Deep Learning based Bone Fracture Prediction using Convolutional Neural Networks: A Comparative Study of Transfer Learning and Fine-tuning Techniques

Le résumé fourni par la source

Computer assisted bone fracture detection system has a vital role in medical automated health-care system. These automation system helps healthcare units to detect the bone fracture accurately. In this proposed paper, the CNN also called as convolutional neural network has been proposed for the classification purpose of the images that is classified into fractured and not_fractured. These images would be used to train the model to classify whether its positive or negative and to validate it. The proposed system has also demonstrated to be sufficiently the robust one to retrieve the necessary information and perform the required analysis on important image regions. Several images have been considered from the dataset and validated without any hindrances. Here the evaluation has been done by the performance measure of the trained model with the collected dataset which contain testing sets of both fractured and not_fractured images around 600 as well as training sets of both fractured and not_fractured around 8,863 images in total. The accuracy rate achieved in this particular paper was over 86%. This system uses clinical dataset to predict the fracture[1]and mainly focuses on hand, wrist, forearm, shoulder, elbow, finger with both positive as well as negative studies.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.