3
|
Roy M, Wang F, Vo H, Teng D, Teodoro G, Farris AB, Castillo-Leon E, Vos MB, Kong J. Deep-learning-based accurate hepatic steatosis quantification for histological assessment of liver biopsies. J Transl Med 2020; 100:1367-1383. [PMID: 32661341 PMCID: PMC7502534 DOI: 10.1038/s41374-020-0463-y] [Citation(s) in RCA: 32] [Impact Index Per Article: 8.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/30/2020] [Revised: 01/30/2020] [Accepted: 06/22/2020] [Indexed: 12/17/2022] Open
Abstract
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.
Collapse
Affiliation(s)
- Mousumi Roy
- Department of Computer Science, Stony Brook University, Stony Brook, NY, 11794, USA
| | - Fusheng Wang
- Department of Computer Science, Stony Brook University, Stony Brook, NY, 11794, USA.
- Department of Biomedical Informatics, Stony Brook University, Stony Brook, NY, 11794, USA.
| | - Hoang Vo
- Department of Computer Science, Stony Brook University, Stony Brook, NY, 11794, USA
| | - Dejun Teng
- Department of Computer Science, Stony Brook University, Stony Brook, NY, 11794, USA
| | - George Teodoro
- Department of Computer Science, Federal University of Minas Gerais, Belo Horizonte, MG, 31270, USA
| | - Alton B Farris
- Department of Pathology and Laboratory Medicine, Emory University School of Medicine, Atlanta, GA, 30322, USA
| | - Eduardo Castillo-Leon
- Division of Gastroenterology, Hepatology, and Nutrition, Department of Pediatrics, Emory University, Atlanta, GA, 30322, USA
| | - Miriam B Vos
- Division of Gastroenterology, Hepatology, and Nutrition, Department of Pediatrics, Emory University, Atlanta, GA, 30322, USA
- Children's Healthcare of Atlanta, Atlanta, GA, 30322, USA
| | - Jun Kong
- Department of Mathematics and Statistics, Georgia State University, Atlanta, GA, 30303, USA.
- Department of Computer Science, Emory University, Atlanta, GA, 30322, USA.
- Department of Biomedical Informatics, Emory University, Atlanta, GA, 30322, USA.
- Winship Cancer Institute, Emory University, Atlanta, GA, 30322, USA.
| |
Collapse
|