HipSAFE: detecting hip fractures on ultrasound imaging using deep learning in a porcine cadaveric model.
Authors
Affiliations (6)
Affiliations (6)
- Sunnybrook Research Institute, Sunnybrook Health Sciences Centre, University of Toronto, Toronto, ON, Canada; Division of Orthopaedic Surgery, Department of Surgery, Temerty Faculty of Medicine, University of Toronto, Toronto, ON, Canada; Institute of Biomedical Engineering, Faculty of Applied Science & Engineering, University of Toronto, Toronto, ON, Canada. Electronic address: [email protected].
- Division of Orthopaedic Surgery, Department of Surgery, Temerty Faculty of Medicine, University of Toronto, Toronto, ON, Canada.
- Department of Medical Imaging, Temerty Faculty of Medicine, University of Toronto, Toronto, ON, Canada.
- Sunnybrook Research Institute, Sunnybrook Health Sciences Centre, University of Toronto, Toronto, ON, Canada.
- Division of Orthopaedic Surgery, Department of Surgery, Temerty Faculty of Medicine, University of Toronto, Toronto, ON, Canada; Division of Orthopaedic Surgery, St. Michael's Hospital, University of Toronto, Toronto, ON, Canada.
- Sunnybrook Research Institute, Sunnybrook Health Sciences Centre, University of Toronto, Toronto, ON, Canada; Division of Orthopaedic Surgery, Department of Surgery, Temerty Faculty of Medicine, University of Toronto, Toronto, ON, Canada; Institute of Biomedical Engineering, Faculty of Applied Science & Engineering, University of Toronto, Toronto, ON, Canada.
Abstract
Hip fractures require timely diagnosis and surgical intervention, and current approaches require diagnosis with pelvic radiographs in emergency departments. Portable, diagnostically reliable point-of-care ultrasound (US) could reduce unnecessary transfers and shorten time to surgery. The objective of this work was to evaluate, in a porcine cadaver model, the accuracy of HipSAFE, a deep-learning-assisted US tool intended to reduce operator dependence and support pre-hospital hip fracture triage by nurses and paramedics. The bilateral hind limbs of 15 juvenile porcine cadavers (30 hips) were imaged by operators with no sonographic training before and after inducing a displaced iatrogenic pertrochanteric hip fracture. The limbs were split at the cadaver level into training (n = 16), validation (n = 6) and held-out test (n = 8) sets. Frame-level classifiers (MobileNetV3, EfficientNet-Lite and ResNet) were pre-trained on ImageNet and fine-tuned. Cine clip predictions used a moving average with Youden index threshold calibration. Model F<sub>1</sub>-scores were compared against the diagnostic radiologists using a femur-level paired bootstrap test with Holm correction. Cine clip performance was reported on the 78 clips collected by 31 operators on 4 cadavers (8 femurs). Most architectures achieved high cine clip performance. EfficientNet-Lite0 reached an F<sub>1</sub>-score of 0.944 (95% confidence interval [CI], 0.920-0.980), sensitivity of 89.5% (95% CI, 75.9%-95.8%) and specificity of 100.0% (95% CI, 91.2%-100.0%); the majority voting ensemble reached an F<sub>1</sub>-score of 0.932 (95% CI, 0.903-0.967). The operators achieved an F<sub>1</sub>-score of 0.667 (0.581--0.750) and the two diagnostic radiologists achieved an F<sub>1</sub>-score of 0.684 (95% CI, 0.531-0.800). Although growth plates were present in intact and fractured femurs, the Grad-CAM attribution maps suggest that the models had difficulty distinguishing growth plates from fracture features. In this pre-clinical setting, a lightweight, deep-learning pipeline accurately identified hip fractures on US imaging, motivating future work on the feasibility of US with deep learning for pre-hospital hip trauma triage.