Objective:

The primary objective of this EPQ is to develop a Python program using Artificial Intelligence for medical image analysis.

I aim to create an artificial intelligence system capable of detecting and identifying fractures in X-ray images with high accuracy in milliseconds.

By utilising the deep learning framework provided by PyTorch, this tool will assist medical professionals in quickly and reliably identifying bone fractures, enhancing both the speed and accuracy of diagnoses in medical facilities worldwide.

Reasoning:

This EPQ is important to the field of medical diagnostics and healthcare technology for five key reasons:

This tool could significantly increase the accuracy of fracture detection in X-ray images, reducing misdiagnoses and improving patient outcomes. From personal experience, a fracture in my index finger was initially missed by a doctor, delaying my treatment until a larger hospital confirmed the fracture. This highlighted the potential for errors in detection—something AI could help prevent.
Detecting fractures in milliseconds can drastically reduce diagnosis times, which is crucial in emergencies and helps maintain workflow in busy medical facilities.
While not replacing human expertise, this AI tool can serve as a valuable second opinion, especially in regions with limited access to specialists.
This project demonstrates the practical application of AI in healthcare, contributing to the growing field of AI-driven medical solutions.
As an EPQ, this project offers hands-on experience with AI and machine learning, while also exploring the ethical implications of AI in healthcare

GitHub - ultralytics/yolov5: YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite