Optimizing Automated Bone Fracture Detection Through Advanced Faster R-CNN Architectures Integrating Multi-Scale Feature Extraction and Data Augmentation Techniques

Bone fracture detection using X-ray images is a critical diagnostic task in the healthcare sector. This study investigates the efficacy of two state-of-the-art Faster R-CNN architectures, ResNeXt 101 Feature Pyramid Network (FPN) and ResNet-50 FPN, implemented using Detectron2. The dataset used includes COCO-style annotated X-ray images with various fracture categories, including shoulder, wrist, and humerus fractures. The models were trained using advanced data augmentation techniques such as rotation, scaling, and flipping to improve generalization. ResNeXt 101 FPN demonstrated superior feature extraction capabilities, achieving higher precision (18.91% AP at IoU=0.50:0.95) compared to ResNet-50 FPN (6.23% AP). However, challenges such as high false negatives and overlapping predictions were identified, highlighting areas for improvement. Experimental results reveal that ResNeXt 101 FPN not only achieves better localization accuracy but also demonstrates robustness in detecting subtle fracture patterns. The integration of these models into clinical workflows could potentially assist radiologists in reducing diagnostic errors. Future work aims to address the identified limitations and explore domain-specific pretraining for enhanced performance.