Deep-learning-based accurate hepatic steatosis quantification for histological assessment of liver biopsies

• Published in: Laboratory investigation Vol. 100; no. 10; pp. 1367 - 1383
• Main Authors: Roy, Mousumi, Wang, Fusheng, Vo, Hoang, Teng, Dejun, Teodoro, George, Farris, Alton B., Castillo-Leon, Eduardo, Vos, Miriam B., Kong, Jun
• Format: Journal Article
• Language: English
• Published: New York Elsevier Inc 01.10.2020; Nature Publishing Group US; Nature Publishing Group
• Subjects: 14/63; 692/308/575; 692/699/1503/1607; Algorithms; Annotations; Artificial intelligence; Biopsy; Boundaries; Decision support systems; Deep Learning; Droplets; Fatty liver; Fatty Liver - diagnostic imaging; Fatty Liver - pathology; Histology; Histopathology; Humans; Image enhancement; Image Interpretation, Computer-Assisted - methods; Image Interpretation, Computer-Assisted - statistics & numerical data; Laboratory Medicine; Liver; Liver - pathology; Liver diseases; Medical imaging; Medical treatment; Medicine; Medicine & Public Health; Pathology; Patients; Pixels; Predictions; Radiographic Image Interpretation, Computer-Assisted - methods; Radiographic Image Interpretation, Computer-Assisted - statistics & numerical data; Radiology; Risk management; Software; Steatosis; technical-report; Transplantation
• ISSN: 0023-6837; 1530-0307
• DOI: 10.1038/s41374-020-0463-y

Hepatic steatosis droplet quantification with histology biopsies has high clinical significance for risk stratification and management of patients with fatty liver diseases and in the decision to use donor livers for transplantation. However, pathology reviewing processes, when conducted manually, are subject to a high inter- and intra-reader variability, due to the overwhelmingly large number and significantly varying appearance of steatosis instances. This process is challenging as there is a large number of overlapped steatosis droplets with either missing or weak boundaries. In this study, we propose a deep-learning-based region-boundary integrated network for precise steatosis quantification with whole slide liver histopathology images. The proposed model consists of two sequential steps: a region extraction and a boundary prediction module for foreground regions and steatosis boundary prediction, followed by an integrated prediction map generation. Missing steatosis boundaries are next recovered from the predicted map and assembled from adjacent image patches to generate results for the whole slide histopathology image. The resulting steatosis measures both at the pixel level and steatosis object-level present strong correlation with pathologist annotations, radiology readouts and clinical data. In addition, the segregated steatosis object count is shown as a promising alternative measure to the traditional metrics at the pixel level. These results suggest a high potential of artificial intelligence-assisted technology to enhance liver disease decision support using whole slide images. Accurate quantification of steatosis in liver biopsies is a key step in the treatment of patients with fatty liver diseases. To assist pathologists for such analysis tasks, we develop a novel deep learning-based framework to segment overlapped steatosis droplets in whole slide liver biopsy images. Quantitative measurements of steatosis at both pixel and object-level present strong correlation with clinical data, suggesting its potential for clinical decision support.