Enhancing bone fracture classification in x-ray using deep learning models

Project Code :TCMAPY1678

Objective

This project improves bone fracture classification in X-ray images by combining deep learning models (VGG19, MobileNet, EfficientNet) with machine learning classifiers like SVM and Random Forest. It also features a simple web interface for testing, highlighting the benefits of hybrid approaches in medical image analysis.

Abstract

This project aims to enhance the classification of bone fractures in X-ray images using deep learning models. Accurate identification of fractures is crucial in the medical field, and this project explores multiple approaches to improve classification performance. The models used include VGG19 combined with Random Forest, MobileNet with Support Vector Machine (SVM) and Random Forest, EfficientNet with SVM and XGboost,. Each model is trained and tested to evaluate its ability to correctly classify different types of bone fractures. By comparing these models, the project identifies strengths and limitations of both standalone and hybrid architectures.

A simple frontend interface is created using HTML, CSS, and JavaScript to allow users to interact with the classification system and view predictions. The application is not intended for deployment but rather to help understand the workflow of deep learning in medical imaging.

This work provides insight into how deep learning and traditional machine learning methods can be combined for better results in image classification tasks, particularly in healthcare.

Keywords: Deep Learning, Bone Fracture, X-ray, VGG19, MobileNet, EfficientNet, SVM, Random Forest, Classification.

NOTE: Without the concern of our team, please don't submit to the college. This Abstract varies based on student requirements.