Fracture Vision: Automated Bone Fracture Detection Using X-Ray Images

Abstract

Bone fractures are a major health concern that require prompt and accurate diagnosis to ensure appropriate treatment and successful recovery. Conventional diagnosis relies on radiologists examining X-ray images, a process that may become challenging because of increasing patient volume, image quality variations, and subtle fracture patterns. Recent progress in artificial intelligence, particularly deep learning, has enabled the development of automated systems capable of assisting clinicians in fracture detection. This survey reviews recent studies on bone fracture detection using X-ray images and examines widely adopted deep learning techniques such as Convolutional Neural Networks (CNNs), VGG16, ResNet50, and EfficientNet. It also discusses the role of image preprocessing, transfer learning, data augmentation, feature extraction, and explainable AI in improving diagnostic performance. A comparative evaluation of existing research is presented to identify their strengths, limitations, and reported outcomes. Finally, the survey highlights current research gaps and proposes future directions for building accurate, interpretable, and clinically reliable fracture detection systems that support healthcare professionals in making faster and more informed decisions.