A Novel Automatic Digital Algorithm that Accurately Quantifies Steatosis in NAFLD on Histopathological Whole‐Slide Images

Abstract

BackgroundAccurate assessment of hepatic steatosis is a key to grade disease severity in non‐alcoholic fatty liver disease (NAFLD).MethodsWe developed a digital automated quantification of steatosis on whole‐slide images (WSIs) of liver tissue and performed a validation study. Hematoxylin–eosin stained liver tissue slides were digitally scanned, and steatotic areas were manually annotated. We identified thresholds for size and roundness parameters by logistic regression to discriminate steatosis from surrounding liver tissue. The resulting algorithm produces a steatosis proportionate area (SPA; ratio of steatotic area to total tissue area described as percentage). The software can be implemented as a Java plug‐in in FIJI, in which digital WSI can be processed automatically using the Pathomation extension.ResultsWe obtained liver tissue specimens from 61 NAFLD patients and 18 controls. The area under the curve of correctly classified steatosis by the algorithm was 0.970 (95% CI 0.968–0.973), P < 0.001. Accuracy of the algorithm was 91.9%, with a classification error of 8.1%. SPA correlated significantly with steatosis grade (Rs = 0.845, CI: 0.749–0.902, P < 0.001) and increased significantly with each individual steatosis grade, except between Grade 2 and 3.ConclusionsWe have developed a novel digital analysis algorithm that accurately quantifies steatosis on WSIs of liver tissue. This algorithm can be incorporated when quantification of steatosis is warranted, such as in clinical trials studying efficacy of new therapeutic interventions in NAFLD. © 2019 The Authors. Cytometry Part B: Clinical Cytometry published by Wiley Periodicals, Inc. on behalf of International Clinical Cytometry Society.

Deep learning quantification of percent steatosis in donor liver biopsy frozen sections

“…To attempt to overcome inter-observer variability, there have been multiple prior efforts to automate quantification of liver steatosis [52] , [53] , [54] , [55] , [56] , [57] . These methods usually measure steatosis by the fraction/percent of the image area that is occupied by fat droplets.…”

Whole Slide Imaging and Its Applications to Histopathological Studies of Liver Disorders

“…As noted for liver fibrosis, technological improvements in slide scanning, digital image analysis, and development of algorithms have been allowing a more objective and comprehensive evaluation of hepatic steatosis in human samples (68)(69)(70)(71). Roy and colleagues propose a more precise image analysis method to recognize, quantify steatosis areas in wholeslide liver tissue microscopy images (70).…”

“…This method consists of whole tissue component extraction, steatosis detection, and segregation of the overlapped steatosis component. More recently, a quantification algorithm was developed to detect potential steatotic hepatocytes in whole slide images and distinguish these images from similar objects, such as blood vessels, bile ducts, and tissue tearing (71).…”

Issue Highlights – September 2020

“…They explore the diagnostic utility of three shape‐specific parameters for branching classification of glands; the chord intersection ratio, convexity ratio, and maximum concave area ratio. This is a developing field that has seen an increasing number of geometric and spatial imaging methods offering new approaches for pattern‐based analysis (29‐31). This and other similar approaches promises to integrate traditional pathology with the quantitative digital analysis and interpretation (29).…”