The summaries are free for public
use. The Chronic Liver Disease
Foundation will continue to add and
archive summaries of articles deemed
relevant to CLDF by the Board of
Trustees and its Advisors.
Abstract Details
Complexity of ballooned hepatocyte feature recognition: Defining a training atlas for artificial intelligence-based imaging in NAFLD
J Hepatol. 2022 Jan 25;S0168-8278(22)00024-1. doi: 10.1016/j.jhep.2022.01.011.Online ahead of print.
Elizabeth M Brunt1, Andrew D Clouston2, Zachary Goodman3, Cynthia Guy4, David E Kleiner5, Carolin Lackner6, Dina G Tiniakos7, Aileen Wee8, Matthew Yeh9, Wei Qiang Leow10, Elaine Chng11, Yayun Ren11, George Goh Boon Bee12, Elizabeth E Powell13, Mary Rinella14, Arun J Sanyal15, Brent Neuschwander-Tetri16, Zobair Younossi17, Michael Charlton18, Vlad Ratziu19, Stephen A Harrison20, Dean Tai21, Quentin M Anstee22
Author information
Department of Pathology and Immunology, Washington University School of Medicine, Saint Louis, Missouri, USA. Electronic address: ebrunt@wustl.edu.
Molecular and Cellular Pathology, University of Queensland and Envoi Specialist Pathologists, Brisbane, Australia.
Pathology Department, and Center for Liver Diseases, Inova Fairfax Hospital, Falls Church, Virginia, USA.
Division of Pathology, Duke University Medical Center, Durham, NC, USA.
Laboratory of Pathology; Center for Cancer Research, National Cancer Institute, National Institutes of Health, Bethesda, Maryland, USA.
Institute of Pathology, Medical University of Graz, Graz, Austria.
Translational and Clinical Research Institute, Faculty of Medical Sciences, Newcastle University, Newcastle upon Tyne, UK; Dept of Pathology, Aretaieion Hospital, National and Kapodistrian University of Athens, Greece.
Department of Pathology, Yong Loo Lin School of Medicine, National University of Singapore, National University Hospital, Singapore.
Department of Pathology, University of Washington, Seattle, Washington, USA.
Department of Anatomical Pathology, Singapore General Hospital, Singapore & Duke-NUS Medical School, Singapore.
HistoIndex Pte Ltd, Singapore.
Department of Gastroenterology and Hepatology, Singapore General Hospital, Singapore.
Centre for Liver Disease Research, Faculty of Medicine, University of Queensland, Translational Research Institute, Brisbane, Queensland, Australia; Department of Gastroenterology and Hepatology, Princess Alexandra Hospital, Brisbane, Queensland, Australia.
Division of Gastroenterology and Hepatology, Feinberg School of Medicine, Northwestern University, Chicago, USA.
Department of Internal Medicine, School of Medicine, Virginia Commonwealth University, Richmond, Virginia, USA.
Division of Gastroenterology and Hepatology, Saint Louis University, Saint Louis, Missouri, USA.
Betty and Guy Beatty Center for Integrated Research, Inova Health System, Falls Church, Virginia, USA.
Center for Liver Diseases, and Transplantation Institute, University of Chicago, Chicago, Illinois, USA.
Department of Hepatology, Sorbonne University and Pitié-Salpêtrière Hospital, Paris, France.
Pinnacle Clinical Research, San Antonio, USA; Hepatology, Radcliffe Department of Medicine, University of Oxford, Oxford, UK.
Department of Anatomical Pathology, Singapore General Hospital, Singapore & Duke-NUS Medical School, Singapore. Electronic address: dean.tai@histoindex.com.
Translational and Clinical Research Institute, Faculty of Medical Sciences, Newcastle University, Newcastle upon Tyne, UK; Newcastle NIHR Biomedical Research Centre, Newcastle upon Tyne Hospitals NHS Foundation Trust, Newcastle upon Tyne, UK. Electronic address: quentin.anstee@newcastle.ac.uk.
Abstract
Background & aims: Histologically assessed hepatocyte ballooning is a key feature discriminating non-alcoholic steatohepatitis (NASH) from steatosis (NAFL). Reliable identification underpins patient inclusion in clinical trials and serves as a key regulatory-approved surrogate endpoint for drug efficacy. High inter/intra-observer variation in ballooning measured using the NASH CRN semi-quantitative score has been reported yet no actionable solutions have been proposed.
Methods: A focused evaluation of hepatocyte ballooning recognition was conducted. Digitized slides were evaluated by 9 internationally recognized expert liver pathologists on 2 separate occasions: each pathologist independently marked every ballooned hepatocyte and later provided an overall non-NASH NAFL/NASH assessment. Interobserver variation was assessed and a 'concordance atlas' of ballooned hepatocytes generated to train second harmonic generation/two-photon excitation fluorescence imaging-based artificial intelligence (AI).
Results: The Fleiss kappa statistic for overall interobserver agreement for presence/absence of ballooning was 0.197 (95% CI 0.094-0.300), rising to 0.362 (0.258-0.465) with a ≥5-cell threshold. However, the intraclass correlation coefficient for consistency was higher (0.718 [0.511-0.900]), indicating 'moderate' agreement on ballooning burden. 133 ballooned cells were identified using a ≥5/9 majority to train AI ballooning detection (AI-pathologist pairwise concordance 19-42%, comparable to inter-pathologist pairwise concordance of between 8-75%). AI quantified change in ballooned cell burden in response to therapy in a separate slide set.
Conclusions: The substantial divergence in hepatocyte ballooning identified amongst expert hepatopathologists suggests that ballooning is a spectrum, too subjective for its presence or complete absence to be unequivocally determined as a trial endpoint. A concordance atlas may be used to train AI assistive technologies to reproducibly quantify ballooned hepatocytes that standardize assessment of therapeutic efficacy. This atlas serves as a reference standard for ongoing work to refine how ballooning is classified by both pathologists and AI.
Lay summary: For the first time, we show that, even amongst expert hepatopathologists, there is poor agreement regarding the number of ballooned hepatocytes seen on the same digitized histology images. This has important implications as the presence of ballooning is needed to establish the diagnosis of non-alcoholic steatohepatitis (NASH), and its unequivocal absence is one of the key requirements to show 'NASH resolution' to support drug efficacy in clinical trials. Artificial intelligence-based approaches may provide a more reliable way to assess the range of injury recorded as "hepatocyte ballooning".