AI-Based Applied Innovation for Fracture Detection in X-rays Using Custom CNN and Transfer Learning Models

Bone fractures present a major global health challenge, particularly in low-resource settings where access to radiology expertise is limited. We developed an AI-based solution for automated fracture detection from X-rays using a custom Convolutional Neural Network (CNN) and benchmarked it against transfer learning models including EfficientNetB0, MobileNetV2, and ResNet50. Our custom CNN achieved 95.96% accuracy, 0.94 precision, 0.88 recall, and an F1-score of 0.91 on the FracAtlas dataset.

arXiv Preprint