Dataset Information

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

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.

SUBMITTER: Roy M

PROVIDER: S-EPMC7502534 | biostudies-literature | 2020 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

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

Roy Mousumi M Wang Fusheng F Vo Hoang H Teng Dejun D Teodoro George G Farris Alton B AB Castillo-Leon Eduardo E Vos Miriam B MB Kong Jun J

Laboratory investigation; a journal of technical methods and pathology 20200713 10

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 ...[more]

PMID: 32661341

Similar Datasets

Project description:Background Advanced confounder-corrected chemical shift-encoded MRI-derived proton density fat fraction (PDFF) is a leading parameter for fat fraction quantification in nonalcoholic fatty liver disease (NAFLD). Because of the limited availability of this MRI technique, there is a need to develop and validate alternative parameters to assess liver fat. Purpose To assess relationship of quantitative US parameters to MRI PDFF and to develop multivariable quantitative US models to detect hepatic steatosis and quantify hepatic fat. Materials and Methods Adults with known NAFLD or who were suspected of having NAFLD were prospectively recruited between August 2015 and February 2019. Participants underwent quantitative US and chemical shift-encoded MRI liver examinations. Liver biopsies were performed if clinically indicated. The correlation between seven quantitative US parameters and MRI PDFF was evaluated. By using leave-one-out cross validation, two quantitative US multivariable models were evaluated: a classifier to differentiate participants with NAFLD versus participants without NAFLD and a fat fraction estimator. Classifier performance was summarized by area under the receiver operating characteristic curve and area under the precision-recall curve. Fat fraction estimator performance was evaluated by correlation, linearity, and bias. Results Included were 102 participants (mean age, 52 years ± 13 [standard deviation]; 53 women), 78 with NAFLD (MRI PDFF ≥ 5%). A two-variable classifier yielded a cross-validated area under the receiver operating characteristic curve of 0.89 (95% confidence interval: 0.82, 0.96) and an area under the precision-recall curve of 0.96 (95% confidence interval: 0.93, 0.99). The cross-validated fat fraction predicted by a two-variable fat fraction estimator was correlated with MRI PDFF (Spearman ρ = 0.82 [P < .001]; Pearson r = 0.76 [P < .001]). The mean bias was 0.02% (P = .97), and 95% limits of agreement were ±12.0%. The predicted fat fraction was linear with MRI PDFF (R 2 = 0.63; slope, 0.69; intercept, 4.3%) for MRI PDFF of 34% or less. Conclusion A multivariable quantitative US approach yielded excellent correlation with MRI proton density fat fraction for hepatic steatosis assessment in nonalcoholic fatty liver disease. © RSNA, 2020 Online supplemental material is available for this article.

Project description:Hepatic steatosis develops after liver transplantation (LT) in 30% of adults, and nonalcoholic fatty liver disease (NAFLD) is the most common chronic liver disease in nontransplanted children. However, posttransplant steatosis has been minimally studied in pediatric LT recipients. We explored the prevalence, persistence, and association with chronic liver damage of hepatic steatosis in these children. In this single-center study of pediatric patients transplanted 1988-2015 (n?=?318), 31% of those with any posttransplant biopsy (n?=?271) had???1 biopsy with steatosis. Median time from transplant to first biopsy with steatosis was 0.8 months (interquartile range [IQR], 0.3-6.5 months) and to last biopsy with steatosis was 5.5 months (IQR, 1.0-24.5 months); 85% of patients with steatosis also had for-cause biopsies without steatosis. All available for-cause biopsies were re-evaluated (n?=?104). Of 9 biopsies that could be interpreted as nonalcoholic steatohepatitis (NASH)/borderline NASH, with steatosis plus inflammation or ballooning, 8 also had features of cholestasis or rejection. Among 70 patients with surveillance biopsies 3.6-20.0 years after transplant, only 1 overweight adolescent had a biopsy with NAFLD (grade 1 steatosis, mild inflammation, no ballooning or fibrosis)-despite a 30% prevalence of overweight/obesity in the cohort and 27% with steatosis on previous for-cause biopsy. Steatosis on preceding for-cause biopsy was not associated with portal (P?=?0.49) or perivenular fibrosis (P?=?0.85) on surveillance biopsy. Hepatic steatosis commonly develops early after transplant in children and adolescents, but it rarely persists. Biopsies that did have steatosis with NASH characteristics were all for-cause, mostly in patients with NAFLD risk factors and/or confounding causes of liver damage. Prospective studies that follow children into adulthood will be needed to evaluate if and when hepatic steatosis presents a longterm risk for pediatric LT recipients. Liver Transplantation 23 957-967 2017 AASLD.

Dataset Information

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

Publications

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

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets