Utility of AI digital pathology as an aid for pathologists scoring fibrosis in MASH.

Autor: Abdurrachim D; Quantitative Biosciences, MSD, Singapore. Electronic address: desiree.abdurrachim@msd.com., Lek S; HistoIndex Pte. Ltd., Singapore., Lin Ong CZ; Quantitative Biosciences, MSD, Singapore., Wong CK; Quantitative Biosciences, MSD, Singapore., Zhou Y; Quantitative Biosciences, MSD, Singapore., Wee A; Department of Pathology, National University Hospital, Singapore., Soon G; Department of Pathology, National University Hospital, Singapore., Kendall TJ; Centre for Inflammation Research, Institute for Regeneration and Repair, University of Edinburgh, United Kingdom., Idowu MO; Department of Pathology, Virginia Commonwealth University School of Medicine, Richmond, VA, USA., Hendra C; Quantitative Biosciences, MSD, Singapore., Saigal A; Cardiometabolic Diseases, Merck & Co., Inc., South San Francisco, CA, USA., Krishnan R; Global Clinical Trial Organization, MSD, UK., Chng E; HistoIndex Pte. Ltd., Singapore., Tai D; HistoIndex Pte. Ltd., Singapore., Ho G; HistoIndex Pte. Ltd., Singapore., Forest T; Non-clinical Drug Safety, Merck & Co., Inc., West Point, PA, USA., Raji A; Global Clinical Development, Merck & Co., Inc., Rahway, NJ, USA., Talukdar S; Cardiometabolic Diseases, Merck & Co., Inc., South San Francisco, CA, USA., Chin CL; Cardiometabolic Diseases, Merck & Co., Inc., South San Francisco, CA, USA., Baumgartner R; Biostatistics and Research Decision Sciences, Merck & Co., Inc., Rahway, NJ, USA., Engel SS; Global Clinical Development, Merck & Co., Inc., Rahway, NJ, USA., Bakar Ali AA; Quantitative Biosciences, MSD, Singapore., Kleiner DE; Laboratory of Pathology, National Cancer Institute, NIH, USA., Sanyal AJ; Stravitz-Sanyal Institute for Liver Disease and Metabolic Health, Virginia Commonwealth University School Of Medicine, Richmond, VA, USA.
Jazyk: angličtina
Zdroj: Journal of hepatology [J Hepatol] 2024 Nov 27. Date of Electronic Publication: 2024 Nov 27.
DOI: 10.1016/j.jhep.2024.11.032
Abstrakt: Background & Aims: Intra and inter-pathologist variability poses a significant challenge in metabolic dysfunction-associated steatohepatitis (MASH) biopsy evaluation, leading to suboptimal selection of patients and confounded assessment of histological response in clinical trials. We evaluated the utility of an artificial intelligence (AI) digital pathology (DP) platform to aid pathologists improve the reliability of fibrosis staging.
Methods: A total of 120 digitized histology slides from two trials (NCT03517540, NCT03912532) were analysed by four expert hepatopathologists, with and without AI-assistance in a randomized, cross-over design. We utilized the HistoIndex AI DP platform, consisting of unstained second harmonic generation/two photon excitation fluorescence (SHG/TPEF) images and AI quantitative fibrosis (qF) values.
Results: AI-assistance significantly improved inter-pathologist kappa for fibrosis (F)-staging, particularly for early fibrosis (F0-F2), with reduced variance around the median reads. Intra-pathologist kappa was unchanged. AI-assistance increased pathologist concordance for identifying clinical trial inclusion subjects (F2-F3) from 45% to 71%, exclusion subjects (F0/F1/F4) from 38% to 55%, and evaluation of fibrosis response to treatment from 49% to 61%. SHG/TPEF images, qFibrosis continuous values, and qF-stage were considered useful by at least 3 out of 4 pathologists in 83%, 55%, and 38% cases, respectively. In the context of a clinical trial, the increase in inter-pathologist concordance in this study is modeled to result in a ∼25% reduction in the potential need for adjudication as well as a ∼50% increase in the study power.
Conclusions: The use of AI DP enhances inter-rater reliability of fibrosis staging for MASH. This indicates that the SHG/TPEF-based AI DP tool is useful for assisting pathologists in assessing fibrosis, thereby enhancing clinical trial efficiency and reliability of fibrosis readouts in response to treatments.
Competing Interests: Declaration of Competing Interest DA, CKW, AS, RK, TF, AR, ST, CLC, RB, SSE, AABA are employees and stockholders of Merck Sharp & Dohme LLC, a subsidiary of Merck & Co., Inc., Rahway, NJ, USA at the time of the study. CZLO, YZ, CH, are employees of Merck Sharp & Dohme LLC, a subsidiary of Merck & Co., Inc., Rahway. SL, EC, DT, GH are employees of HistoIndex Pte. Ltd. AJS has served as a consultant to Histoindex, Gilead, Intercept, Merck, Eli Lilly, Novo Nordisk, Pfizer, Astra Zeneca, Boehringer Ingelhiem, Madrigal, Novartis, Genentech, Roche, Hanmi, Sequana, Bard, Alnylam, Regeneron, Poxel, Surrozen, Avant Sante, Amgen, Path AI, Myovant, Aligos, Promed, Rona. His institution has received grants from Gilead, Madrigal, Salix, Novo Nordisk, Eli Lilly, Hanmi, Bristol Myers Squibb, Echosens. He has stock options in Genfit, Tiziana, Durect, Inversago, Indalo, Northsea, Rivus. He received royalties from Wolter Kluwers and Elsevier. MOI has served as a consultant for, or received speakers' fees from Path AI, Clinnovate Health, and Target RWE. He has received grants from the National Institutes of Health (NIH) and the National Cancer Institute (NCI). TJK has served as a consultant for, or received speakers' fees from Resolution Therapeutics, Clinnovate Health, HistoIndex, Servier Laboratories, Fibrofind, Kynos Therapeutics, Perspectum Diagnostics, Concept Life Sciences, Jazz Pharmaceuticals and Incyte Corporation. AW, GS, MOI and TJK received a fee-for-service from Clinnovate Health as expert pathologists in this study. DEK discloses no conflict of interest.
(Copyright © 2024. Published by Elsevier B.V.)
Databáze: MEDLINE
Externí odkaz: