Comprehensive Quantitative Evaluation of Transfemoral Prosthetic Socket Fit Using Machine Learning MRI Segmentation and Finite Element Modeling

Accurate evaluation of pressure distribution at the socket–limb interface is essential for improving prosthetic fit and comfort in transfemoral amputees. This study aimed to develop a data-driven framework that integrates machine learning–based segmentation with finite element method (FEM) to quantitatively assess interface pressure during socket application. MRI data from a transfemoral amputee were processed using a custom image segmentation algorithm to extract adipose tissue, femur, and ischium, achieving high F-measure scores. The segmented tissues were reconstructed into 3D models, refined through outlier removal and surface smoothing, and used for FEM simulations in LS-DYNA. Pressure values were extracted at nine sensor locations and compared with experimental measurements. The results showed consistent polarity between measured and simulated values across all points. Furthermore, at the eight locations excluding the ischial tuberosity (IS) region, a statistically significant and moderately strong positive correlation was observed between measured and simulated pressures (r = 0.7485, p < 0.05). Notably, positive pressure regions demonstrated close agreement between experimental and simulated values, whereas the discrepancy observed at the IS region was likely influenced by the medial boundary conditions introduced to prevent unrealistic tissue displacement. This difference highlights a limitation of the current simulation setup. Overall, the proposed framework demonstrated reliable pressure estimation and offers a promising approach for personalized prosthetic socket design through automated anatomical modeling and simulation.