AutoML Radiomics-Based Classification for Opportunistic Osteoporosis Screening with Lumbar Fat and Water using IDEAL-IQ MRI

Motivation: Could lumbar fat and water MRI be as an opportunistic screening tool?Goal(s): To develop autoML radiomics-Based Classification for osteoporosis prediction using lumbar fat and water MRI. Approach: A TPOP-radiomics classification model was trained using lumbar fat and water images obtained through the IDEAL-IQ method in normal and osteoporosis patients identified by DeXA. Three datasets of radiomics features were used, categorized based on their dimension (2D, 3D, and projection map)Results: Our results indicate that the best model from the AutoML process demonstrated mean sensitivity of 0.745 and mean specificity of 0.758 in distinguishing between normal and osteroporosis. Impact: Because osteoporosis is often considered a 'silent' disease, routine IDEAL-IQ lumbar scans have the potential to serve as an opportunistic screening tool for reducing the risk of fragility fractures, which are associated with morbidity and mortality.