Genetic architecture of high-dimensional liver radiomic phenotypes and their role in common metabolic diseases

Abstract

The liver plays a central role in systemic metabolism, yet large-scale genetic studies of quantitative liver imaging phenotypes remain limited. Here, we applied deep learning-based segmentation and radiomics extraction to derive 200 well-defined liver MRI features across multiple categories and imaging contrasts in 43,176 UK Biobank participants. Association analyses revealed steatosis-independent radiomic signals predicting incident chronic liver disease beyond conventional risk factors. We conducted genome-wide association studies in 37,725 individuals and identified multiple heritable liver MRI features; joint genetic structure and pleiotropy analyses demonstrated that these radiomic traits capture complex genetic architecture beyond the extent of hepatic steatosis. These MRI features showed widespread genetic overlap with plasma proteins, metabolites, and cardiometabolic traits through shared genetic loci and genetic correlations independent of adiposity. We identified putative causal links between liver MRI traits and cardiometabolic and liver-related outcomes, as well as evidence for pathway-specific imaging biomarkers to track activity of hepatically-influenced therapeutics.