Keywords: Analysis/Processing, Diabetes
Motivation: Medical research indicates that the composition of skeletal muscle, especially in certain muscle groups, could offer new insights into diabetes risk.
Goal(s): Calculate muscle features from MRI and identify their value as biomarkers for diabetes.
Approach: The NAKO cohort consists of 28,077 subjects with MR images and tabular features. Muscle features were obtained from segmented gluteus, psoas and thigh muscles in T1W Dixon MRI. An XGBoost model predicted diabetes from 213 features, like BMI or MR-based muscle features. A feature importance method assessed which input features were most important for the model’s predictions.
Results: MR-based gluteus and psoas fat fractions aid diabetes prediction.
Impact: This study shows that MR-based skeletal muscle features, particularly fat fractions of the gluteus and psoas muscles, can improve diabetes classification model’s predictions. Using several MRI-derived predictors, diabetes diagnosis may become possible purely from MRI, i.e., without targeted diabetes-specific measurements.
How to access this content:
For one year after publication, abstracts and videos are only open to registrants of this annual meeting. Registrants should use their existing login information. Non-registrant access can be purchased via the ISMRM E-Library.
After one year, current ISMRM & ISMRT members get free access to both the abstracts and videos. Non-members and non-registrants must purchase access via the ISMRM E-Library.
After two years, the meeting proceedings (abstracts) are opened to the public and require no login information. Videos remain behind password for access by members, registrants and E-Library customers.
Keywords