Bone Fracture Detection using CNN

Bone fractures are a significant medical concern requiring accurate and timely diagnosis to ensure effective treatment. This project presents a deep learning-based system for bone fracture detection and classification using Convolutional Neural Networks (CNNs). The system integrates a user-friendly Graphical User Interface (GUI) to facilitate the input of bone fracture images. The process begins with the selection of a bone fracture image, followed by image resizing for uniformity. A pre-processed dataset of bone fracture images is utilized for training the CNN model to detect and classify fractures into three categories: Mild, Moderate, and Severe. The deep learning model leverages advanced CNN architectures for feature extraction and classification, achieving high accuracy in predicting fracture severity. The GUI enables users to input images, run the detection process, and view classified outputs seamlessly. This automated system demonstrates the potential to assist healthcare professionals in diagnosing fractures quickly and accurately, reducing dependency on manual assessments and enhancing clinical decision-making. The achieved accuracy underscores the effectiveness of the proposed approach, making it a valuable tool in medical imaging applications and orthopaedic care.

Index Terms— Bone Fracture images Dataset, Deep Learning algorithm, Convolutional Neural Network, GUI and Accuracy.