Paper Key : IRJ************014
Author: Sindhu A,Preethi K P
Date Published: 11 Jul 2024
Abstract
Bone fractures are common injuries that require prompt diagnosis and treatment to ensure optimal patient outcomes. However, accurately identifying fractures in medical imaging such as X-rays can be challenging, particularly in environments with limited access to specialized medical expertise. In this paper, we propose an Edge AI-based Bone Fracture Detection system using TensorFlow Lite (TFLite) for deployment on edge devices. Our system leverages deep learning models trained on annotated X-ray images to automatically detect and localize bone fractures in real-time. By deploying the detection model on edge devices, such as smartphones or portable X-ray machines, we enable rapid and decentralized fracture diagnosis, facilitating timely medical interventions. We evaluate the performance of our system using a dataset of labeled X-ray images and demonstrate its effectiveness in accurately detecting bone fractures with high precision and recall. The proposed Edge AI-based Bone Fracture Detection system offers a cost-effective and accessible solution for improving fracture diagnosis in resource-constrained healthcare settings, ultimately enhancing patient care and outcomes.