the application of machine learning algorithms. J Thorac Dis 2021; 13:4033-4042. [PMID: 34422333 PMCID: PMC8339794 DOI: 10.21037/jtd-21-98] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/14/2021] [Accepted: 05/21/2021] [Indexed: 12/25/2022]
Abstract
Background Lymph node metastasis (LNM) status can be a critical decisive factor for clinical management of lung cancer. Accurately evaluating the risk of LNM during or after the surgery can be helpful for making clinical decisions. This study aims to incorporate clinicopathological characteristics to develop reliable machine learning (ML)-based models for predicting LNM in patients with early-stage lung adenocarcinoma. Methods A total of 709 lung adenocarcinoma patients with tumor size ≤2 cm were enrolled for analysis and modeling by multiple ML algorithms. The receiver operating characteristic (ROC) curve and decision curve were used for evaluating model’s predictive performance and clinical usefulness. Feature selection based on potential models was performed to identify most-contributed predictive factors. Results LNM occurred in 11.3% (80/709) of patients with lung adenocarcinoma. Most models reached high areas under the ROC curve (AUCs) >0.9. In the decision curve, all models performed better than the treat-all and treat-none lines. The random forest classifier (RFC) model, with a minimal number of five variables introduced (including carcinoembryonic antigen, solid component, micropapillary component, lymphovascular invasion and pleural invasion), was identified as the optimal model for predicting LNM, because of its excellent performance in both ROC and decision curves. Conclusions The cost-efficient application of RFC model could precisely predict LNM during or after the operation of early-stage adenocarcinomas (sensitivity: 87.5%; specificity: 82.2%). Incorporating clinicopathological characteristics, it is feasible to predict LNM intraoperatively or postoperatively by ML algorithms.
Collapse
Affiliation(s)
- Yuming Chong
- Peking Union Medical College, Chinese Academy of Medical Sciences, Beijing, China
| | - Yijun Wu
- Department of Radiation Oncology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, China
| | - Jianghao Liu
- Peking Union Medical College, Chinese Academy of Medical Sciences, Beijing, China
| | - Chang Han
- Peking Union Medical College, Chinese Academy of Medical Sciences, Beijing, China
| | - Liang Gong
- Peking Union Medical College, Chinese Academy of Medical Sciences, Beijing, China
| | - Xinyu Liu
- Peking Union Medical College, Chinese Academy of Medical Sciences, Beijing, China
| | - Naixin Liang
- Department of Thoracic Surgery, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, China
| | - Shanqing Li
- Department of Thoracic Surgery, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, China
| |
Collapse
|
|
32
|
Nakajo M, Jinguji M, Tani A, Hirahara D, Nagano H, Takumi K, Yoshiura T. Application of a machine learning approach to characterization of liver function using 99mTc-GSA SPECT/CT. Abdom Radiol (NY) 2021; 46:3184-3192. [PMID: 33675380 DOI: 10.1007/s00261-021-02985-1] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/15/2020] [Revised: 01/21/2021] [Accepted: 02/09/2021] [Indexed: 12/17/2022]
Abstract
PURPOSE To assess the utility of a machine-learning approach for predicting liver function based on technetium-99 m-galactosyl serum albumin (99mTc-GSA) single photon emission computed tomography (SPECT)/CT. METHODS One hundred twenty-eight patients underwent a 99mTc-GSA SPECT/CT-based liver function evaluation. All were classified into the low liver-damage or high liver-damage group. Four clinical (age, sex, background liver disease and histological type) and 8 quantitative 99mTc-GSA SPECT/CT features (receptor index [LHL15], clearance index [HH15], liver-SUVmax, liver-SUVmean, heart-SUVmax, metabolic volume of liver [MVL], total lesion GSA [TL-GSA, liver-SUVmean × MVL] and SUVmax ratio [liver-SUVmax/heart-SUVmax]) were obtained. To predict high liver damage, a machine learning classification with features selection based on Gini impurity and principal component analysis (PCA) were performed using a support vector machine and a random forest (RF) with a five-fold cross-validation scheme. To overcome imbalanced data, stratified sampling was used. The ability to predict high liver damage was evaluated using a receiver operating characteristic (ROC) curve analysis. RESULTS Four indices (LHL15, HH15, heart SUVmax and SUVmax ratio) yielded high areas under the ROC curves (AUCs) for predicting high liver damage (range: 0.89-0.93). In a machine learning classification, the RF with selected features (heart SUVmax, SUVmax ratio, LHL15, HH15, and background liver disease) and PCA model yielded the best performance for predicting high liver damage (AUC = 0.956, sensitivity = 96.3%, specificity = 90.0%, accuracy = 91.4%). CONCLUSION A machine-learning approach based on clinical and quantitative 99mTc-GSA SPECT/CT parameters might be useful for predicting liver function.
Collapse
|
|
33
|
Cao SE, Zhang LQ, Kuang SC, Shi WQ, Hu B, Xie SD, Chen YN, Liu H, Chen SM, Jiang T, Ye M, Zhang HX, Wang J. Multiphase convolutional dense network for the classification of focal liver lesions on dynamic contrast-enhanced computed tomography. World J Gastroenterol 2020; 26:3660-3672. [PMID: 32742134 PMCID: PMC7366064 DOI: 10.3748/wjg.v26.i25.3660] [Citation(s) in RCA: 30] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 03/17/2020] [Revised: 05/08/2020] [Accepted: 06/03/2020] [Indexed: 02/06/2023] Open
Abstract
BACKGROUND The accurate classification of focal liver lesions (FLLs) is essential to properly guide treatment options and predict prognosis. Dynamic contrast-enhanced computed tomography (DCE-CT) is still the cornerstone in the exact classification of FLLs due to its noninvasive nature, high scanning speed, and high-density resolution. Since their recent development, convolutional neural network-based deep learning techniques has been recognized to have high potential for image recognition tasks.
AIM To develop and evaluate an automated multiphase convolutional dense network (MP-CDN) to classify FLLs on multiphase CT.
METHODS A total of 517 FLLs scanned on a 320-detector CT scanner using a four-phase DCE-CT imaging protocol (including precontrast phase, arterial phase, portal venous phase, and delayed phase) from 2012 to 2017 were retrospectively enrolled. FLLs were classified into four categories: Category A, hepatocellular carcinoma (HCC); category B, liver metastases; category C, benign non-inflammatory FLLs including hemangiomas, focal nodular hyperplasias and adenomas; and category D, hepatic abscesses. Each category was split into a training set and test set in an approximate 8:2 ratio. An MP-CDN classifier with a sequential input of the four-phase CT images was developed to automatically classify FLLs. The classification performance of the model was evaluated on the test set; the accuracy and specificity were calculated from the confusion matrix, and the area under the receiver operating characteristic curve (AUC) was calculated from the SoftMax probability outputted from the last layer of the MP-CDN.
RESULTS A total of 410 FLLs were used for training and 107 FLLs were used for testing. The mean classification accuracy of the test set was 81.3% (87/107). The accuracy/specificity of distinguishing each category from the others were 0.916/0.964, 0.925/0.905, 0.860/0.918, and 0.925/0.963 for HCC, metastases, benign non-inflammatory FLLs, and abscesses on the test set, respectively. The AUC (95% confidence interval) for differentiating each category from the others was 0.92 (0.837-0.992), 0.99 (0.967-1.00), 0.88 (0.795-0.955) and 0.96 (0.914-0.996) for HCC, metastases, benign non-inflammatory FLLs, and abscesses on the test set, respectively.
CONCLUSION MP-CDN accurately classified FLLs detected on four-phase CT as HCC, metastases, benign non-inflammatory FLLs and hepatic abscesses and may assist radiologists in identifying the different types of FLLs.
Collapse
Affiliation(s)
- Su-E Cao
- Department of Radiology, The Third Affiliated Hospital, Sun Yat-Sen University, Guangzhou 510630, Guangdong Province, China
| | - Lin-Qi Zhang
- Department of Radiology, The Third Affiliated Hospital, Sun Yat-Sen University, Guangzhou 510630, Guangdong Province, China
| | - Si-Chi Kuang
- Department of Radiology, The Third Affiliated Hospital, Sun Yat-Sen University, Guangzhou 510630, Guangdong Province, China
| | - Wen-Qi Shi
- Department of Radiology, The Third Affiliated Hospital, Sun Yat-Sen University, Guangzhou 510630, Guangdong Province, China
| | - Bing Hu
- Department of Radiology, The Third Affiliated Hospital, Sun Yat-Sen University, Guangzhou 510630, Guangdong Province, China
| | - Si-Dong Xie
- Department of Radiology, The Third Affiliated Hospital, Sun Yat-Sen University, Guangzhou 510630, Guangdong Province, China
| | - Yi-Nan Chen
- Department of Scientific and Technological Research, 12 Sigma Technologies, Beijing 100102, China
| | - Hui Liu
- Department of Scientific and Technological Research, 12 Sigma Technologies, Beijing 100102, China
| | - Si-Min Chen
- Department of Radiology, The Third Affiliated Hospital, Sun Yat-Sen University, Guangzhou 510630, Guangdong Province, China
| | - Ting Jiang
- Department of Radiology, The Third Affiliated Hospital, Sun Yat-Sen University, Guangzhou 510630, Guangdong Province, China
| | - Meng Ye
- Department of Scientific and Technological Research, 12 Sigma Technologies, Beijing 100102, China
| | - Han-Xi Zhang
- Department of Radiology, The Third Affiliated Hospital, Sun Yat-Sen University, Guangzhou 510630, Guangdong Province, China
| | - Jin Wang
- Department of Radiology, The Third Affiliated Hospital, Sun Yat-Sen University, Guangzhou 510630, Guangdong Province, China
| |
Collapse
|
|
34
|
Wu Y, Liu J, Han C, Liu X, Chong Y, Wang Z, Gong L, Zhang J, Gao X, Guo C, Liang N, Li S. Preoperative Prediction of Lymph Node Metastasis in Patients With Early-T-Stage Non-small Cell Lung Cancer by Machine Learning Algorithms. Front Oncol 2020; 10:743. [PMID: 32477952 PMCID: PMC7237747 DOI: 10.3389/fonc.2020.00743] [Citation(s) in RCA: 24] [Impact Index Per Article: 4.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/27/2019] [Accepted: 04/20/2020] [Indexed: 12/13/2022] Open
Abstract
Background: Lymph node metastasis (LNM) is difficult to precisely predict before surgery in patients with early-T-stage non-small cell lung cancer (NSCLC). This study aimed to develop machine learning (ML)-based predictive models for LNM. Methods: Clinical characteristics and imaging features were retrospectively collected from 1,102 NSCLC ≤ 2 cm patients. A total of 23 variables were included to develop predictive models for LNM by multiple ML algorithms. The models were evaluated by the receiver operating characteristic (ROC) curve for predictive performance and decision curve analysis (DCA) for clinical values. A feature selection approach was used to identify optimal predictive factors. Results: The areas under the ROC curve (AUCs) of the 8 models ranged from 0.784 to 0.899. Some ML-based models performed better than models using conventional statistical methods in both ROC curves and decision curves. The random forest classifier (RFC) model with 9 variables introduced was identified as the best predictive model. The feature selection indicated the top five predictors were tumor size, imaging density, carcinoembryonic antigen (CEA), maximal standardized uptake value (SUVmax), and age. Conclusions: By incorporating clinical characteristics and radiographical features, it is feasible to develop ML-based models for the preoperative prediction of LNM in early-T-stage NSCLC, and the RFC model performed best.
Collapse
Affiliation(s)
- Yijun Wu
- Department of Thoracic Surgery, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China.,Peking Union Medical College, Eight-year MD Program, Chinese Academy of Medical Sciences, Beijing, China
| | - Jianghao Liu
- Department of Thoracic Surgery, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China.,Peking Union Medical College, Eight-year MD Program, Chinese Academy of Medical Sciences, Beijing, China
| | - Chang Han
- Department of Thoracic Surgery, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China.,Peking Union Medical College, Eight-year MD Program, Chinese Academy of Medical Sciences, Beijing, China
| | - Xinyu Liu
- Peking Union Medical College, Eight-year MD Program, Chinese Academy of Medical Sciences, Beijing, China.,Department of Radiology, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China
| | - Yuming Chong
- Department of Thoracic Surgery, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China.,Peking Union Medical College, Eight-year MD Program, Chinese Academy of Medical Sciences, Beijing, China
| | - Zhile Wang
- Department of Thoracic Surgery, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China.,Peking Union Medical College, Eight-year MD Program, Chinese Academy of Medical Sciences, Beijing, China
| | - Liang Gong
- Department of Thoracic Surgery, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China.,Peking Union Medical College, Eight-year MD Program, Chinese Academy of Medical Sciences, Beijing, China
| | - Jiaqi Zhang
- Department of Thoracic Surgery, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China
| | - Xuehan Gao
- Department of Thoracic Surgery, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China
| | - Chao Guo
- Department of Thoracic Surgery, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China
| | - Naixin Liang
- Department of Thoracic Surgery, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China
| | - Shanqing Li
- Department of Thoracic Surgery, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China
| |
Collapse
|
|
35
|
Wu Y, Rao K, Liu J, Han C, Gong L, Chong Y, Liu Z, Xu X. Machine Learning Algorithms for the Prediction of Central Lymph Node Metastasis in Patients With Papillary Thyroid Cancer. Front Endocrinol (Lausanne) 2020; 11:577537. [PMID: 33193092 PMCID: PMC7609926 DOI: 10.3389/fendo.2020.577537] [Citation(s) in RCA: 45] [Impact Index Per Article: 9.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 06/29/2020] [Accepted: 09/25/2020] [Indexed: 12/18/2022] Open
Abstract
BACKGROUND Central lymph node metastasis (CLNM) occurs frequently in patients with papillary thyroid cancer (PTC), but performing prophylactic central lymph node dissection is still controversial. There are no reliable models for predicting CLNM. This study aimed to develop predictive models for CLNM by machine learning (ML) algorithms. METHODS Patients with PTC who underwent initial thyroid resection at our hospital between January 2018 and December 2019 were enrolled. A total of 22 variables, including clinical characteristics and ultrasonography (US) features, were used for conventional univariate and multivariate analysis and to construct ML-based models. A 5-fold cross validation strategy was used for validation and a feature selection approach was applied to identify risk factors. RESULTS The areas under the receiver operating characteristic curve (AUC) of 7 models ranged from 0.680 to 0.731. All models performed significantly better than US (AUC=0.623) in predicting CLNM (P<0.05). In decision curve, most of the models also performed better than US. The gradient boosting decision tree model with 7 variables was identified as the best model because of its best performance in both ROC (AUC=0.731) and decision curves. Based on multivariate analysis and feature selection, young age, male sex, low serum thyroid peroxidase antibody and US features such as suspected lymph nodes, microcalcification and tumor size > 1.1 cm were the most contributing predictors for CLNM. CONCLUSIONS It is feasible to develop predictive models of CLNM in PTC patients by incorporating clinical characteristics and US features. The ML algorithm may be a useful tool for the prediction of lymph node metastasis in thyroid cancer.
Collapse
Affiliation(s)
- Yijun Wu
- Department of General Surgery, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China
- Peking Union Medical College, Chinese Academy of Medical Sciences, Beijing, China
| | - Ke Rao
- Department of General Surgery, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China
- Peking Union Medical College, Chinese Academy of Medical Sciences, Beijing, China
| | - Jianghao Liu
- Peking Union Medical College, Chinese Academy of Medical Sciences, Beijing, China
| | - Chang Han
- Peking Union Medical College, Chinese Academy of Medical Sciences, Beijing, China
| | - Liang Gong
- Peking Union Medical College, Chinese Academy of Medical Sciences, Beijing, China
| | - Yuming Chong
- Peking Union Medical College, Chinese Academy of Medical Sciences, Beijing, China
| | - Ziwen Liu
- Department of General Surgery, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China
- *Correspondence: Xiequn Xu, ; Ziwen Liu,
| | - Xiequn Xu
- Department of General Surgery, Peking Union Medical College Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing, China
- *Correspondence: Xiequn Xu, ; Ziwen Liu,
| |
Collapse
|
|
36
|
Wang Y, Xiong Y, Wang X. Re: Zhengzheng Xu, Guangzhe Ge, Bao Guan, et al. Noninvasive Detection and Localization of Genitourinary Cancers Using Urinary Sediment DNA Methylomes and Copy Number Profiles. Eur Urol 2020;77:288-90. Eur Urol 2019; 77:e90. [PMID: 31892481 DOI: 10.1016/j.eururo.2019.12.015] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/19/2019] [Accepted: 12/17/2019] [Indexed: 11/27/2022]
Affiliation(s)
- Yejinpeng Wang
- Department of Urology, Zhongnan Hospital of Wuhan University, Wuhan, China
| | - Yaoyi Xiong
- Department of Urology, Zhongnan Hospital of Wuhan University, Wuhan, China; Department of Biological Repositories, Zhongnan Hospital of Wuhan University, Wuhan, China
| | - Xinghuan Wang
- Department of Urology, Zhongnan Hospital of Wuhan University, Wuhan, China.
| |
Collapse
|
|
37
|
|
|
38
|
Huang K, Jiang H, Zhang XY. Field Support Vector Machines. IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE 2017. [DOI: 10.1109/tetci.2017.2751062] [Citation(s) in RCA: 15] [Impact Index Per Article: 1.9] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/09/2022]
|