Image-based Disease-wide Association Study via Self-supervised Learning links Abdominal MRI Features to 158 Diseases
Seyed Rasoul Mousavi, Jatin Arora, Richa Agarwal, Anja Fischer, Stefanie Mueller, Zhihao Ding, Johann de Jong, Ke Yuan
This paper uses self-supervised learning on abdominal MRI data to identify associations with 158 diseases, including those not directly related to abdominal anatomy, and shows improved performance over standard biomarkers for MASH.
bioRxiv · Jul 28, 2026 · PreprintBioinformatics