Deep learning-based method for grading histopathological liver fibrosis in rodent models of metabolic dysfunction-associated steatohepatitis

IntroductionMetabolic dysfunction-associated steatohepatitis (MASH) is a significant liver disease that can lead to cirrhosis and liver cancer. Accurate assessment of liver fibrosis is crucial for diagnosis, prognosis, and informed treatment decision-making. Staging of liver fibrosis in MASH is base...

Full description

Saved in:
Bibliographic Details
Main Authors: Soo Min Ko, Jae-ik Shin, Yiyu Hong, Hyunji Kim, Insuk Sohn, Ji-Young Lee, Hyo-Jeong Han, Da Som Jeong, Yerin Lee, Woo-Chan Son
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-07-01
Series:Frontiers in Medicine
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fmed.2025.1629036/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849426984004747264
author Soo Min Ko
Jae-ik Shin
Jae-ik Shin
Yiyu Hong
Hyunji Kim
Insuk Sohn
Ji-Young Lee
Hyo-Jeong Han
Da Som Jeong
Yerin Lee
Woo-Chan Son
author_facet Soo Min Ko
Jae-ik Shin
Jae-ik Shin
Yiyu Hong
Hyunji Kim
Insuk Sohn
Ji-Young Lee
Hyo-Jeong Han
Da Som Jeong
Yerin Lee
Woo-Chan Son
author_sort Soo Min Ko
collection DOAJ
description IntroductionMetabolic dysfunction-associated steatohepatitis (MASH) is a significant liver disease that can lead to cirrhosis and liver cancer. Accurate assessment of liver fibrosis is crucial for diagnosis, prognosis, and informed treatment decision-making. Staging of liver fibrosis in MASH is based on Kleiner’s score, which categorizes fibrosis based on its location within the liver as observed microscopically. This scoring system is part of a standard clinical research network and relies heavily on the expertise of pathologists.MethodsThis study utilized Sirius Red-stained whole slide images of liver tissue obtained from various MASH animal models to develop deep learning (DL) models for scoring liver fibrosis, with a focus on the criteria outlined in Kleiner’s score. We created a trainable and testable dataset of whole-slide images of the liver, consisting of 999,711 patch images derived from 914 whole-slide images. The performance of the multi-class classification model was evaluated using the kappa statistic, area under the precision-recall curve (AUPRC), area under the receiver operating characteristic curve (AUROC), and Matthews correlation coefficient (MCC).ResultsTo address challenges in clinical subclassification, a 5-class classification model was initially applied; the model achieved moderate agreement. A more refined 7-class model was subsequently developed, which outperformed the 5-class classification model. The enhanced subclassification significantly improved classification performance, as evidenced by the superior AUROC and AUPRC values of the 7-class model.DiscussionThis study highlights that DL models for scoring liver fibrosis can support expert pathologists in staging liver fibrosis in preclinical animal studies.
format Article
id doaj-art-0dea2645a68049a98ab04669a3541d5b
institution Kabale University
issn 2296-858X
language English
publishDate 2025-07-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Medicine
spelling doaj-art-0dea2645a68049a98ab04669a3541d5b2025-08-20T03:29:10ZengFrontiers Media S.A.Frontiers in Medicine2296-858X2025-07-011210.3389/fmed.2025.16290361629036Deep learning-based method for grading histopathological liver fibrosis in rodent models of metabolic dysfunction-associated steatohepatitisSoo Min Ko0Jae-ik Shin1Jae-ik Shin2Yiyu Hong3Hyunji Kim4Insuk Sohn5Ji-Young Lee6Hyo-Jeong Han7Da Som Jeong8Yerin Lee9Woo-Chan Son10Department of Medical Science, AMIST, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of KoreaDepartment of R&D Center, Arontier Co., Ltd., Seoul, Republic of KoreaDepartment of Radiation Oncology, Yonsei University College of Medicine, Seoul, Republic of KoreaDepartment of R&D Center, Arontier Co., Ltd., Seoul, Republic of KoreaDepartment of R&D Center, Arontier Co., Ltd., Seoul, Republic of KoreaDepartment of R&D Center, Arontier Co., Ltd., Seoul, Republic of KoreaDepartment of Pathology, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of KoreaDepartment of Pathology, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of KoreaDepartment of Medical Science, AMIST, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of KoreaDepartment of Medical Science, AMIST, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of KoreaDepartment of Pathology, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of KoreaIntroductionMetabolic dysfunction-associated steatohepatitis (MASH) is a significant liver disease that can lead to cirrhosis and liver cancer. Accurate assessment of liver fibrosis is crucial for diagnosis, prognosis, and informed treatment decision-making. Staging of liver fibrosis in MASH is based on Kleiner’s score, which categorizes fibrosis based on its location within the liver as observed microscopically. This scoring system is part of a standard clinical research network and relies heavily on the expertise of pathologists.MethodsThis study utilized Sirius Red-stained whole slide images of liver tissue obtained from various MASH animal models to develop deep learning (DL) models for scoring liver fibrosis, with a focus on the criteria outlined in Kleiner’s score. We created a trainable and testable dataset of whole-slide images of the liver, consisting of 999,711 patch images derived from 914 whole-slide images. The performance of the multi-class classification model was evaluated using the kappa statistic, area under the precision-recall curve (AUPRC), area under the receiver operating characteristic curve (AUROC), and Matthews correlation coefficient (MCC).ResultsTo address challenges in clinical subclassification, a 5-class classification model was initially applied; the model achieved moderate agreement. A more refined 7-class model was subsequently developed, which outperformed the 5-class classification model. The enhanced subclassification significantly improved classification performance, as evidenced by the superior AUROC and AUPRC values of the 7-class model.DiscussionThis study highlights that DL models for scoring liver fibrosis can support expert pathologists in staging liver fibrosis in preclinical animal studies.https://www.frontiersin.org/articles/10.3389/fmed.2025.1629036/fullartificial intelligencedeep learningmetabolic dysfunction-associated steatohepatitisliver fibrosishistopathology
spellingShingle Soo Min Ko
Jae-ik Shin
Jae-ik Shin
Yiyu Hong
Hyunji Kim
Insuk Sohn
Ji-Young Lee
Hyo-Jeong Han
Da Som Jeong
Yerin Lee
Woo-Chan Son
Deep learning-based method for grading histopathological liver fibrosis in rodent models of metabolic dysfunction-associated steatohepatitis
Frontiers in Medicine
artificial intelligence
deep learning
metabolic dysfunction-associated steatohepatitis
liver fibrosis
histopathology
title Deep learning-based method for grading histopathological liver fibrosis in rodent models of metabolic dysfunction-associated steatohepatitis
title_full Deep learning-based method for grading histopathological liver fibrosis in rodent models of metabolic dysfunction-associated steatohepatitis
title_fullStr Deep learning-based method for grading histopathological liver fibrosis in rodent models of metabolic dysfunction-associated steatohepatitis
title_full_unstemmed Deep learning-based method for grading histopathological liver fibrosis in rodent models of metabolic dysfunction-associated steatohepatitis
title_short Deep learning-based method for grading histopathological liver fibrosis in rodent models of metabolic dysfunction-associated steatohepatitis
title_sort deep learning based method for grading histopathological liver fibrosis in rodent models of metabolic dysfunction associated steatohepatitis
topic artificial intelligence
deep learning
metabolic dysfunction-associated steatohepatitis
liver fibrosis
histopathology
url https://www.frontiersin.org/articles/10.3389/fmed.2025.1629036/full
work_keys_str_mv AT soominko deeplearningbasedmethodforgradinghistopathologicalliverfibrosisinrodentmodelsofmetabolicdysfunctionassociatedsteatohepatitis
AT jaeikshin deeplearningbasedmethodforgradinghistopathologicalliverfibrosisinrodentmodelsofmetabolicdysfunctionassociatedsteatohepatitis
AT jaeikshin deeplearningbasedmethodforgradinghistopathologicalliverfibrosisinrodentmodelsofmetabolicdysfunctionassociatedsteatohepatitis
AT yiyuhong deeplearningbasedmethodforgradinghistopathologicalliverfibrosisinrodentmodelsofmetabolicdysfunctionassociatedsteatohepatitis
AT hyunjikim deeplearningbasedmethodforgradinghistopathologicalliverfibrosisinrodentmodelsofmetabolicdysfunctionassociatedsteatohepatitis
AT insuksohn deeplearningbasedmethodforgradinghistopathologicalliverfibrosisinrodentmodelsofmetabolicdysfunctionassociatedsteatohepatitis
AT jiyounglee deeplearningbasedmethodforgradinghistopathologicalliverfibrosisinrodentmodelsofmetabolicdysfunctionassociatedsteatohepatitis
AT hyojeonghan deeplearningbasedmethodforgradinghistopathologicalliverfibrosisinrodentmodelsofmetabolicdysfunctionassociatedsteatohepatitis
AT dasomjeong deeplearningbasedmethodforgradinghistopathologicalliverfibrosisinrodentmodelsofmetabolicdysfunctionassociatedsteatohepatitis
AT yerinlee deeplearningbasedmethodforgradinghistopathologicalliverfibrosisinrodentmodelsofmetabolicdysfunctionassociatedsteatohepatitis
AT woochanson deeplearningbasedmethodforgradinghistopathologicalliverfibrosisinrodentmodelsofmetabolicdysfunctionassociatedsteatohepatitis