Leveraging Deep Learning for Accurate Fracture Detection and Classification Using X-Ray Images

Bones are the body's support system, providing structure, storing minerals, and protecting vital organs. When fracture occurs, it compromises this stability, making quick and accurate diagnosis crucial. This study aims to detect bone fractures in X-ray images using a dataset from Kaggle. To tackle the issue of uneven numbers of fractured versus nonfractured samples, we used data augmentation techniques, that makes the model more reliable. By leveraging the ResNet-50 architecture for its powerful feature extraction capabilities, we achieved a remarkable classification accuracy of 99.82% on our test set. These results highlight how data augmentation can significantly improve diagnostic precision and advance medical imaging practices.