Association between myosteatosis and impaired glucose metabolism: A deep learning whole-body MRI population phenotyping approach

Diabetes remains a major challenge for healthcare systems, making screening and early detection desirable. We used deep learning to quantify myosteatosis as 1) skeletal muscle fat fraction (SMFF) and 2) intramuscular adipose tissue (IMAT) normalized for SM mass and assessed their association with impaired glucose metabolism. SMFF had a higher discriminatory capacity for impaired glucose metabolism than IMAT. In multivariable logistic regression adjusted for baseline demographics and cardiometabolic risk factors, only SMFF remained an independent predictor of impaired glucose metabolism. Deep learning-based MR phenotyping enables opportunistic screening of myosteatosis and may identify individuals at high risk for impaired glucose metabolism.