Deep Learning based Bone Fracture Detection
Sailaja Thota, Pranav Kandukuru, Meenakshi Sundaram, Anooja Ali, Syed Muzamil Basha, N Hima Bindu
Abstract
A current trend across several industries involves utilizing computer-based technologies to identify faults. To meet the demands of immediate detection and high precision, a highly responsive system should leverage modern approaches and make full use of available resources. While various methods exist for detecting bone fractures in the modern world, such as Magnetic Resonance Imaging (MRI), CT scans, and Bone scans, these approaches tend to be more expensive, uncomfortable for patients, and less effective at detecting subtle fractures that, if left untreated, could lead to significant challenges. In recent years, the application of Convolutional Neural Networks (CNNs) in medical image fracture identification has shown promise in automating the detection of bone fractures from X-ray images. However, deploying such algorithms on devices remains challenging due to limited computing resources. In this research work, MobileNet, employs X-ray images to detect bone fractures, and its results are compared with those of a CNN model. The MobileNet architecture is chosen for its capacity to reduce computational complexity while maintaining high accuracy of 98%.