An Anatomically Guided and Optimization-Refined Radiomics Framework for Opportunistic Osteoporosis Assessment from Lumbar Spine MRI.
Magnetic resonance imaging radiomics framework classified osteoporosis-related bone quality with 85.2% accuracy
An Anatomically Guided and Optimization-Refined Radiomics Framework for Opportunistic Osteoporosis Assessment from Lumbar Spine MRI.
Osteoporosis is a major contributor to vertebral compression fractures (vertebral compression fractures) and other skeletal complications, yet quantitative bone mineral density (bone mineral density) assessment using dual-energy X-ray absorptiometry (DEXA) is not routinely available in many spine surgery workflows.
This study proposes an anatomically guided and optimization-refined radiomics framework for opportunistic osteoporosis assessment from routine lumbar spine magnetic resonance imaging (magnetic resonance imaging).
The proposed pipeline employs a hierarchical template-matching strategy to automatically localize the L1-L4 vertebral region, followed by an optimization-based refinement procedure that adapts vertebral regions of interest (regions of interest) using intensity, texture, boundary, and geometric constraints.
Experimental results demonstrated robust and anatomically consistent vertebral localization across heterogeneous lumbar magnetic resonance imaging acquisitions.
In addition, exploratory bone mineral density regression analysis demonstrated the feasibility of estimating DEXA-derived bone mineral density directly from magnetic resonance imaging-derived radiomic features, achieving mean absolute percentage errors of approximately 15-20% across lumbar vertebral levels.
These findings suggest that anatomically guided vertebral radiomics extracted from routine lumbar spine magnetic resonance imaging contain clinically meaningful information associated with osteoporosis-related bone quality changes and may provide a practical tool for automated opportunistic osteoporosis assessment in settings where DEXA measurements are unavailable.