Artificial Intelligence-assisted Digital Pathology for Non-alcoholic Steatohepatitis: Current Status and Future Directions

Overview

Journal J Hepatol

Publisher Elsevier

Specialty Gastroenterology

Date 2023 Oct 25

PMID 37879461

Authors

Vlad Ratziu

Marcus Hompesch

Mathieu Petitjean

Cindy Serdjebi

Janani S Iyer

Anil V Parwani

Dean Tai

Elisabetta Bugianesi

Kenneth Cusi

Scott L Friedman

Eric Lawitz

Manuel Romero-Gomez

Detlef Schuppan

Rohit Loomba

Valerie Paradis

Cynthia Behling

Arun J Sanyal

Affiliations

Soon will be listed here.

Abstract

The worldwide prevalence of non-alcoholic steatohepatitis (NASH) is increasing, causing a significant medical burden, but no approved therapeutics are currently available. NASH drug development requires histological analysis of liver biopsies by expert pathologists for trial enrolment and efficacy assessment, which can be hindered by multiple issues including sample heterogeneity, inter-reader and intra-reader variability, and ordinal scoring systems. Consequently, there is a high unmet need for accurate, reproducible, quantitative, and automated methods to assist pathologists with histological analysis to improve the precision around treatment and efficacy assessment. Digital pathology (DP) workflows in combination with artificial intelligence (AI) have been established in other areas of medicine and are being actively investigated in NASH to assist pathologists in the evaluation and scoring of NASH histology. DP/AI models can be used to automatically detect, localise, quantify, and score histological parameters and have the potential to reduce the impact of scoring variability in NASH clinical trials. This narrative review provides an overview of DP/AI tools in development for NASH, highlights key regulatory considerations, and discusses how these advances may impact the future of NASH clinical management and drug development. This should be a high priority in the NASH field, particularly to improve the development of safe and effective therapeutics.

Citing Articles

Revolutionizing MASLD: How Artificial Intelligence Is Shaping the Future of Liver Care.

Pugliese N, Bertazzoni A, Hassan C, Schattenberg J, Aghemo A Cancers (Basel). 2025; 17(5).

PMID: 40075570 PMC: 11899536. DOI: 10.3390/cancers17050722.

Metabolic dysfunction-associated steatotic liver disease in adults.

Huang D, Wong V, Rinella M, Boursier J, Lazarus J, Yki-Jarvinen H Nat Rev Dis Primers. 2025; 11(1):14.

PMID: 40050362 DOI: 10.1038/s41572-025-00599-1.

The evolving role of liver biopsy: Current applications and future prospects.

Gopal P, Hu X, Robert M, Zhang X Hepatol Commun. 2025; 9(1.

PMID: 39774070 PMC: 11717517. DOI: 10.1097/HC9.0000000000000628.

Advancements in Artificial Intelligence-Enhanced Imaging Diagnostics for the Management of Liver Disease-Applications and Challenges in Personalized Care.

Nishida N Bioengineering (Basel). 2025; 11(12.

PMID: 39768061 PMC: 11673237. DOI: 10.3390/bioengineering11121243.

Hepatic Steatosis Analysis in Metabolic Dysfunction-Associated Steatotic Liver Disease Based on Artificial Intelligence.

Wang X, Song Y, Jin R, Wang Z, Li X, Yang Q Diagnostics (Basel). 2025; 14(24.

PMID: 39767250 PMC: 11675354. DOI: 10.3390/diagnostics14242889.

References

van den Hoek A, de Jong J, Worms N, van Nieuwkoop A, Voskuilen M, Menke A . Diet and exercise reduce pre-existing NASH and fibrosis and have additional beneficial effects on the vasculature, adipose tissue and skeletal muscle via organ-crosstalk. Metabolism. 2021; 124:154873. DOI: 10.1016/j.metabol.2021.154873. View

Tai D, Tan N, Xu S, Kang C, Chia S, Cheng C . Fibro-C-Index: comprehensive, morphology-based quantification of liver fibrosis using second harmonic generation and two-photon microscopy. J Biomed Opt. 2009; 14(4):044013. DOI: 10.1117/1.3183811. View

Kleiner D, Brunt E, Van Natta M, Behling C, Contos M, Cummings O . Design and validation of a histological scoring system for nonalcoholic fatty liver disease. Hepatology. 2005; 41(6):1313-21. DOI: 10.1002/hep.20701. View

Ratziu V, Francque S, Sanyal A . Breakthroughs in therapies for NASH and remaining challenges. J Hepatol. 2022; 76(6):1263-1278. DOI: 10.1016/j.jhep.2022.04.002. View

Taylor R, Taylor R, Bayliss S, Hagstrom H, Nasr P, Schattenberg J . Association Between Fibrosis Stage and Outcomes of Patients With Nonalcoholic Fatty Liver Disease: A Systematic Review and Meta-Analysis. Gastroenterology. 2020; 158(6):1611-1625.e12. DOI: 10.1053/j.gastro.2020.01.043. View

Chang P, Goh G, Leow W, Shen L, Lim K, Tan C . Second harmonic generation microscopy provides accurate automated staging of liver fibrosis in patients with non-alcoholic fatty liver disease. PLoS One. 2018; 13(6):e0199166. PMC: 6010245. DOI: 10.1371/journal.pone.0199166. View

Ratziu V, Friedman S . Why Do So Many Nonalcoholic Steatohepatitis Trials Fail?. Gastroenterology. 2020; 165(1):5-10. DOI: 10.1053/j.gastro.2020.05.046. View

Ramot Y, Deshpande A, Morello V, Michieli P, Shlomov T, Nyska A . Microscope-Based Automated Quantification of Liver Fibrosis in Mice Using a Deep Learning Algorithm. Toxicol Pathol. 2021; 49(5):1126-1133. DOI: 10.1177/01926233211003866. View

Mostaco-Guidolin L, Rosin N, Hackett T . Imaging Collagen in Scar Tissue: Developments in Second Harmonic Generation Microscopy for Biomedical Applications. Int J Mol Sci. 2017; 18(8). PMC: 5578161. DOI: 10.3390/ijms18081772. View

10.

Wang Y, Wong G, He F, Sun J, Chan A, Yang J . Quantifying and monitoring fibrosis in non-alcoholic fatty liver disease using dual-photon microscopy. Gut. 2019; 69(6):1116-1126. DOI: 10.1136/gutjnl-2019-318841. View

11.

Perez-Bueno F, Vega M, Sales M, Aneiros-Fernandez J, Naranjo V, Molina R . Blind color deconvolution, normalization, and classification of histological images using general super Gaussian priors and Bayesian inference. Comput Methods Programs Biomed. 2021; 211:106453. DOI: 10.1016/j.cmpb.2021.106453. View

12.

Jensen V, Tveden-Nyborg P, Zacho-Rasmussen C, Quaade M, Ipsen D, Hvid H . Variation in diagnostic NAFLD/NASH read-outs in paired liver samples from rodent models. J Pharmacol Toxicol Methods. 2019; 101:106651. DOI: 10.1016/j.vascn.2019.106651. View

13.

Liu F, Goh G, Tiniakos D, Wee A, Leow W, Zhao J . qFIBS: An Automated Technique for Quantitative Evaluation of Fibrosis, Inflammation, Ballooning, and Steatosis in Patients With Nonalcoholic Steatohepatitis. Hepatology. 2019; 71(6):1953-1966. DOI: 10.1002/hep.30986. View

14.

De Rudder M, Bouzin C, Nachit M, Louvegny H, Velde G, Jule Y . Automated computerized image analysis for the user-independent evaluation of disease severity in preclinical models of NAFLD/NASH. Lab Invest. 2019; 100(1):147-160. DOI: 10.1038/s41374-019-0315-9. View

15.

Nam D, Chapiro J, Paradis V, Seraphin T, Kather J . Artificial intelligence in liver diseases: Improving diagnostics, prognostics and response prediction. JHEP Rep. 2022; 4(4):100443. PMC: 8867112. DOI: 10.1016/j.jhepr.2022.100443. View

16.

Brunt E, Clouston A, Goodman Z, Guy C, Kleiner D, Lackner C . Complexity of ballooned hepatocyte feature recognition: Defining a training atlas for artificial intelligence-based imaging in NAFLD. J Hepatol. 2022; 76(5):1030-1041. PMC: 10544770. DOI: 10.1016/j.jhep.2022.01.011. View

17.

Leow W, Bedossa P, Liu F, Wei L, Lim K, Wan W . An Improved qFibrosis Algorithm for Precise Screening and Enrollment into Non-Alcoholic Steatohepatitis (NASH) Clinical Trials. Diagnostics (Basel). 2020; 10(9). PMC: 7554942. DOI: 10.3390/diagnostics10090643. View

18.

Wanless I, Nakashima E, Sherman M . Regression of human cirrhosis. Morphologic features and the genesis of incomplete septal cirrhosis. Arch Pathol Lab Med. 2000; 124(11):1599-607. DOI: 10.5858/2000-124-1599-ROHC. View

19.

Taylor-Weiner A, Pokkalla H, Han L, Jia C, Huss R, Chung C . A Machine Learning Approach Enables Quantitative Measurement of Liver Histology and Disease Monitoring in NASH. Hepatology. 2021; 74(1):133-147. PMC: 8361999. DOI: 10.1002/hep.31750. View

20.

Le M, Le D, Baez T, Wu Y, Ito T, Lee E . Global incidence of non-alcoholic fatty liver disease: A systematic review and meta-analysis of 63 studies and 1,201,807 persons. J Hepatol. 2023; 79(2):287-295. DOI: 10.1016/j.jhep.2023.03.040. View