Paper Contents
Abstract
Bone fractures are a significant medical challenge that requires rapid and precise diagnosis to ensure timely treatment and recovery. Conventional X-ray-based diagnosis relies heavily on human expertise, which can be time-consuming and susceptible to errors. This research presents an advanced deep learning based system that harnesses Convolutional Neural Networks (CNNs) for automated fracture detection in medical images. We trained ResNet50 models to enhance classification accuracy by utilizing the MURA dataset. The system is structured into two primary stages: bone part identification and subsequent fracture classification. Through the integration of data augmentation strategies and transfer learning, the model's robustness is improved, making it an efficient tool for supporting radiologists and healthcare professionals in delivering precise and timely diagnoses.
Copyright
Copyright © 2025 Jaina Shivani. This is an open access article distributed under the Creative Commons Attribution License.
