Individual thigh muscle and proximal femoral features predict displacement in femoral neck Fractures: An AI-driven CT analysis.
Authors
Affiliations (6)
Affiliations (6)
- Department of Orthopedic Surgery, Inha University Hospital, Inha University College of Medicine, Incheon, South Korea. Electronic address: [email protected].
- Department of Biomedical Research Institute, Inha University Hospital, Incheon, South Korea.
- Department of Nuclear Medicine, Kyung Hee University Hospital, Kyung Hee University School of Medicine, Seoul, South Korea.
- Division of Endocrinology and Metabolism, Department of Internal Medicine, Soonchunhyang University Hospital, Soonchunhyang University College of Medicine, Seoul, South Korea.
- Department of Orthopaedic Surgery, Seoul Bumin Hospital, Seoul, South Korea.
- Department of Orthopaedic Surgery, Seoul National University Bundang Hospital, Seongnam, South Korea.
Abstract
Hip fractures, particularly among the elderly, impose a significant public health burden due to increased morbidity and mortality. Femoral neck fractures, commonly resulting from low-energy falls, can lead to severe complications such as avascular necrosis, and often necessitate total hip arthroplasty. This study harnesses AI to enhance musculoskeletal assessments by performing automatic muscle segmentation on whole thigh CT scans and detailed cortical measurements using the StradView program. The primary aim is to improve the prediction and prevention of severe femoral neck fractures, ultimately supporting more effective rehabilitation and treatment strategies. This study measured anatomical features from whole thigh CT scans of 60 femoral neck fracture patients. An AI-driven individual muscle segmentation model (a dice score of 0.84) segmented 27 muscles in the thigh region, to calculate muscle volumes. Proximal femoral bone parameters were measured using StradView, including average cortical thickness, inner density and FWHM at four regions. Correlation analysis evaluated relationships between muscle features, cortical parameters, and fracture displacement. Machine learning models (Random Forest, SVM and Multi-layer Perceptron) predicted displacement using these variables. Correlation analysis showed significant associations between femoral neck displacement and trabecular density at the femoral neck/intertrochanter, as well as volumes of specific thigh muscles such as the Tensor fasciae latae. Machine learning models using a combined feature set of thigh muscle volumes and proximal femoral parameters performed best in predicting displacement, with the Random Forest model achieving an F1 score of 0.91 and SVM model 0.93. Decreased volumes of the Tensor fasciae latae, Rectus femoris, and Semimembranosus muscles, coupled with reduced trabecular density at the femoral neck and intertrochanter, were significantly associated with increased fracture displacement. Notably, our SVM model-integrating both muscle and femoral features-achieved the highest predictive performance. These findings underscore the critical importance of muscle strength and bone density in rehabilitation planning and highlight the potential of AI-driven predictive models for improving clinical outcomes in femoral neck fractures.