AI Body Composition MRI Analysis Predicts Cardiometabolic Disease Risk

Risk assessment often relies on body mass index, which overlooks muscle quality and regional fat distribution. This limits precision prevention and treatment planning across inpatient and outpatient care. To help address this challenge, investigators have developed an artificial intelligence approach that extracts clinically relevant body composition data from whole-body magnetic resonance imaging (MRI) for risk prediction.

Researchers at University Medical Center Freiburg in Germany created an open‑source, fully automated deep learning framework for whole‑body MRI. The system quantifies subcutaneous and visceral adipose tissue, skeletal muscle, skeletal muscle fat fraction, and intramuscular adipose tissue. It normalizes each measure by age, sex, and height to generate z‑scores that indicate deviation from population reference values.

In a retrospective study, the team analyzed scans from 66,608 individuals who participated in the UK Biobank and the German National Cohort between April 2014 and May 2022. The cohort had a mean age of 57.7 years, included 34,443 males, and had a mean body mass index of 26.2. The investigators categorized z‑scores as low, middle, or high and assessed their prognostic value for incident diabetes, major adverse cardiovascular events, and all‑cause mortality.

High visceral fat was associated with a 2.26‑fold increased risk of future diabetes. High intramuscular fat was associated with a 1.54‑fold increased risk of future major cardiovascular events. Low skeletal muscle was associated with a 1.44‑fold higher all‑cause mortality beyond cardiometabolic risk factors, underscoring the prognostic importance of both muscle quantity and quality.

The findings were published in Radiology. The group also released a web‑based, age‑, sex‑, and height‑adjusted body composition z‑score calculator to support research comparability and accelerate clinical translation. The authors noted that a dedicated whole‑body MRI exam is not always required, because comparable information can be extracted opportunistically from existing CT or MRI studies; future work will validate reference curves in clinical populations and develop disease‑specific values, including in oncology and patients receiving glucagon‑like peptide‑1 (GLP‑1) agonists.

“It's not only how much muscle you have, but also it's the quality of that muscle. Knowing the volume of intramuscular fat gives us a window into muscle quality that other methods like BMI, bioelectrical impedance analysis, or DEXA can't easily provide,” stated Matthias Jung, M.D., from the Department of Diagnostic and Interventional Radiology, University Medical Center Freiburg.

“Adjusting for confounding factors is critical for improving screening accuracy and tailoring treatment decisions. This tool has the potential to identify whether an individual's body composition puts them at greater risk for metabolic disease compared to their age‑matched peers,” said Jakob Weiss, M.D., Ph.D., radiologist in the Department of Diagnostic and Interventional Radiology at University Medical Center Freiburg in Germany.

Related Links
University Medical Center Freiburg