Automated Segmentation and Morphological Characterization of Hepatic Steatosis and Correlation with Histopathology

Juan Esparza; Utsav Shrestha; David E Kleiner; James M Crawford; Jason Vanatta; Sanjaya Satapathy; Aaryani Tipirneni-Sajja

doi:10.1016/j.jceh.2022.12.003

Automated Segmentation and Morphological Characterization of Hepatic Steatosis and Correlation with Histopathology

J Clin Exp Hepatol. 2023 May-Jun;13(3):468-478. doi: 10.1016/j.jceh.2022.12.003. Epub 2022 Dec 7.

Authors

Juan Esparza¹, Utsav Shrestha¹, David E Kleiner², James M Crawford³, Jason Vanatta⁴, Sanjaya Satapathy⁵, Aaryani Tipirneni-Sajja^{1

6}

Affiliations

¹ Department of Biomedical Engineering, The University of Memphis, Memphis, TN, USA.
² Laboratory of Pathology, Center for Cancer Research, National Cancer Institute, National Institute to Health, Bethesda, MD, USA.
³ Department of Pathology and Laboratory Medicine, Donald and Barbara Zucker School of Medicine at Hofstra/Northwell, Hempstead, NY, USA.
⁴ Department of Surgery, University of Tennessee Health and Science Center, Memphis, TN, USA.
⁵ Liver Transplantation, North Shore University Hospital/Northwell Health, Manhasset, NY, USA.
⁶ Department of Diagnostic Imaging, St. Jude Children's Research Hospital, Memphis, TN, USA.

PMID: 37250872
PMCID: PMC10213977 (available on 2024-05-01)
DOI: 10.1016/j.jceh.2022.12.003

Abstract

Background/objectives: Prevalence of nonalcoholic fatty liver disease (NAFLD) has increased to 25% of the world population. Hepatic steatosis is a hallmark feature of NAFLD and is assessed histologically using visual and ordinal fat grading criteria (0-3) from the Nonalcoholic Steatohepatitis (NASH) Clinical Research Network (CRN) scoring system. The purpose of this study is to automatically segment and extract morphological characteristics and distributions of fat droplets (FDs) on liver histology images and find associations with severity of steatosis.

Methods: A previously published human cohort of 68 NASH candidates was graded for steatosis by an experienced pathologist using the Fat CRN grading system. The automated segmentation algorithm quantified fat fraction (FF) and fat-affected hepatocyte ratio (FHR), extracted fat morphology by calculating radius and circularity of FDs, and examined FDs distribution and heterogeneity using nearest neighbor distance and regional isotropy.

Results: Regression analysis and Spearman correlation (ρ) yielded high correlations for radius (R² = 0.86, ρ = 0.72), nearest neighbor distance (R² = 0.82, ρ = -0.82), regional isotropy (R² = 0.84, ρ = 0.74), and FHR (R² = 0.90, ρ = 0.85), and low correlation for circularity (R² = 0.48, ρ = -0.32) with FF and pathologist grades, respectively. FHR showed a better distinction between pathologist Fat CRN grades compared to conventional FF measurements, making it a potential surrogate measure for Fat CRN scores. Our results showed variation in distribution of morphological features and steatosis heterogeneity within the same patient's biopsy sample as well as between patients of similar FF.

Conclusions: The fat percentage measurements, specific morphological characteristics, and patterns of distribution quantified with the automated segmentation algorithm showed associations with steatosis severity; however, future studies are warranted to evaluate the clinical significance of these steatosis features in progression of NAFLD and NASH.

Keywords: fat fraction; liver; morphometry; segmentation; steatosis.