Enhancing the Effectiveness of Bone Fracture Detection and Analyzing X-ray Images with Machine learning, An Automated approach
Year: 2025
Type: article
Abstract: Bone fracture detection using deep learning is an emerging solution aimed at automating the diagnosis process in medical imaging, specifically targeting fractures in X-ray, CT, or MRI scans. Leveraging Convolutional Neural Networks (CNNs) and transfer learning, this approach enhances the accuracy and efficiency of detecting fractures in medical images. Preprocessing techniques like image normalization and data augmentation, along with handling class imbalances, are crucial to improving model performance. By employing models like ResNet or DenseNet, and deploying the system through TensorFlow Lite for real-time edge applications, the system can deliver fast, accurate results, suitable for integration into clinical environments. The ultimate goal is to reduce diagnostic errors, particularly false negatives, and provide a robust, explainable AI tool for assisting medical professionals in fracture detection. Further validation and regulatory compliance ensure the system's safety and effectiveness in real-world use
Author: Yash Atul Chokhandre
Language: English
Topic: Medical Imaging and Analysis
Subfield: Biomedical Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W4408911128