Efficient CNN-Based Bone Fracture Detection in X-Ray Radiographs with MobileNetV2

In this study, a deep learning-based approach for detecting bone fractures in X-ray images, utilizing a MobileNetV2 architecture combined with Convolutional Neural Networks (CNNs). Fractures are a prevalent musculoskeletal injury demanding swift and accurate diagnosis for optimal treatment. Our system leverages the Bone Fracture Dataset to train the model in identifying and classifying fractures across diverse anatomical regions. The integration of MobileNetV2, known for its efficiency in mobile and embedded vision applications, with CNNs, allowed us to achieve significant performance improvements while maintaining computational efficiency. In its best performance, the system achieved a success rate of 94.8% on the practice data it was trained on. When tested on entirely new data, it was still able to identify fractures correctly in 93.5% of the cases, demonstrating its efficacy in accurately detecting bone fractures. This approach not only enhances diagnostic accuracy but also reduces the time and effort required for manual evaluation. By automating the initial detection phase, the system endeavors to minimize diagnostic errors and improve patient outcomes, offering a reliable and rapid assessment tool for healthcare professionals.