Exome-wide association analysis of CT imaging-derived hepatic fat in a medical biobank

A Cloud-Based System for Automated AI Image Analysis and Reporting

Although numerous AI algorithms have been published, the relatively small number of algorithms used clinically is partly due to the difficulty of implementing AI seamlessly into the clinical workflow for radiologists and for their healthcare enterprise. The authors developed an AI orchestrator to facilitate the deployment and use of AI tools in a large multi-site university healthcare system and used it to conduct opportunistic screening for hepatic steatosis. During the 60-day study period, 991 abdominal CTs were processed at multiple different physical locations with an average turnaround time of 2.8 min. Quality control images and AI results were fully integrated into the existing clinical workflow. All input into and output from the server was in standardized data formats. The authors describe the methodology in detail; this framework can be adapted to integrate any clinical AI algorithm.

Human APOE4 Protects High-Fat and High-Sucrose Diet Fed Targeted Replacement Mice against Fatty Liver Disease Compared to APOE3

Recent genome- and exome-wide association studies suggest that the human APOE ε4 allele protects against non-alcoholic fatty liver disease (NAFLD), while ε3 promotes hepatic steatosis and steatohepatitis. The present study aimed at examining the APOE genotype-dependent development of fatty liver disease and its underlying mechanisms in a targeted replacement mouse model. Male mice expressing the human APOE3 or APOE4 protein isoforms on a C57BL/6J background and unmodified C57BL/6J mice were chronically fed a high-fat and high-sucrose diet to induce obesity. After 7 months, body weight gain was more pronounced in human APOE than endogenous APOE expressing mice with elevated plasma biomarkers suggesting aggravated metabolic dysfunction. APOE3 mice exhibited the highest liver weights and, compared to APOE4, massive hepatic steatosis. An untargeted quantitative proteome analysis of the liver identified a high number of proteins differentially abundant in APOE3 versus APOE4 mice. The majority of the higher abundant proteins in APOE3 mice could be grouped to inflammation and damage-associated response, and lipid storage, amongst others. Results of the targeted qRT-PCR and Western blot analyses contribute to the overall finding that APOE3 as opposed to APOE4 promotes hepatic steatosis, inflammatory- and damage-associated response signaling and fibrosis in the liver of obese mice. Our experimental data substantiate the observation of an increased NAFLD-risk associated with the human APOEε3 allele, while APOEε4 appears protective. The underlying mechanisms of the protection possibly involve a higher capacity of nonectopic lipid deposition in subcutaneous adipose tissue and lower hepatic pathogen recognition in the APOE4 mice.

The quest for the missing links in fatty liver genetics: Deep learning to the rescue!

Park, MacLean, et al. conduct an exome-wide association study of liver fat content in the Penn Medicine BioBank.¹ By leveraging machine learning-assisted analysis of clinical CT scans to quantify steatosis, they uncover previously undescribed liver fat-associated genetic variants.