1
|
Garrett JW, Pickhardt PJ, Summers RM. Methodology for a fully automated pipeline of AI-based body composition tools for abdominal CT. Abdom Radiol (NY) 2025:10.1007/s00261-025-04951-7. [PMID: 40293521 DOI: 10.1007/s00261-025-04951-7] [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: 12/30/2024] [Revised: 04/04/2025] [Accepted: 04/09/2025] [Indexed: 04/30/2025]
Abstract
Accurate, reproducible body composition analysis from abdominal computed tomography (CT) images is critical for both clinical research and patient care. We present a fully automated, artificial intelligence (AI)-based pipeline that streamlines the entire process-from data normalization and anatomical landmarking to automated tissue segmentation and quantitative biomarker extraction. Our methodology ensures standardized inputs and robust segmentation models to compute volumetric, density, and cross-sectional area metrics for a range of organs and tissues. Additionally, we capture selected DICOM header fields to enable downstream analysis of scan parameters and facilitate correction for acquisition-related variability. By emphasizing portability and compatibility across different scanner types, image protocols, and computational environments, we ensure broad applicability of our framework. This toolkit is the basis for the Opportunistic Screening Consortium in Abdominal Radiology (OSCAR) and has been shown to be robust and versatile, critical for large multi-center studies.
Collapse
Affiliation(s)
- John W Garrett
- Department of Radiology, University of Wisconsin School of Medicine & Public Health, Madison, WI, USA.
- Department of Medical Physics, University of Wisconsin School of Medicine & Public Health, Madison, WI, USA.
- Department of Biostatistics and Medical Informatics, University of Wisconsin School of Medicine & Public Health, Madison, WI, USA.
| | - Perry J Pickhardt
- Department of Radiology, University of Wisconsin School of Medicine & Public Health, Madison, WI, USA
- Department of Medical Physics, University of Wisconsin School of Medicine & Public Health, Madison, WI, USA
| | - Ronald M Summers
- Imaging Biomarkers and Computer-Aided Diagnosis Laboratory, Department of Radiology and Imaging Sciences, National Institutes of Health Clinical Center, Bethesda, MD, USA
| |
Collapse
|
2
|
Tan Y, Li PP, Liu H, Zhu JY, Wu QS. Hepatic Arterial Infusion Chemotherapy for Hepatocellular Carcinoma: A Three-Dimensional Visualization Perspective. J Hepatocell Carcinoma 2025; 12:837-840. [PMID: 40322279 PMCID: PMC12047304 DOI: 10.2147/jhc.s513695] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/22/2024] [Accepted: 04/05/2025] [Indexed: 05/08/2025] Open
Abstract
In Asia, hepatic arterial infusion chemotherapy is an alternative therapeutic option for hepatocellular carcinoma (HCC). However, the current application of HAIC lacks precision, as drug dosages are typically calculated based solely on body surface area. This approach often results in underdosing for patients with larger liver tumors or greater liver volume and overdosing for those with smaller liver tumors or reduced liver volume. Consequently, determining drug dosages according to the specific target volume requiring treatment may enhance individualized and standardized therapy for HCC, aligning with the principles of precision oncology.
Collapse
Affiliation(s)
- Yong Tan
- Department of Hepatobiliary Surgery, Yuebei People’s Hospital, Shaoguan, Guangdong, 512026, People’s Republic of China
| | - Ping-Ping Li
- Department of Ophthalmology, Yuebei People’s Hospital, Shaoguan, Guangdong, 512026, People’s Republic of China
| | - Hui Liu
- Department of Hepatobiliary Surgery, Yuebei People’s Hospital, Shaoguan, Guangdong, 512026, People’s Republic of China
| | - Jian-Yong Zhu
- Department of Hepato-Pancreato-Biliary Surgery, The First Medical Center of PLA General Hospital, Beijing, 100853, People’s Republic of China
| | - Qing-Song Wu
- Department of Hepatobiliary Surgery, Yuebei People’s Hospital, Shaoguan, Guangdong, 512026, People’s Republic of China
| |
Collapse
|
3
|
Huang Z, Deng Z, Ye J, Wang H, Su Y, Li T, Sun H, Cheng J, Chen J, He J, Gu Y, Zhang S, Gu L, Qiao Y. A-Eval: A benchmark for cross-dataset and cross-modality evaluation of abdominal multi-organ segmentation. Med Image Anal 2025; 101:103499. [PMID: 39970528 DOI: 10.1016/j.media.2025.103499] [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: 02/20/2024] [Revised: 01/16/2025] [Accepted: 02/06/2025] [Indexed: 02/21/2025]
Abstract
Although deep learning has revolutionized abdominal multi-organ segmentation, its models often struggle with generalization due to training on small-scale, specific datasets and modalities. The recent emergence of large-scale datasets may mitigate this issue, but some important questions remain unsolved: Can models trained on these large datasets generalize well across different datasets and imaging modalities? If yes/no, how can we further improve their generalizability? To address these questions, we introduce A-Eval, a benchmark for the cross-dataset and cross-modality Evaluation ('Eval') of Abdominal ('A') multi-organ segmentation, integrating seven datasets across CT and MRI modalities. Our evaluations indicate that significant domain gaps persist despite larger data scales. While increased datasets improve generalization, model performance on unseen data remains inconsistent. Joint training across multiple datasets and modalities enhances generalization, though annotation inconsistencies pose challenges. These findings highlight the need for diverse and well-curated training data across various clinical scenarios and modalities to develop robust medical imaging models. The code and pre-trained models are available at https://github.com/uni-medical/A-Eval.
Collapse
Affiliation(s)
- Ziyan Huang
- Institute of Medical Robotics, Shanghai Jiao Tong University, Shanghai, 200240, China; School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, 200240, China; Shanghai Artificial Intelligence Laboratory, Shanghai, 200000, China
| | - Zhongying Deng
- Shanghai Artificial Intelligence Laboratory, Shanghai, 200000, China; Department of Applied Mathematics and Theoretical Physics, University of Cambridge, Cambridge, CB2 1TN, United Kingdom
| | - Jin Ye
- Shanghai Artificial Intelligence Laboratory, Shanghai, 200000, China
| | - Haoyu Wang
- Institute of Medical Robotics, Shanghai Jiao Tong University, Shanghai, 200240, China; School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, 200240, China; Shanghai Artificial Intelligence Laboratory, Shanghai, 200000, China
| | - Yanzhou Su
- Shanghai Artificial Intelligence Laboratory, Shanghai, 200000, China
| | - Tianbin Li
- Shanghai Artificial Intelligence Laboratory, Shanghai, 200000, China
| | - Hui Sun
- Shanghai Artificial Intelligence Laboratory, Shanghai, 200000, China
| | - Junlong Cheng
- Shanghai Artificial Intelligence Laboratory, Shanghai, 200000, China
| | - Jianpin Chen
- School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, 200240, China; Shanghai Artificial Intelligence Laboratory, Shanghai, 200000, China
| | - Junjun He
- Shanghai Artificial Intelligence Laboratory, Shanghai, 200000, China
| | - Yun Gu
- Institute of Medical Robotics, Shanghai Jiao Tong University, Shanghai, 200240, China
| | - Shaoting Zhang
- Shanghai Artificial Intelligence Laboratory, Shanghai, 200000, China
| | - Lixu Gu
- Institute of Medical Robotics, Shanghai Jiao Tong University, Shanghai, 200240, China; School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, 200240, China.
| | - Yu Qiao
- Shanghai Artificial Intelligence Laboratory, Shanghai, 200000, China.
| |
Collapse
|
4
|
Mathai TS, Lubner MG, Pickhardt PJ, Summers RM. Fully Automated and Explainable Measurement of Liver Surface Nodularity in CT: Utility for Staging Hepatic Fibrosis. Acad Radiol 2025; 32:1398-1408. [PMID: 39379241 PMCID: PMC11875990 DOI: 10.1016/j.acra.2024.09.050] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/23/2024] [Revised: 09/19/2024] [Accepted: 09/23/2024] [Indexed: 10/10/2024]
Abstract
RATIONALE AND OBJECTIVES In the United States, cirrhosis was the 12th leading cause of death in 2016. Despite end-stage cirrhosis being irreversible, earlier stages of hepatic fibrosis can be reversed via early diagnosis and intervention. The objective is to investigate the utility of a fully automated technique to measure liver surface nodularity (LSN) for staging hepatic fibrosis (stages F0-F4). MATERIALS AND METHODS In this retrospective study, a dataset consisting of patients with multiple etiologies of liver disease collected at Institution-A (METAVIR F0-F4, 2000-2016) was used. The LSN was automatically measured in contrast-enhanced CT volumes and compared against scores from a manual tool. Area under the receiver operating characteristics curve (AUC) was used to distinguish between clinically significant fibrosis (≥ F2), advanced fibrosis (≥F3), and end-stage cirrhosis (F4). RESULTS The study sample had 480 patients (304 men, 176 women, mean age, 49±9). Automatically derived LSN scores progressively increased with the fibrosis stage: F0 (1.64 [mean]±1.13 [standard deviation]), F1 (2.16±2.39), F2 (2.17±2.55), F3 (2.23±2.52), and F4 (4.21±2.94). For discriminating significant fibrosis (≥F2), advanced fibrosis (≥F3), and cirrhosis (F4), the automated tool achieved ROC AUCs of 73.9%, 82.5%, and 87.8% respectively. The sensitivity and specificity for significant fibrosis (nodularity threshold 1.51) was 85.2% and 73.3%, advanced fibrosis (nodularity threshold 1.73) was 84.2% and 79.5%, and cirrhosis (nodularity threshold 2.18) was 86.5% and 79.5%. Statistical tests revealed that the automated LSN scores distinguished patients with advanced fibrosis (p<.001) and cirrhosis (p<.001). CONCLUSION The fully automated LSN measurement retained its predictive power for distinguishing between advanced fibrosis and cirrhosis. The clinical impact is that the fully automated LSN measurement may be useful for early interventions and population-based studies. It can automatically predict the fibrosis stage in ∼45 s in comparison to the ∼2 min needed to manually measure the LSN in a CT volume.
Collapse
Affiliation(s)
- Tejas Sudharshan Mathai
- National Institutes of Health Clinical Center, Building 10 Room 1C224, Bethesda, Maryland 20892-1182, USA (T.S.M., R.M.S.).
| | - Meghan G Lubner
- University of Wisconsin School of Medicine & Public Health (M.G.L., P.J.P.).
| | - Perry J Pickhardt
- University of Wisconsin School of Medicine & Public Health (M.G.L., P.J.P.).
| | - Ronald M Summers
- National Institutes of Health Clinical Center, Building 10 Room 1C224, Bethesda, Maryland 20892-1182, USA (T.S.M., R.M.S.).
| |
Collapse
|
5
|
Pomohaci MD, Grasu MC, Băicoianu-Nițescu AŞ, Enache RM, Lupescu IG. Systematic Review: AI Applications in Liver Imaging with a Focus on Segmentation and Detection. Life (Basel) 2025; 15:258. [PMID: 40003667 PMCID: PMC11856300 DOI: 10.3390/life15020258] [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: 12/29/2024] [Revised: 02/02/2025] [Accepted: 02/05/2025] [Indexed: 02/27/2025] Open
Abstract
The liver is a frequent focus in radiology due to its diverse pathology, and artificial intelligence (AI) could improve diagnosis and management. This systematic review aimed to assess and categorize research studies on AI applications in liver radiology from 2018 to 2024, classifying them according to areas of interest (AOIs), AI task and imaging modality used. We excluded reviews and non-liver and non-radiology studies. Using the PRISMA guidelines, we identified 6680 articles from the PubMed/Medline, Scopus and Web of Science databases; 1232 were found to be eligible. A further analysis of a subgroup of 329 studies focused on detection and/or segmentation tasks was performed. Liver lesions were the main AOI and CT was the most popular modality, while classification was the predominant AI task. Most detection and/or segmentation studies (48.02%) used only public datasets, and 27.65% used only one public dataset. Code sharing was practiced by 10.94% of these articles. This review highlights the predominance of classification tasks, especially applied to liver lesion imaging, most often using CT imaging. Detection and/or segmentation tasks relied mostly on public datasets, while external testing and code sharing were lacking. Future research should explore multi-task models and improve dataset availability to enhance AI's clinical impact in liver imaging.
Collapse
Affiliation(s)
- Mihai Dan Pomohaci
- Department 8: Radiology, Discipline of Radiology, Medical Imaging and Interventional Radiology I, University of Medicine and Pharmacy “Carol Davila”, 050474 Bucharest, Romania; (M.D.P.); (A.-Ș.B.-N.)
- Department of Radiology and Medical Imaging, Fundeni Clinical Institute, 022328 Bucharest, Romania;
| | - Mugur Cristian Grasu
- Department 8: Radiology, Discipline of Radiology, Medical Imaging and Interventional Radiology I, University of Medicine and Pharmacy “Carol Davila”, 050474 Bucharest, Romania; (M.D.P.); (A.-Ș.B.-N.)
- Department of Radiology and Medical Imaging, Fundeni Clinical Institute, 022328 Bucharest, Romania;
| | - Alexandru-Ştefan Băicoianu-Nițescu
- Department 8: Radiology, Discipline of Radiology, Medical Imaging and Interventional Radiology I, University of Medicine and Pharmacy “Carol Davila”, 050474 Bucharest, Romania; (M.D.P.); (A.-Ș.B.-N.)
- Department of Radiology and Medical Imaging, Fundeni Clinical Institute, 022328 Bucharest, Romania;
| | - Robert Mihai Enache
- Department of Radiology and Medical Imaging, Fundeni Clinical Institute, 022328 Bucharest, Romania;
| | - Ioana Gabriela Lupescu
- Department 8: Radiology, Discipline of Radiology, Medical Imaging and Interventional Radiology I, University of Medicine and Pharmacy “Carol Davila”, 050474 Bucharest, Romania; (M.D.P.); (A.-Ș.B.-N.)
- Department of Radiology and Medical Imaging, Fundeni Clinical Institute, 022328 Bucharest, Romania;
| |
Collapse
|
6
|
Gringeri E, Furlanetto A, Polacco M, Perin L, Nieddu E, Rosso E, De Nardi C, Ballo M, De Feo T, Trapani S, Burra P, Spada M, Colledan M, Lauterio A, Romagnoli R, Cardillo M, Feltrin G, De Carlis L, Cillo U. Exploring auxiliary liver transplantation in the era of transplant oncology-A proposal for a new liver splitting program (ALERT-50). Liver Transpl 2025:01445473-990000000-00552. [PMID: 39835850 DOI: 10.1097/lvt.0000000000000574] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/21/2024] [Accepted: 12/08/2024] [Indexed: 01/22/2025]
Abstract
Total hepatectomy and liver transplantation have emerged as a game-changing strategy in the treatment of several liver-confined primary or metastatic tumors, opening a new era of transplant oncology. However, the expansion of indications is going to worsen the chronic scarcity of organs, and new strategies are needed to enlarge the donor pool. A possible source of organs could be developing split liver transplantation programs. We propose to refer donors aged 18-50 years unsuitable for pediatric patients and donors aged 50-60 years for split evaluation. This will generate new small left lateral grafts that can be used for resection and partial liver segment II-III transplantation with delayed total hepatectomy procedures, based on a national waiting list specifically for non-HCC oncologic patients. Centralized imaging review will streamline the donor-recipient matching process and address organizational challenges. Additionally, adopting an ex situ splitting technique during hypothermic oxygenated machine perfusion could further enhance logistical efficiency and improve graft viability. The proposed protocol (ALERT 50) will therefore promote the development of oncologic indications without affecting the standard waiting list and without competing with urgent or pediatric patients.
Collapse
Affiliation(s)
- Enrico Gringeri
- Hepato-biliary-pancreatic Surgery and Liver Transplantation Unit, Padua University Hospital, Padua, Italy
| | - Alessandro Furlanetto
- Hepato-biliary-pancreatic Surgery and Liver Transplantation Unit, Padua University Hospital, Padua, Italy
| | - Marina Polacco
- Hepato-biliary-pancreatic Surgery and Liver Transplantation Unit, Padua University Hospital, Padua, Italy
| | - Luca Perin
- Hepato-biliary-pancreatic Surgery and Liver Transplantation Unit, Padua University Hospital, Padua, Italy
| | - Eleonora Nieddu
- Hepato-biliary-pancreatic Surgery and Liver Transplantation Unit, Padua University Hospital, Padua, Italy
| | - Eugenia Rosso
- Hepato-biliary-pancreatic Surgery and Liver Transplantation Unit, Padua University Hospital, Padua, Italy
| | - Clarissa De Nardi
- Hepato-biliary-pancreatic Surgery and Liver Transplantation Unit, Padua University Hospital, Padua, Italy
| | - Mattia Ballo
- Hepato-biliary-pancreatic Surgery and Liver Transplantation Unit, Padua University Hospital, Padua, Italy
| | - Tullia De Feo
- North Italy Transplant Program (NITp), UOC Coordinamento Trapianti, Fondazione IRCCS Ca' Granda-Ospedale Maggiore Policlinico, Milan, Italy
| | - Silvia Trapani
- Italian National Transplant Center-Istituto Superiore Di Sanità, Rome, Italy
| | - Patrizia Burra
- Multivisceral Transplant Unit, Padova University, Padova, Italy
| | - Marco Spada
- Division of Hepatobiliopancreatic Surgery, Liver and Kidney Transplantation, Ospedale Pediatrico Bambino Gesù, IRCCS, Roma, Italy
| | - Michele Colledan
- Department of Medicine and Surgery, University of Milano-Bicocca, Milan, Italy
- Department of Organ Failure and Transplantation, Ospedale Papa Giovanni XXIII, Bergamo, Italy
| | - Andrea Lauterio
- Department of General Surgery and Transplantation, Niguarda Ca' Granda Hospital, Milan, Italy
| | - Renato Romagnoli
- Liver Transplant Center, General Surgery 2, University of Turin, AOU Città della Salute e della Scienza di Torino, Turin, Italy
| | - Massimo Cardillo
- North Italy Transplant Program (NITp), UOC Coordinamento Trapianti, Fondazione IRCCS Ca' Granda-Ospedale Maggiore Policlinico, Milan, Italy
| | - Giuseppe Feltrin
- Italian National Transplant Center-Istituto Superiore Di Sanità, Rome, Italy
| | - Luciano De Carlis
- Department of General Surgery and Transplantation, Niguarda Ca' Granda Hospital, Milan, Italy
| | - Umberto Cillo
- Hepato-biliary-pancreatic Surgery and Liver Transplantation Unit, Padua University Hospital, Padua, Italy
| |
Collapse
|
7
|
Wei H, Zheng T, Zhang X, Zheng C, Jiang D, Wu Y, Lee JM, Bashir MR, Lerner E, Liu R, Wu B, Guo H, Chen Y, Yang T, Gong X, Jiang H, Song B. Deep learning-based 3D quantitative total tumor burden predicts early recurrence of BCLC A and B HCC after resection. Eur Radiol 2025; 35:127-139. [PMID: 39028376 PMCID: PMC11632001 DOI: 10.1007/s00330-024-10941-y] [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: 01/16/2024] [Revised: 05/15/2024] [Accepted: 06/16/2024] [Indexed: 07/20/2024]
Abstract
OBJECTIVES This study aimed to evaluate the potential of deep learning (DL)-assisted automated three-dimensional quantitative tumor burden at MRI to predict postoperative early recurrence (ER) of hepatocellular carcinoma (HCC). MATERIALS AND METHODS This was a single-center retrospective study enrolling patients who underwent resection for BCLC A and B HCC and preoperative contrast-enhanced MRI. Quantitative total tumor volume (cm3) and total tumor burden (TTB, %) were obtained using a DL automated segmentation tool. Radiologists' visual assessment was used to ensure the quality control of automated segmentation. The prognostic value of clinicopathological variables and tumor burden-related parameters for ER was determined by Cox regression analyses. RESULTS A total of 592 patients were included, with 525 and 67 patients assigned to BCLC A and B, respectively (2-year ER rate: 30.0% vs. 45.3%; hazard ratio (HR) = 1.8; p = 0.007). TTB was the most important predictor of ER (HR = 2.2; p < 0.001). Using 6.84% as the threshold of TTB, two ER risk strata were obtained in overall (p < 0.001), BCLC A (p < 0.001), and BCLC B (p = 0.027) patients, respectively. The BCLC B low-TTB patients had a similar risk for ER to BCLC A patients and thus were reassigned to a BCLC An stage; whilst the BCLC B high-TTB patients remained in a BCLC Bn stage. The 2-year ER rate was 30.5% for BCLC An patients vs. 58.1% for BCLC Bn patients (HR = 2.8; p < 0.001). CONCLUSIONS TTB determined by DL-based automated segmentation at MRI was a predictive biomarker for postoperative ER and facilitated refined subcategorization of patients within BCLC stages A and B. CLINICAL RELEVANCE STATEMENT Total tumor burden derived by deep learning-based automated segmentation at MRI may serve as an imaging biomarker for predicting early recurrence, thereby improving subclassification of Barcelona Clinic Liver Cancer A and B hepatocellular carcinoma patients after hepatectomy. KEY POINTS Total tumor burden (TTB) is important for Barcelona Clinic Liver Cancer (BCLC) staging, but is heterogenous. TTB derived by deep learning-based automated segmentation was predictive of postoperative early recurrence. Incorporating TTB into the BCLC algorithm resulted in successful subcategorization of BCLC A and B patients.
Collapse
Affiliation(s)
- Hong Wei
- Department of Radiology, Functional, and Molecular Imaging Key Laboratory of Sichuan Province, West China Hospital, Sichuan University, Chengdu, Sichuan, 610041, China
- Department of Radiology, Seoul National University Hospital, Seoul, 03080, Republic of Korea
| | - Tianying Zheng
- Department of Radiology, Functional, and Molecular Imaging Key Laboratory of Sichuan Province, West China Hospital, Sichuan University, Chengdu, Sichuan, 610041, China
| | | | - Chao Zheng
- Shukun Technology Co., Ltd, Beijing, 100102, China
| | - Difei Jiang
- Shukun Technology Co., Ltd, Beijing, 100102, China
| | - Yuanan Wu
- Big Data Research Center, University of Electronic Science and Technology of China, Chengdu, Sichuan, 610000, China
| | - Jeong Min Lee
- Department of Radiology, Seoul National University Hospital, Seoul, 03080, Republic of Korea
- Department of Radiology, Seoul National University College of Medicine, Seoul, 03080, Republic of Korea
| | - Mustafa R Bashir
- Department of Radiology, Duke University Medical Center, Durham, NC, 27710, USA
- Center for Advanced Magnetic Resonance in Medicine, Duke University Medical Center, Durham, NC, 27705, USA
- Division of Gastroenterology, Department of Medicine, Duke University Medical Center, Durham, NC, 27710, USA
| | - Emily Lerner
- Department of Radiology, Duke University Medical Center, Durham, NC, 27710, USA
| | - Rongbo Liu
- Department of Radiology, Functional, and Molecular Imaging Key Laboratory of Sichuan Province, West China Hospital, Sichuan University, Chengdu, Sichuan, 610041, China
| | - Botong Wu
- Center for Biomedical Imaging Research, Department of Biomedical Engineering, School of Medicine, Tsinghua University, Beijing, 100102, China
| | - Hua Guo
- Center for Biomedical Imaging Research, Department of Biomedical Engineering, School of Medicine, Tsinghua University, Beijing, 100102, China
| | - Yidi Chen
- Department of Radiology, Functional, and Molecular Imaging Key Laboratory of Sichuan Province, West China Hospital, Sichuan University, Chengdu, Sichuan, 610041, China
| | - Ting Yang
- Department of Radiology, Functional, and Molecular Imaging Key Laboratory of Sichuan Province, West China Hospital, Sichuan University, Chengdu, Sichuan, 610041, China
| | - Xiaoling Gong
- Department of Radiology, Functional, and Molecular Imaging Key Laboratory of Sichuan Province, West China Hospital, Sichuan University, Chengdu, Sichuan, 610041, China
| | - Hanyu Jiang
- Department of Radiology, Functional, and Molecular Imaging Key Laboratory of Sichuan Province, West China Hospital, Sichuan University, Chengdu, Sichuan, 610041, China.
| | - Bin Song
- Department of Radiology, Functional, and Molecular Imaging Key Laboratory of Sichuan Province, West China Hospital, Sichuan University, Chengdu, Sichuan, 610041, China.
- Department of Radiology, Sanya People's Hospital, Sanya, Hainan, 572000, China.
| |
Collapse
|
8
|
Bull N, Goonawardena J, Hua L, Lim D, Cheung KT, Ramachandran V, Fox A, Hassen S. Measurement of the distal bile duct density on computed tomography can differentiate choledocholithiasis from a control population. ANZ J Surg 2024; 94:2195-2200. [PMID: 39101372 DOI: 10.1111/ans.19189] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/27/2024] [Revised: 06/25/2024] [Accepted: 07/25/2024] [Indexed: 08/06/2024]
Abstract
PURPOSE Hounsfield unit density of biliary fluid on CT may be a useful clinical marker that has not been described in the literature. This method has been used to differentiate pyonephrosis from hydronephrosis in obstructed collecting systems of the kidney. We aimed to create a user-friendly technique to measure the density of the distal bile duct using CT. The bile duct density of cases with proven choledocholithiasis at ERCP were compared with those of a control group (no biliary pathology). METHODS A total of 106 patients with proven choledocholithiasis at ERCP and 50 control patients were analysed. The distal bile duct density was calculated using the 4-point and max ellipse methods. Two blinded, independent investigators calculated the bile duct density. RESULTS The HU is significantly higher in the presence of choledocholithiasis (P < 0.0001). Using the Youden index a cut-off value of 28.6 HU for the 4-point technique is useful to predict the presence of choledocholithiasis (Sensitivity 58%, Specificity 86%). CONCLUSION Calculation of the distal bile duct density can differentiate choledocholithiasis from a control population. It may be useful alone or as a component of a scoring system to select patients more effectively for intervention. The improved use of CT may also decrease use of MRCP and reduce time to ERCP, which have potential cost benefits.
Collapse
Affiliation(s)
- Nicholas Bull
- Department of UGI and HPB Surgery, Box Hill Hospital, Box Hill, Victoria, Australia
| | - Janindu Goonawardena
- Department of UGI and HPB Surgery, Box Hill Hospital, Box Hill, Victoria, Australia
| | - Lina Hua
- Department of UGI and HPB Surgery, Box Hill Hospital, Box Hill, Victoria, Australia
| | - Dee Lim
- Department of UGI and HPB Surgery, Box Hill Hospital, Box Hill, Victoria, Australia
| | - King Tung Cheung
- Department of UGI and HPB Surgery, Box Hill Hospital, Box Hill, Victoria, Australia
| | - Vivek Ramachandran
- Department of Radiology, Box Hill Hospital, Box Hill, Victoria, Australia
| | - Adrian Fox
- Department of UGI and HPB Surgery, Box Hill Hospital, Box Hill, Victoria, Australia
| | - Sayed Hassen
- Department of UGI and HPB Surgery, Box Hill Hospital, Box Hill, Victoria, Australia
| |
Collapse
|
9
|
Ma J, Zhang Y, Gu S, Ge C, Mae S, Young A, Zhu C, Yang X, Meng K, Huang Z, Zhang F, Pan Y, Huang S, Wang J, Sun M, Zhang R, Jia D, Choi JW, Alves N, de Wilde B, Koehler G, Lai H, Wang E, Wiesenfarth M, Zhu Q, Dong G, He J, FLARE Challenge Consortium, Wang B. Unleashing the strengths of unlabelled data in deep learning-assisted pan-cancer abdominal organ quantification: the FLARE22 challenge. Lancet Digit Health 2024; 6:e815-e826. [PMID: 39455194 DOI: 10.1016/s2589-7500(24)00154-7] [Citation(s) in RCA: 7] [Impact Index Per Article: 7.0] [Reference Citation Analysis] [Collaborators] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/17/2023] [Revised: 06/30/2024] [Accepted: 07/08/2024] [Indexed: 10/28/2024]
Abstract
Deep learning has shown great potential to automate abdominal organ segmentation and quantification. However, most existing algorithms rely on expert annotations and do not have comprehensive evaluations in real-world multinational settings. To address these limitations, we organised the FLARE 2022 challenge to benchmark fast, low-resource, and accurate abdominal organ segmentation algorithms. We first constructed an intercontinental abdomen CT dataset from more than 50 clinical research groups. We then independently validated that deep learning algorithms achieved a median dice similarity coefficient (DSC) of 90·0% (IQR 87·4-91·3%) by use of 50 labelled images and 2000 unlabelled images, which can substantially reduce manual annotation costs. The best-performing algorithms successfully generalised to holdout external validation sets, achieving a median DSC of 89·4% (85·2-91·3%), 90·0% (84·3-93·0%), and 88·5% (80·9-91·9%) on North American, European, and Asian cohorts, respectively. These algorithms show the potential to use unlabelled data to boost performance and alleviate annotation shortages for modern artificial intelligence models.
Collapse
Affiliation(s)
- Jun Ma
- University Health Network, Toronto, ON, Canada; Department of Laboratory Medicine and Pathobiology, University of Toronto, Toronto, ON, Canada; Vector Institute, Toronto, ON, Canada
| | - Yao Zhang
- AI Lab, Lenovo Research, Beijing, China
| | - Song Gu
- Department of Image Reconstruction, Nanjing Anke Medical Technology, Nanjing, China
| | - Cheng Ge
- School of Medicine and Pharmacy, Ocean University of China, Qingdao, China
| | - Shihao Mae
- University Health Network, Toronto, ON, Canada; Department of Computer Science, University of Toronto, Toronto, ON, Canada; Vector Institute, Toronto, ON, Canada
| | - Adamo Young
- Department of Computer Science, University of Toronto, Toronto, ON, Canada; Vector Institute, Toronto, ON, Canada; Terrence Donnelly Centre for Cellular and Biomolecular Research, University of Toronto, Toronto, ON, Canada
| | - Cheng Zhu
- Beijing Tinavi Medical Technologies, Beijing, China
| | - Xin Yang
- School of Biomedical Engineering, Health Science Center, Shenzhen University, Shenzhen, China
| | - Kangkang Meng
- University of Science and Technology Beijing, Beijing, China
| | - Ziyan Huang
- Institute of Medical Robotics, Shanghai Jiao Tong University, Shanghai, China; Shanghai AI Laboratory, Shanghai, China
| | - Fan Zhang
- Department of Radiological Algorithm, Fosun Aitrox Information Technology, Shanghai, China
| | - Yuanke Pan
- Shenzhen Technology University, Shenzhen, China
| | | | | | - Mingze Sun
- Tsinghua-Berkeley Shenzhen Institute, Tsinghua University, Shenzhen, China
| | - Rongguo Zhang
- Academy for Multidisciplinary Studies, Capital Normal University, Beijing, China
| | - Dengqiang Jia
- Hong Kong Centre for Cerebro-cardiovascular Health Engineering, Hong Kong Special Administrative Region, China
| | - Jae Won Choi
- Department of Radiology, Seoul National University Hospital, Seoul, South Korea
| | - Natália Alves
- Department of Radiology, Radboud University Medical Center, Nijmegen, Netherlands
| | - Bram de Wilde
- Department of Radiology, Radboud University Medical Center, Nijmegen, Netherlands
| | - Gregor Koehler
- Division of Medical Image Computing, German Cancer Research Center Heidelberg, Heidelberg, Germany; German Cancer Research Center Heidelberg, Heidelberg, Germany; Helmholtz Information and Data Science School for Health, Karlsruhe/Heidelberg, Germany
| | - Haoran Lai
- Southern Medical University, Guangzhou, China
| | | | - Manuel Wiesenfarth
- Division of Biostatistics, German Cancer Research Center Heidelberg, Heidelberg, Germany
| | - Qiongjie Zhu
- Department of Radiology, Shidong Hospital affiliated to University of Shanghai for Science and Technology, Shanghai, China
| | - Guoqiang Dong
- Department of Interventional Radiology, The Second Affiliated Hospital of Bengbu Medical University, Bengbu, China
| | - Jian He
- Department of Nuclear Medicine, Nanjing Drum Tower Hospital, Nanjing, China
| | | | - Bo Wang
- University Health Network, Toronto, ON, Canada; Department of Laboratory Medicine and Pathobiology, University of Toronto, Toronto, ON, Canada; Department of Computer Science, University of Toronto, Toronto, ON, Canada; Vector Institute, Toronto, ON, Canada; University Health Network AI Hub, Toronto, ON, Canada.
| |
Collapse
Collaborators
Junjun He, Hua Yang, Bingding Huang, Mengye Lyu, Yongkang Ma, Heng Guo, Weixin Xu, Klaus Maier-Hein, Yajun Wu,
Collapse
|
10
|
Moeller AR, Garrett JW, Summers RM, Pickhardt PJ. Adjusting for the effect of IV contrast on automated CT body composition measures during the portal venous phase. Abdom Radiol (NY) 2024; 49:2543-2551. [PMID: 38744704 DOI: 10.1007/s00261-024-04376-8] [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: 02/09/2024] [Revised: 05/04/2024] [Accepted: 05/06/2024] [Indexed: 05/16/2024]
Abstract
OBJECTIVE Fully-automated CT-based algorithms for quantifying numerous biomarkers have been validated for unenhanced abdominal scans. There is great interest in optimizing the documentation and reporting of biophysical measures present on all CT scans for the purposes of opportunistic screening and risk profiling. The purpose of this study was to determine and adjust the effect of intravenous (IV) contrast on these automated body composition measures at routine portal venous phase post-contrast imaging. METHODS Final study cohort consisted of 1,612 older adults (mean age, 68.0 years; 594 women) all imaged utilizing a uniform CT urothelial protocol consisting of pre-contrast, portal venous, and delayed excretory phases. Fully-automated CT-based algorithms for quantifying numerous biomarkers, including muscle and fat area and density, bone mineral density, and solid organ volume were applied to pre-contrast and portal venous phases. The effect of IV contrast upon these body composition measures was analyzed. Regression analyses, including square of the Pearson correlation coefficient (r2), were performed for each comparison. RESULTS We found that simple, linear relationships can be derived to determine non-contrast equivalent values from the post-contrast CT biomeasures. Excellent positive linear correlation (r2 = 0.91-0.99) between pre- and post-contrast values was observed for all automated soft tissue measures, whereas moderate positive linear correlation was observed for bone attenuation (r2 = 0.58-0.76). In general, the area- and volume-based measurement require less adjustment than attenuation-based measures, as expected. CONCLUSION Fully-automated quantitative CT-biomarker measures at portal venous phase abdominal CT can be adjusted to a non-contrast equivalent using simple, linear relationships.
Collapse
Affiliation(s)
- Alexander R Moeller
- Department of Radiology, University of Wisconsin School of Medicine & Public Health, E3/311 Clinical Science Center 600 Highland Ave., Madison, WI, 53792-3252, USA
| | - John W Garrett
- Department of Radiology, University of Wisconsin School of Medicine & Public Health, E3/311 Clinical Science Center 600 Highland Ave., Madison, WI, 53792-3252, USA
| | - Ronald M Summers
- Imaging Biomarkers and Computer-Aided Diagnosis Laboratory, Department of Radiology and Imaging Sciences, National Institutes of Health Clinical Center, Bethesda, MD, USA
| | - Perry J Pickhardt
- Department of Radiology, University of Wisconsin School of Medicine & Public Health, E3/311 Clinical Science Center 600 Highland Ave., Madison, WI, 53792-3252, USA.
| |
Collapse
|
11
|
Fan L, Liu J, Ju B, Lou D, Tian Y. A deep learning based holistic diagnosis system for immunohistochemistry interpretation and molecular subtyping. Neoplasia 2024; 50:100976. [PMID: 38412576 PMCID: PMC10904904 DOI: 10.1016/j.neo.2024.100976] [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: 11/06/2023] [Accepted: 02/02/2024] [Indexed: 02/29/2024]
Abstract
BACKGROUND Breast cancer in different molecular subtypes, which is determined by the overexpression rates of human epidermal growth factor receptor 2 (HER2), estrogen receptor (ER), progesterone receptor (PR), and Ki67, exhibit distinct symptom characteristics and sensitivity to different treatment. The immunohistochemical method, one of the most common detecting tools for tumour markers, is heavily relied on artificial judgment and in clinical practice, with an inherent limitation in interpreting stability and operating efficiency. Here, a holistic intelligent breast tumour diagnosis system has been developed for tumour-markeromic analysis, combining the automatic interpretation and clinical suggestion. METHODS The holistic intelligent breast tumour diagnosis system included two main modules. The interpreting modules were constructed based on convolutional neural network, for comprehensively extracting and analyzing the multi-features of immunostaining. Referring to the clinical classification criteria, the interpreting results were encoded in a low-dimensional feature representation in the subtyping module, to efficiently output a holistic detecting result of the critical tumour-markeromic with diagnosis suggestions on molecular subtypes. RESULTS The overexpression rates of HER2, ER, PR, and Ki67, as well as an effective determination of molecular subtypes were successfully obtained by this diagnosis system, with an average sensitivity of 97.6 % and an average specificity of 96.1 %, among those, the sensitivity and specificity for interpreting HER2 were up to 99.8 % and 96.9 %. CONCLUSION The holistic intelligent breast tumour diagnosis system shows improved performance in the interpretation of immunohistochemical images over pathologist-level, which can be expected to overcome the limitations of conventional manual interpretation in efficiency, precision, and repeatability.
Collapse
Affiliation(s)
- Lin Fan
- School of Integrated Circuit Science and Engineering (Industry-Education Integration School), Nanjing University of Posts and Telecommunications, Nanjing 210023, PR China; State Key Laboratory of Bioelectronics, Jiangsu Key Laboratory for Biomaterials and Devices, School of Biological Science and Medical Engineering & Collaborative Innovation Center of Suzhou Nano Science and Technology, Southeast University, Nanjing 210096, PR China; Medical School of Nanjing University, Nanjing 210093, PR China.
| | - Jiahe Liu
- School of Integrated Circuit Science and Engineering (Industry-Education Integration School), Nanjing University of Posts and Telecommunications, Nanjing 210023, PR China
| | - Baoyang Ju
- School of Integrated Circuit Science and Engineering (Industry-Education Integration School), Nanjing University of Posts and Telecommunications, Nanjing 210023, PR China
| | - Doudou Lou
- Nanjing Institute for Food and Drug Control, Nanjing, Jiangsu 211198, PR China
| | - Yushen Tian
- School of Electrical Engineering, Shenyang University of Technology, Shenyang, Liaoning 110870, PR China.
| |
Collapse
|
12
|
Hill DLG. AI in imaging: the regulatory landscape. Br J Radiol 2024; 97:483-491. [PMID: 38366148 PMCID: PMC11027239 DOI: 10.1093/bjr/tqae002] [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: 10/11/2023] [Revised: 12/03/2023] [Accepted: 12/26/2023] [Indexed: 02/18/2024] Open
Abstract
Artificial intelligence (AI) methods have been applied to medical imaging for several decades, but in the last few years, the number of publications and the number of AI-enabled medical devices coming on the market have significantly increased. While some AI-enabled approaches are proving very valuable, systematic reviews of the AI imaging field identify significant weaknesses in a significant proportion of the literature. Medical device regulators have recently become more proactive in publishing guidance documents and recognizing standards that will require that the development and validation of AI-enabled medical devices need to be more rigorous than required for tradition "rule-based" software. In particular, developers are required to better identify and mitigate risks (such as bias) that arise in AI-enabled devices, and to ensure that the devices are validated in a realistic clinical setting to ensure their output is clinically meaningful. While this evolving regulatory landscape will mean that device developers will take longer to bring novel AI-based medical imaging devices to market, such additional rigour is necessary to address existing weaknesses in the field and ensure that patients and healthcare professionals can trust AI-enabled devices. There would also be benefits in the academic community taking into account this regulatory framework, to improve the quality of the literature and make it easier for academically developed AI tools to make the transition to medical devices that impact healthcare.
Collapse
|
13
|
Zhang Y, Fan X, Song B, Liu Y, Chen Y, Zheng T, Guo Y, Duan T, Huang Z, Yang L. Noninvasive prediction of insufficient biochemical response after ursodeoxycholic acid treatment in patients with primary biliary cholangitis based on pretreatment nonenhanced MRI. Eur Radiol 2024; 34:1268-1279. [PMID: 37581659 PMCID: PMC10853298 DOI: 10.1007/s00330-023-10080-w] [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: 11/30/2022] [Revised: 06/12/2023] [Accepted: 07/20/2023] [Indexed: 08/16/2023]
Abstract
OBJECTIVES To explore the feasibility of pretreatment nonenhanced magnetic resonance imaging (MRI) in predicting insufficient biochemical response to ursodeoxycholic acid (UDCA) in patients with primary biliary cholangitis (PBC). METHODS From January 2009 to April 2022, consecutive PBC patients who were treated with UDCA and underwent nonenhanced MRI within 30 days before treatment were retrospectively enrolled. All MR images were independently evaluated by two blinded radiologists. Uni- and multivariable logistic regression analyses were performed to develop a predictive model for 12-month insufficient biochemical response. Model performances were evaluated by computing the area under the receiver operating characteristic curve (AUC), sensitivity, and specificity. RESULTS A total of 74 patients (50.6 ± 11.9 years; 62 females) were included. Three pretreatment MRI features, including hepatomegaly (odds ratio [OR]: 4.580; p = 0.011), periportal hyperintensity on T2-weighted imaging (T2WI) (OR: 4.795, p = 0.008), and narrowing of the bile ducts (OR: 3.491; p = 0.027) were associated with 12-month insufficient biochemical response in the multivariable analysis. A predictive model based on the above indicators had an AUC of 0.781, sensitivity of 85.4%, and specificity of 61.5% for predicting insufficient biochemical response. CONCLUSIONS A noninvasive model based on three pretreatment MRI features could accurately predict 12-month insufficient biochemical response to UDCA in patients with PBC. Early identification of PBC patients at increased risk for insufficient response can facilitate the timely initiation of additional treatment. CLINICAL RELEVANCE STATEMENT A noninvasive predictive model constructed by incorporating three pretreatment MRI features may help identify patients with primary biliary cholangitis at high risk of insufficient biochemical response to ursodeoxycholic acid and facilitate the timely initiation of additional treatment. KEY POINTS • Noninvasive imaging features based on nonenhanced pretreatment MRI may predict an insufficient biochemical response to UDCA in PBC patients. • A combined model based on three MRI features (hepatomegaly, periportal hyperintensity on T2-weighted imaging, and narrowing of the bile ducts) further improved the predictive efficacy for an insufficient biochemical response to UDCA in PBC patients, with high sensitivity and specificity. • The nomogram of the combined model showed good calibration and predictive efficacy for an insufficient biochemical response to UDCA in PBC patients. In particular, the calibration curve visualised the clinical applicability of the prediction model.
Collapse
Affiliation(s)
- Yun Zhang
- Department of Radiology, West China Hospital, Sichuan University, No.37 Guoxue Alley, Wuhou District, Chengdu, 610041, Sichuan, China
| | - Xiaoli Fan
- Department of Gastroenterology and Hepatology, Sichuan University-University of Oxford Huaxi Joint Centre for Gastrointestinal Cancer, West China Hospital, Sichuan University, Chengdu, 610041, Sichuan, China
| | - Bin Song
- Department of Radiology, West China Hospital, Sichuan University, No.37 Guoxue Alley, Wuhou District, Chengdu, 610041, Sichuan, China
- Department of Radiology, Sanya People's Hospital, Sanya, Hainan, China
| | - Yifeng Liu
- Department of Gastroenterology and Hepatology, Sichuan University-University of Oxford Huaxi Joint Centre for Gastrointestinal Cancer, West China Hospital, Sichuan University, Chengdu, 610041, Sichuan, China
| | - Yidi Chen
- Department of Radiology, West China Hospital, Sichuan University, No.37 Guoxue Alley, Wuhou District, Chengdu, 610041, Sichuan, China
| | - Tianying Zheng
- Department of Radiology, West China Hospital, Sichuan University, No.37 Guoxue Alley, Wuhou District, Chengdu, 610041, Sichuan, China
| | - Yuxin Guo
- Department of Gastroenterology and Hepatology, Sichuan University-University of Oxford Huaxi Joint Centre for Gastrointestinal Cancer, West China Hospital, Sichuan University, Chengdu, 610041, Sichuan, China
| | - Ting Duan
- Department of Radiology, West China Hospital, Sichuan University, No.37 Guoxue Alley, Wuhou District, Chengdu, 610041, Sichuan, China
| | - Zixing Huang
- Department of Radiology, West China Hospital, Sichuan University, No.37 Guoxue Alley, Wuhou District, Chengdu, 610041, Sichuan, China.
- Department of Radiology, West China Tianfu Hospital of Sichuan University, Chengdu, China.
| | - Li Yang
- Department of Gastroenterology and Hepatology, Sichuan University-University of Oxford Huaxi Joint Centre for Gastrointestinal Cancer, West China Hospital, Sichuan University, Chengdu, 610041, Sichuan, China.
| |
Collapse
|
14
|
Machry M, Ferreira LF, Lucchese AM, Kalil AN, Feier FH. Liver volumetric and anatomic assessment in living donor liver transplantation: The role of modern imaging and artificial intelligence. World J Transplant 2023; 13:290-298. [PMID: 38174151 PMCID: PMC10758682 DOI: 10.5500/wjt.v13.i6.290] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 06/27/2023] [Revised: 08/17/2023] [Accepted: 10/17/2023] [Indexed: 12/15/2023] Open
Abstract
The shortage of deceased donor organs has prompted the development of alternative liver grafts for transplantation. Living-donor liver transplantation (LDLT) has emerged as a viable option, expanding the donor pool and enabling timely transplantation with favorable graft function and improved long-term outcomes. An accurate evaluation of the donor liver's volumetry (LV) and anatomical study is crucial to ensure adequate future liver remnant, graft volume and precise liver resection. Thus, ensuring donor safety and an appropriate graft-to-recipient weight ratio. Manual LV (MLV) using computed tomography has traditionally been considered the gold standard for assessing liver volume. However, the method has been limited by cost, subjectivity, and variability. Automated LV techniques employing advanced segmentation algorithms offer improved reproducibility, reduced variability, and enhanced efficiency compared to manual measurements. However, the accuracy of automated LV requires further investigation. The study provides a comprehensive review of traditional and emerging LV methods, including semi-automated image processing, automated LV techniques, and machine learning-based approaches. Additionally, the study discusses the respective strengths and weaknesses of each of the aforementioned techniques. The use of artificial intelligence (AI) technologies, including machine learning and deep learning, is expected to become a routine part of surgical planning in the near future. The implementation of AI is expected to enable faster and more accurate image study interpretations, improve workflow efficiency, and enhance the safety, speed, and cost-effectiveness of the procedures. Accurate preoperative assessment of the liver plays a crucial role in ensuring safe donor selection and improved outcomes in LDLT. MLV has inherent limitations that have led to the adoption of semi-automated and automated software solutions. Moreover, AI has tremendous potential for LV and segmentation; however, its widespread use is hindered by cost and availability. Therefore, the integration of multiple specialties is necessary to embrace technology and explore its possibilities, ranging from patient counseling to intraoperative decision-making through automation and AI.
Collapse
Affiliation(s)
- Mayara Machry
- Department of Hepato-Biliary-Pancreatic Surgery and Liver Transplantation, Irmandade Santa Casa de Misericórdia de Porto Alegre, Porto Alegre 90020-090, Brazil
| | - Luis Fernando Ferreira
- Postgraduation Program in Medicine: Hepatology, Federal University of Health Sciences of Porto Alegre, Porto Alegre 90050-170, Brazil
| | - Angelica Maria Lucchese
- Department of Hepato-Biliary-Pancreatic Surgery and Liver Transplantation, Irmandade Santa Casa de Misericórdia de Porto Alegre, Porto Alegre 90020-090, Brazil
| | - Antonio Nocchi Kalil
- Department of Hepato-Biliary-Pancreatic Surgery and Liver Transplantation, Irmandade Santa Casa de Misericórdia de Porto Alegre, Porto Alegre 90020-090, Brazil
- Postgraduation Program in Medicine: Hepatology, Federal University of Health Sciences of Porto Alegre, Porto Alegre 90050-170, Brazil
| | - Flavia Heinz Feier
- Department of Hepato-Biliary-Pancreatic Surgery and Liver Transplantation, Irmandade Santa Casa de Misericórdia de Porto Alegre, Porto Alegre 90020-090, Brazil
- Postgraduation Program in Medicine: Hepatology, Federal University of Health Sciences of Porto Alegre, Porto Alegre 90050-170, Brazil
| |
Collapse
|
15
|
Rao S, Glavis-Bloom J, Bui TL, Afzali K, Bansal R, Carbone J, Fateri C, Roth B, Chan W, Kakish D, Cortes G, Wang P, Meraz J, Chantaduly C, Chow DS, Chang PD, Houshyar R. Artificial Intelligence for Improved Hepatosplenomegaly Diagnosis. Curr Probl Diagn Radiol 2023; 52:501-504. [PMID: 37277270 DOI: 10.1067/j.cpradiol.2023.05.005] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/23/2023] [Revised: 04/14/2023] [Accepted: 05/08/2023] [Indexed: 06/07/2023]
Abstract
Hepatosplenomegaly is commonly diagnosed by radiologists based on single dimension measurements and heuristic cut-offs. Volumetric measurements may be more accurate for diagnosing organ enlargement. Artificial intelligence techniques may be able to automatically calculate liver and spleen volume and facilitate more accurate diagnosis. After IRB approval, 2 convolutional neural networks (CNN) were developed to automatically segment the liver and spleen on a training dataset comprised of 500 single-phase, contrast-enhanced CT abdomen and pelvis examinations. A separate dataset of ten thousand sequential examinations at a single institution was segmented with these CNNs. Performance was evaluated on a 1% subset and compared with manual segmentations using Sorensen-Dice coefficients and Pearson correlation coefficients. Radiologist reports were reviewed for diagnosis of hepatomegaly and splenomegaly and compared with calculated volumes. Abnormal enlargement was defined as greater than 2 standard deviations above the mean. Median Dice coefficients for liver and spleen segmentation were 0.988 and 0.981, respectively. Pearson correlation coefficients of CNN-derived estimates of organ volume against the gold-standard manual annotation were 0.999 for the liver and spleen (P < 0.001). Average liver volume was 1556.8 ± 498.7 cc and average spleen volume was 194.6 ± 123.0 cc. There were significant differences in average liver and spleen volumes between male and female patients. Thus, the volume thresholds for ground-truth determination of hepatomegaly and splenomegaly were determined separately for each sex. Radiologist classification of hepatomegaly was 65% sensitive, 91% specific, with a positive predictive value (PPV) of 23% and an negative predictive value (NPV) of 98%. Radiologist classification of splenomegaly was 68% sensitive, 97% specific, with a positive predictive value (PPV) of 50% and a negative predictive value (NPV) of 99%. Convolutional neural networks can accurately segment the liver and spleen and may be helpful to improve radiologist accuracy in the diagnosis of hepatomegaly and splenomegaly.
Collapse
Affiliation(s)
- Sriram Rao
- University of California, Irvine School of Medicine, Irvine, CA
| | - Justin Glavis-Bloom
- Department of Radiological Sciences, University of California, Irvine Medical Center, Orange, CA
| | - Thanh-Lan Bui
- Department of Radiological Sciences, University of California, Irvine Medical Center, Orange, CA
| | - Kasra Afzali
- Department of Radiological Sciences, University of California, Irvine Medical Center, Orange, CA
| | - Riya Bansal
- University of California, Irvine School of Medicine, Irvine, CA
| | - Joseph Carbone
- Department of Radiological Sciences, University of California, Irvine Medical Center, Orange, CA
| | - Cameron Fateri
- University of California, Irvine School of Medicine, Irvine, CA
| | - Bradley Roth
- University of California, Irvine School of Medicine, Irvine, CA
| | - William Chan
- University of California, Irvine School of Medicine, Irvine, CA
| | - David Kakish
- Department of Radiological Sciences, University of California, Irvine Medical Center, Orange, CA
| | - Gillean Cortes
- Department of Radiological Sciences, University of California, Irvine Medical Center, Orange, CA
| | - Peter Wang
- Department of Radiological Sciences, University of California, Irvine Medical Center, Orange, CA
| | - Jeanette Meraz
- Department of Radiological Sciences, University of California, Irvine Medical Center, Orange, CA
| | - Chanon Chantaduly
- Department of Radiological Sciences, University of California, Irvine Medical Center, Orange, CA
| | - Dan S Chow
- Department of Radiological Sciences, University of California, Irvine Medical Center, Orange, CA
| | - Peter D Chang
- Department of Radiological Sciences, University of California, Irvine Medical Center, Orange, CA
| | - Roozbeh Houshyar
- Department of Radiological Sciences, University of California, Irvine Medical Center, Orange, CA.
| |
Collapse
|
16
|
Zhang Y, Zheng T, Huang Z, Song B. CT and MR imaging of primary biliary cholangitis: a pictorial review. Insights Imaging 2023; 14:180. [PMID: 37880457 PMCID: PMC10600092 DOI: 10.1186/s13244-023-01517-3] [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: 04/26/2023] [Accepted: 09/03/2023] [Indexed: 10/27/2023] Open
Abstract
Primary biliary cholangitis (PBC) is a rare chronic autoimmune-mediated cholestatic liver disease involving medium and small bile ducts that can lead to liver fibrosis and cirrhosis. To date, the pathogenesis of PBC remains elusive, and there is currently no curative medical treatment. Computed tomography (CT) and magnetic resonance (MR) imaging, as common technical tools that allow non-invasive monitoring of liver tissue in vivo, play crucial roles in the diagnosis, staging, and prognosis prediction in PBC by enabling assessment of abnormalities in liver morphology and parenchyma, irregular configuration of bile ducts, lymphadenopathy, portal hypertension, and complications of cirrhosis. Moreover, CT and MRI can be used to monitor the disease progression after treatment of PBC (e.g. the onset of cirrhotic decompensation or HCC) to guide the clinical decisions for liver transplantation. With the optimization of imaging technology, magnetic resonance elastography (MRE) offers additional information on liver stiffness, allows for the identification of early cirrhosis in PBC and provides a basis for predicting prognosis. Gadoxetic acid-enhanced MRI enables the assessment of liver function in patients with PBC. The purpose of this review is to detail and illustrate the definition, pathological basis, and clinical importance of CT and MRI features of PBC to help radiologists and clinicians enhance their understanding of PBC.Critical Relevance StatementCharacteristic CT and MR imaging manifestations of primary biliary cholangitis may reflect the course of the disease and provide information associated with histological grading and altered cellular function.Key points• Imaging has become highly useful for differentiating PBC from other diseases.• Key pathological alterations of PBC can be captured by CT and MRI.• Characteristic manifestations provide information associated with histological grade and cellular function.• Despite this, the CT or MRI features of PBC are not specific.
Collapse
Affiliation(s)
- Yun Zhang
- Department of Radiology, West China Hospital, Sichuan University, No.37 Guoxue Alley, Wuhou District, Chengdu, 610041, Sichuan, China
| | - Tianying Zheng
- Department of Radiology, West China Hospital, Sichuan University, No.37 Guoxue Alley, Wuhou District, Chengdu, 610041, Sichuan, China
| | - Zixing Huang
- Department of Radiology, West China Hospital, Sichuan University, No.37 Guoxue Alley, Wuhou District, Chengdu, 610041, Sichuan, China
- Department of Radiology, West China Tianfu hospital of Sichuan University, Chengdu, China
| | - Bin Song
- Department of Radiology, West China Hospital, Sichuan University, No.37 Guoxue Alley, Wuhou District, Chengdu, 610041, Sichuan, China.
- Department of Radiology, Sanya People's Hospital, Sanya, Hainan, China.
| |
Collapse
|
17
|
Zhang L, LaBelle W, Unberath M, Chen H, Hu J, Li G, Dreizin D. A vendor-agnostic, PACS integrated, and DICOM-compatible software-server pipeline for testing segmentation algorithms within the clinical radiology workflow. Front Med (Lausanne) 2023; 10:1241570. [PMID: 37954555 PMCID: PMC10637622 DOI: 10.3389/fmed.2023.1241570] [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: 06/20/2023] [Accepted: 10/09/2023] [Indexed: 11/14/2023] Open
Abstract
Background Reproducible approaches are needed to bring AI/ML for medical image analysis closer to the bedside. Investigators wishing to shadow test cross-sectional medical imaging segmentation algorithms on new studies in real-time will benefit from simple tools that integrate PACS with on-premises image processing, allowing visualization of DICOM-compatible segmentation results and volumetric data at the radiology workstation. Purpose In this work, we develop and release a simple containerized and easily deployable pipeline for shadow testing of segmentation algorithms within the clinical workflow. Methods Our end-to-end automated pipeline has two major components- 1. A router/listener and anonymizer and an OHIF web viewer backstopped by a DCM4CHEE DICOM query/retrieve archive deployed in the virtual infrastructure of our secure hospital intranet, and 2. An on-premises single GPU workstation host for DICOM/NIfTI conversion steps, and image processing. DICOM images are visualized in OHIF along with their segmentation masks and associated volumetry measurements (in mL) using DICOM SEG and structured report (SR) elements. Since nnU-net has emerged as a widely-used out-of-the-box method for training segmentation models with state-of-the-art performance, feasibility of our pipleine is demonstrated by recording clock times for a traumatic pelvic hematoma nnU-net model. Results Mean total clock time from PACS send by user to completion of transfer to the DCM4CHEE query/retrieve archive was 5 min 32 s (± SD of 1 min 26 s). This compares favorably to the report turnaround times for whole-body CT exams, which often exceed 30 min, and illustrates feasibility in the clinical setting where quantitative results would be expected prior to report sign-off. Inference times accounted for most of the total clock time, ranging from 2 min 41 s to 8 min 27 s. All other virtual and on-premises host steps combined ranged from a minimum of 34 s to a maximum of 48 s. Conclusion The software worked seamlessly with an existing PACS and could be used for deployment of DL models within the radiology workflow for prospective testing on newly scanned patients. Once configured, the pipeline is executed through one command using a single shell script. The code is made publicly available through an open-source license at "https://github.com/vastc/," and includes a readme file providing pipeline config instructions for host names, series filter, other parameters, and citation instructions for this work.
Collapse
Affiliation(s)
- Lei Zhang
- School of Medicine, University of Maryland, Baltimore, MD, United States
| | - Wayne LaBelle
- School of Medicine, University of Maryland, Baltimore, MD, United States
| | - Mathias Unberath
- Department of Computer Science, Whiting School of Engineering, Johns Hopkins University, Baltimore, MD, United States
| | - Haomin Chen
- Department of Computer Science, Whiting School of Engineering, Johns Hopkins University, Baltimore, MD, United States
| | - Jiazhen Hu
- Department of Computer Science, Whiting School of Engineering, Johns Hopkins University, Baltimore, MD, United States
| | - Guang Li
- School of Medicine, University of Maryland, Baltimore, MD, United States
| | - David Dreizin
- School of Medicine, University of Maryland, Baltimore, MD, United States
| |
Collapse
|
18
|
Sun K, Fan C, Feng Z, Min X, Wang Y, Sun Z, Li Y, Cai W, Yin X, Zhang P, Liu Q, Xia L. Magnetic resonance imaging based deep-learning model: a rapid, high-performance, automated tool for testicular volume measurements. Front Med (Lausanne) 2023; 10:1277535. [PMID: 37795413 PMCID: PMC10546058 DOI: 10.3389/fmed.2023.1277535] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/14/2023] [Accepted: 09/06/2023] [Indexed: 10/06/2023] Open
Abstract
Background Testicular volume (TV) is an essential parameter for monitoring testicular functions and pathologies. Nevertheless, current measurement tools, including orchidometers and ultrasonography, encounter challenges in obtaining accurate and personalized TV measurements. Purpose Based on magnetic resonance imaging (MRI), this study aimed to establish a deep learning model and evaluate its efficacy in segmenting the testes and measuring TV. Materials and methods The study cohort consisted of retrospectively collected patient data (N = 200) and a prospectively collected dataset comprising 10 healthy volunteers. The retrospective dataset was divided into training and independent validation sets, with an 8:2 random distribution. Each of the 10 healthy volunteers underwent 5 scans (forming the testing dataset) to evaluate the measurement reproducibility. A ResUNet algorithm was applied to segment the testes. Volume of each testis was calculated by multiplying the voxel volume by the number of voxels. Manually determined masks by experts were used as ground truth to assess the performance of the deep learning model. Results The deep learning model achieved a mean Dice score of 0.926 ± 0.034 (0.921 ± 0.026 for the left testis and 0.926 ± 0.034 for the right testis) in the validation cohort and a mean Dice score of 0.922 ± 0.02 (0.931 ± 0.019 for the left testis and 0.932 ± 0.022 for the right testis) in the testing cohort. There was strong correlation between the manual and automated TV (R2 ranging from 0.974 to 0.987 in the validation cohort; R2 ranging from 0.936 to 0.973 in the testing cohort). The volume differences between the manual and automated measurements were 0.838 ± 0.991 (0.209 ± 0.665 for LTV and 0.630 ± 0.728 for RTV) in the validation cohort and 0.815 ± 0.824 (0.303 ± 0.664 for LTV and 0.511 ± 0.444 for RTV) in the testing cohort. Additionally, the deep-learning model exhibited excellent reproducibility (intraclass correlation >0.9) in determining TV. Conclusion The MRI-based deep learning model is an accurate and reliable tool for measuring TV.
Collapse
Affiliation(s)
- Kailun Sun
- Department of Urology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China
| | - Chanyuan Fan
- Department of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, Hubei, China
| | - Zhaoyan Feng
- Department of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, Hubei, China
| | - Xiangde Min
- Department of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, Hubei, China
| | - Yu Wang
- Department of Research and Development, Infervision Medical Technology Co., Ltd., Beijing, China
| | - Ziyan Sun
- Department of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, Hubei, China
| | - Yan Li
- Department of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, Hubei, China
| | - Wei Cai
- Department of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, Hubei, China
| | - Xi Yin
- Department of CT & MRI, The First Affiliated Hospital, College of Medicine, Shihezi University, Shihezi, China
| | - Peipei Zhang
- Department of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, Hubei, China
| | - Qiuyu Liu
- Department of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, Hubei, China
| | - Liming Xia
- Department of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, Hubei, China
| |
Collapse
|
19
|
Zhang L, LaBelle W, Unberath M, Chen H, Hu J, Li G, Dreizin D. A vendor-agnostic, PACS integrated, and DICOMcompatible software-server pipeline for testing segmentation algorithms within the clinical radiology workflow. RESEARCH SQUARE 2023:rs.3.rs-2837634. [PMID: 37163064 PMCID: PMC10168465 DOI: 10.21203/rs.3.rs-2837634/v1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/11/2023]
Abstract
Background Reproducible approaches are needed to bring AI/ML for medical image analysis closer to the bedside. Investigators wishing to shadow test cross-sectional medical imaging segmentation algorithms on new studies in real-time will benefit from simple tools that integrate PACS with on-premises image processing, allowing visualization of DICOM-compatible segmentation results and volumetric data at the radiology workstation. Purpose In this work, we develop and release a simple containerized and easily deployable pipeline for shadow testing of segmentation algorithms within the clinical workflow. Methods Our end-to-end automated pipeline has two major components-1. a router/listener and anonymizer and an OHIF web viewer backstopped by a DCM4CHEE DICOM query/retrieve archive deployed in the virtual infrastructure of our secure hospital intranet, and 2. An on-premises single GPU workstation host for DICOM/NIfTI conversion steps, and image processing. DICOM images are visualized in OHIF along with their segmentation masks and associated volumetry measurements (in mL) using DICOM SEG and structured report (SR) elements. Feasibility is demonstrated by recording clock times for a traumatic pelvic hematoma cascaded nnU-net model. Results Mean total clock time from PACS send by user to completion of transfer to the DCM4CHEE query/retrieve archive was 5 minutes 32 seconds (+/- SD of 1 min 26 sec). This compares favorably to the report turnaround times for whole-body CT exams, which often exceed 30 minutes. Inference times accounted for most of the total clock time, ranging from 2 minutes 41 seconds to 8 minutes 27 seconds. All other virtual and on-premises host steps combined ranged from a minimum of 34 seconds to a maximum of 48 seconds. Conclusion The software worked seamlessly with an existing PACS and could be used for deployment of DL models within the radiology workflow for prospective testing on newly scanned patients. Once configured, the pipeline is executed through one command using a single shell script. The code is made publicly available through an open-source license at "https://github.com/vastc/", and includes a readme file providing pipeline config instructions for host names, series filter, other parameters, and citation instructions for this work.
Collapse
Affiliation(s)
| | | | | | | | | | - Guang Li
- University of Maryland, Baltimore
| | | |
Collapse
|
20
|
Elhakim T, Trinh K, Mansur A, Bridge C, Daye D. Role of Machine Learning-Based CT Body Composition in Risk Prediction and Prognostication: Current State and Future Directions. Diagnostics (Basel) 2023; 13:968. [PMID: 36900112 PMCID: PMC10000509 DOI: 10.3390/diagnostics13050968] [Citation(s) in RCA: 7] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/23/2022] [Revised: 02/11/2023] [Accepted: 02/18/2023] [Indexed: 03/08/2023] Open
Abstract
CT body composition analysis has been shown to play an important role in predicting health and has the potential to improve patient outcomes if implemented clinically. Recent advances in artificial intelligence and machine learning have led to high speed and accuracy for extracting body composition metrics from CT scans. These may inform preoperative interventions and guide treatment planning. This review aims to discuss the clinical applications of CT body composition in clinical practice, as it moves towards widespread clinical implementation.
Collapse
Affiliation(s)
- Tarig Elhakim
- Department of Medicine, Perelman School of Medicine at the University of Pennsylvania, Philadelphia, PA 19104, USA
- Department of Radiology, Massachusetts General Hospital, Boston, MA 02114, USA
| | - Kelly Trinh
- School of Medicine, Texas Tech University Health Sciences Center, School of Medicine, Lubbock, TX 79430, USA
| | - Arian Mansur
- Harvard Medical School, Harvard University, Boston, MA 02115, USA
| | - Christopher Bridge
- Department of Radiology, Massachusetts General Hospital, Boston, MA 02114, USA
- Harvard Medical School, Harvard University, Boston, MA 02115, USA
| | - Dania Daye
- Department of Radiology, Massachusetts General Hospital, Boston, MA 02114, USA
- Harvard Medical School, Harvard University, Boston, MA 02115, USA
| |
Collapse
|
21
|
de Padua V Alves V, Dillman JR, Somasundaram E, Taylor ZP, Brady SL, Zhang B, Trout AT. Computed tomography-based measurements of normative liver and spleen volumes in children. Pediatr Radiol 2023; 53:378-386. [PMID: 36471169 DOI: 10.1007/s00247-022-05551-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/29/2022] [Revised: 09/29/2022] [Accepted: 11/10/2022] [Indexed: 12/12/2022]
Abstract
BACKGROUND Quantification of organ size has utility in clinical care and research for diagnostics, prognostics and surgical planning. Volumetry is regarded as the best measure of organ size and change in size over time. Scarce reference values exist for liver and spleen volumes in healthy children. OBJECTIVE To report liver and spleen volumes for a sample of children defined by manual segmentation of contrast-enhanced CT images with the goal of defining normal values and thresholds that might indicate disease. MATERIALS AND METHODS This retrospective study included clinically acquired contrast-enhanced CTs of the abdomen/pelvis for children and adolescents imaged between January 2018 and July 2021. Liver and spleen volumes were derived through manual segmentation of CTs reconstructed at 2.5-, 3- or 5-mm slice thickness. A subset of images (5%, n=16) was also segmented using 0.5-mm slice thickness reconstructions to define agreement based on image slice thickness. We used Pearson correlation and multivariable regression to assess associations between organ volumes and patient characteristics. We generated reference intervals for the 5th, 25th, 50th (median), 75th and 95th percentiles for organ volumes as a function of age and weight using quantile regression models. Finally, we calculated Bland-Altman plots and intraclass correlation coefficients (ICC) to quantify agreement. RESULTS We included a total of 320 children (mean age ± standard deviation [SD] = 9±4.6 years; mean weight 38.1±18.8 kg; 160 female). Liver volume ranged from 340-2,002 mL, and spleen volume ranged from 28-480 mL. Patient weight (kg) (β=12.5), age (months) (β=1.7) and sex (female) (β = -35.3) were independent predictors of liver volume, whereas patient weight (kg) (β=2.4) and age (months) (β=0.3) were independent predictors of spleen volume. There was excellent absolute agreement (ICC=0.99) and minimal absolute difference (4 mL) in organ volumes based on reconstructed slice thickness. CONCLUSION We report reference liver and spleen volumes for children without liver or spleen disease. These results provide reference ranges and potential thresholds to identify liver and spleen size abnormalities that might reflect disease in children.
Collapse
Affiliation(s)
- Vinicius de Padua V Alves
- Department of Radiology, Cincinnati Children's Hospital Medical Center, 3333 Burnet Ave., Kasota Building MLC 5031, Cincinnati, OH, 45229, USA
| | - Jonathan R Dillman
- Department of Radiology, Cincinnati Children's Hospital Medical Center, 3333 Burnet Ave., Kasota Building MLC 5031, Cincinnati, OH, 45229, USA
- Department of Radiology, University of Cincinnati College of Medicine, Cincinnati, OH, USA
| | - Elanchezhian Somasundaram
- Department of Radiology, Cincinnati Children's Hospital Medical Center, 3333 Burnet Ave., Kasota Building MLC 5031, Cincinnati, OH, 45229, USA
| | - Zachary P Taylor
- Department of Radiology, Cincinnati Children's Hospital Medical Center, 3333 Burnet Ave., Kasota Building MLC 5031, Cincinnati, OH, 45229, USA
| | - Samuel L Brady
- Department of Radiology, Cincinnati Children's Hospital Medical Center, 3333 Burnet Ave., Kasota Building MLC 5031, Cincinnati, OH, 45229, USA
- Department of Radiology, University of Cincinnati College of Medicine, Cincinnati, OH, USA
| | - Bin Zhang
- Division of Biostatistics and Epidemiology, Cincinnati Children's Hospital Medical Center, Cincinnati, OH, USA
- Department of Pediatrics, University of Cincinnati College of Medicine, Cincinnati, OH, USA
| | - Andrew T Trout
- Department of Radiology, Cincinnati Children's Hospital Medical Center, 3333 Burnet Ave., Kasota Building MLC 5031, Cincinnati, OH, 45229, USA.
- Department of Radiology, University of Cincinnati College of Medicine, Cincinnati, OH, USA.
- Department of Pediatrics, University of Cincinnati College of Medicine, Cincinnati, OH, USA.
| |
Collapse
|
22
|
Yu Q, Xu C, Li Q, Ding Z, Lv Y, Liu C, Huang Y, Zhou J, Huang S, Xia C, Meng X, Lu C, Li Y, Tang T, Wang Y, Song Y, Qi X, Ye J, Ju S. Spleen volume-based non-invasive tool for predicting hepatic decompensation in people with compensated cirrhosis (CHESS1701). JHEP Rep 2022; 4:100575. [PMID: 36204707 PMCID: PMC9531280 DOI: 10.1016/j.jhepr.2022.100575] [Citation(s) in RCA: 9] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 05/18/2022] [Revised: 07/14/2022] [Accepted: 08/16/2022] [Indexed: 11/30/2022] Open
Abstract
Background & Aims Non-invasive stratification of the liver decompensation risk remains unmet in people with compensated cirrhosis. This study aimed to develop a non-invasive tool (NIT) to predict hepatic decompensation. Methods This retrospective study recruited 689 people with compensated cirrhosis (median age, 54 years; 441 men) from 5 centres from January 2016 to June 2020. Baseline abdominal computed tomography (CT), clinical features, and liver stiffness were collected, and then the first decompensation was registered during the follow-up. The spleen-based model was designed for predicting decompensation based on a deep learning segmentation network to generate the spleen volume and least absolute shrinkage and selection operator (LASSO)-Cox. The spleen-based model was trained on the training cohort of 282 individuals (Institutions I–III) and was validated in 2 external validation cohorts (97 and 310 individuals from Institutions IV and V, respectively) and compared with the conventional serum-based models and the Baveno VII criteria. Results The decompensation rate at 3 years was 23%, with a 37.6-month median (IQR 21.1–52.1 months) follow-up. The proposed model showed good performance in predicting decompensation (C-index ≥0.84) and outperformed the serum-based models (C-index comparison test p <0.05) in both the training and validation cohorts. The hazard ratio (HR) for decompensation in individuals with high risk was 7.3 (95% CI 4.2–12.8) in the training and 5.8 (95% CI 3.9–8.6) in the validation (log-rank test, p <0.05) cohorts. The low-risk group had a negligible 3-year decompensation risk (≤1%), and the model had a competitive performance compared with the Baveno VII criteria. Conclusions This spleen-based model provides a non-invasive and user-friendly method to help predict decompensation in people with compensated cirrhosis in diverse healthcare settings where liver stiffness is not available. Lay summary People with compensated cirrhosis with larger spleen volume would have a higher risk of decompensation. We developed a spleen-based model and validated it in external validation cohorts. The proposed model might help predict hepatic decompensation in people with compensated cirrhosis when invasive tools are unavailable.
Spleen volume is a predictor for decompensation by rapid risk increasement after spleen volume >364 cm3. The spleen-based model revealed incremental prognostic improvement (C-index >0.84). Low-risk patients identified by the spleen-based model had a negligible 3-year risk (≤1%) of decompensation.
Collapse
Affiliation(s)
- Qian Yu
- Department of Radiology, Zhongda Hospital, School of Medicine, Southeast University, Nanjing, China
| | - Chuanjun Xu
- Department of Radiology, The Second Hospital of Nanjing, Nanjing University of Chinese Medicine, Nanjing, China
| | - Qinyi Li
- Department of Radiology, The Affiliated Third Hospital of Jiangsu University, Zhenjiang, China
| | - Zhimin Ding
- Department of Radiology, Yijishan Hospital of Wannan Medical College, Wuhu, China
| | - Yan Lv
- Department of Medical Imaging, Subei People’s Hospital, Medical School of Yangzhou University, Yangzhou, China
| | - Chuan Liu
- Center of Portal Hypertension, Department of Radiology, Zhongda Hospital, School of Medicine, Southeast University, Nanjing, China
| | - Yifei Huang
- CHESS Center, Institute of Portal Hypertension, The First Hospital of Lanzhou University, Lanzhou, China
| | - Jiaying Zhou
- Department of Radiology, Zhongda Hospital, School of Medicine, Southeast University, Nanjing, China
| | - Shan Huang
- Department of Radiology, Zhongda Hospital, School of Medicine, Southeast University, Nanjing, China
| | - Cong Xia
- Department of Radiology, Zhongda Hospital, School of Medicine, Southeast University, Nanjing, China
| | - Xiangpan Meng
- Department of Radiology, Zhongda Hospital, School of Medicine, Southeast University, Nanjing, China
| | - Chunqiang Lu
- Department of Radiology, Zhongda Hospital, School of Medicine, Southeast University, Nanjing, China
| | - Yuefeng Li
- Department of Radiology, The Affiliated Hospital of Jiangsu University, Zhenjiang, China
| | - Tianyu Tang
- Department of Radiology, Zhongda Hospital, School of Medicine, Southeast University, Nanjing, China
| | - Yuancheng Wang
- Department of Radiology, Zhongda Hospital, School of Medicine, Southeast University, Nanjing, China
| | - Yang Song
- MR Scientific Marketing, Siemens Healthineers Ltd., Shanghai, China
| | - Xiaolong Qi
- Center of Portal Hypertension, Department of Radiology, Zhongda Hospital, School of Medicine, Southeast University, Nanjing, China
| | - Jing Ye
- Department of Medical Imaging, Subei People’s Hospital, Medical School of Yangzhou University, Yangzhou, China
| | - Shenghong Ju
- Department of Radiology, Zhongda Hospital, School of Medicine, Southeast University, Nanjing, China
- Corresponding author. Address: Department of Radiology, Zhongda Hospital, School of Medicine, Southeast University, Nanjing, China. Tel.: +86-83272121.
| |
Collapse
|
23
|
Bates DDB, Pickhardt PJ. CT-Derived Body Composition Assessment as a Prognostic Tool in Oncologic Patients: From Opportunistic Research to Artificial Intelligence-Based Clinical Implementation. AJR Am J Roentgenol 2022; 219:671-680. [PMID: 35642760 DOI: 10.2214/ajr.22.27749] [Citation(s) in RCA: 31] [Impact Index Per Article: 10.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/12/2022]
Abstract
CT-based body composition measures are well established in research settings as prognostic markers in oncologic patients. Numerous retrospective studies have shown the role of objective measurements extracted from abdominal CT images of skeletal muscle, abdominal fat, and bone mineral density in providing more accurate assessments of frailty and cancer cachexia in comparison with traditional clinical methods. Quantitative CT-based measurements of liver fat and aortic atherosclerotic calcification have received relatively less attention in cancer care but also provide prognostic information. Patients with cancer routinely undergo serial CT examinations for staging, treatment response, and surveillance, providing the opportunity for quantitative body composition assessment to be performed as part of routine clinical care. The emergence of fully automated artificial intelligence-based segmentation and quantification tools to replace earlier time-consuming manual and semiautomated methods for body composition analysis will allow these opportunistic measures to transition from the research realm to clinical practice. With continued investigation, the measurements may ultimately be applied to achieve more precise risk stratification as a component of personalized oncologic care.
Collapse
Affiliation(s)
- David D B Bates
- Department of Radiology, Memorial Sloan Kettering Cancer Center, New York, NY
| | - Perry J Pickhardt
- Department of Radiology, University of Wisconsin School of Medicine & Public Health, E3/311 Clinical Science Center, 600 Highland Ave, Madison, WI 53792-3252
| |
Collapse
|
24
|
Bao J, Feng X, Ma Y, Wang Y, Qi J, Qin C, Tan X, Tian Y. The latest application progress of radiomics in prediction and diagnosis of liver diseases. Expert Rev Gastroenterol Hepatol 2022; 16:707-719. [PMID: 35880549 DOI: 10.1080/17474124.2022.2104711] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 11/04/2022]
Abstract
INTRODUCTION Early detection and individualized treatment of patients with liver disease is the key to survival. Radiomics can extract high-throughput quantitative features by multimode imaging, which has good application prospects for the diagnosis, staging and prognosis of benign and malignant liver diseases. Therefore, this paper summarizes the current research status in the field of liver disease, in order to help these patients achieve personalized and precision medical care. AREAS COVERED This paper uses several keywords on the PubMed database to search the references, and reviews the workflow of traditional radiomics, as well as the characteristics and influencing factors of different imaging modes. At the same time, the references on the application of imaging in different benign and malignant liver diseases were also summarized. EXPERT OPINION For patients with liver disease, the traditional imaging evaluation can only provide limited information. Radiomics exploits the characteristics of high-throughput and high-dimensional extraction, enabling liver imaging capabilities far beyond the scope of traditional visual image analysis. Recent studies have demonstrated the prospect of this technology in personalized diagnosis and treatment decision in various fields of the liver. However, further clinical validation is needed in its application and practice.
Collapse
Affiliation(s)
- Jiaying Bao
- Shandong Provincial Hospital Affiliated to Shandong First Medical University, Jinan, P.R. China
| | - Xiao Feng
- Shandong Provincial Hospital Affiliated to Shandong First Medical University, Jinan, P.R. China
| | - Yan Ma
- Department of Ultrasound, Zibo Central Hospital, Zibo, P.R. China
| | - Yanyan Wang
- Departments of Emergency Medicine, Shandong Provincial Hospital Affiliated to Shandong First Medical University, Jinan, Shandong, P.R. China
| | - Jianni Qi
- Central Laboratory, Shandong Provincial Hospital Affiliated to Shandong First Medical University, Jinan, Shandong, P.R. China
| | - Chengyong Qin
- Shandong Provincial Hospital Affiliated to Shandong First Medical University, Jinan, P.R. China
| | - Xu Tan
- Department of Gynecology, Shandong Provincial Hospital Affiliated to Shandong First Medical University, Jinan, Shandong, P.R. China
| | - Yongmei Tian
- Department of Geriatrics, Shandong Provincial Hospital Affiliated to Shandong First Medical University, Jinan, Shandong, P.R. China
| |
Collapse
|
25
|
Yuan E, Ye Z, Song B. Imaging-based deep learning in liver diseases. Chin Med J (Engl) 2022; 135:1325-1327. [PMID: 35837673 PMCID: PMC9433077 DOI: 10.1097/cm9.0000000000002199] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [MESH Headings] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/14/2021] [Indexed: 02/05/2023] Open
Affiliation(s)
- Enyu Yuan
- West China School of Medicine, Sichuan University, Chengdu, Sichuan 610041, China
- Department of Radiology, West China Hospital, Chengdu, Sichuan 610041, China
| | - Zheng Ye
- West China School of Medicine, Sichuan University, Chengdu, Sichuan 610041, China
- Department of Radiology, West China Hospital, Chengdu, Sichuan 610041, China
| | - Bin Song
- West China School of Medicine, Sichuan University, Chengdu, Sichuan 610041, China
- Department of Radiology, West China Hospital, Chengdu, Sichuan 610041, China
- Department of Radiology, Sanya People's Hospital, Sanya/West China (Sanya) Hospital, Sanya, Hainan 572022, China
| |
Collapse
|
26
|
Pickhardt PJ. Value-added Opportunistic CT Screening: State of the Art. Radiology 2022; 303:241-254. [PMID: 35289661 PMCID: PMC9083232 DOI: 10.1148/radiol.211561] [Citation(s) in RCA: 119] [Impact Index Per Article: 39.7] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/21/2021] [Revised: 08/24/2021] [Accepted: 08/27/2021] [Indexed: 12/13/2022]
Abstract
Opportunistic CT screening leverages robust imaging data embedded within abdominal and thoracic scans that are generally unrelated to the specific clinical indication and have heretofore gone largely unused. This incidental imaging information may prove beneficial to patients in terms of wellness, prevention, risk profiling, and presymptomatic detection of relevant disease. The growing interest in CT-based opportunistic screening relates to a confluence of factors: the objective and generalizable nature of CT-based body composition measures, the emergence of fully automated explainable AI solutions, the sheer volume of body CT scans performed, and the increasing emphasis on precision medicine and value-added initiatives. With a systematic approach to body composition and other useful CT markers, initial evidence suggests that their ability to help radiologists assess biologic age and predict future adverse cardiometabolic events rivals even the best available clinical reference standards. Emerging data suggest that standalone "intended" CT screening over an unorganized opportunistic approach may be justified, especially when combined with established cancer screening. This review will discuss the current status of opportunistic CT screening, including specific body composition markers and the various disease processes that may be impacted. The remaining hurdles to widespread clinical adoption include generalization to more diverse patient populations, disparate technical settings, and reimbursement.
Collapse
Affiliation(s)
- Perry J. Pickhardt
- From the Department of Radiology, The University of Wisconsin School
of Medicine and Public Health, E3/311 Clinical Science Center, 600 Highland Ave,
Madison, WI 53792-3252
| |
Collapse
|
27
|
Pavone AM, Benfante V, Stefano A, Mamone G, Milazzo M, Di Pizza A, Parenti R, Maruzzelli L, Miraglia R, Comelli A. Automatic Liver Segmentation in Pre-TIPS Cirrhotic Patients: A Preliminary Step for Radiomics Studies. LECTURE NOTES IN COMPUTER SCIENCE 2022:408-418. [DOI: 10.1007/978-3-031-13321-3_36] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 01/03/2025]
|