Open AccessDETECTION OF OSTEOPOROSIS IN DEFECTED BONES USING RADTORCH AND DEEP LEARNING TECHNIQUES
Author(s) -
Mohsin Shahzad,
Talha Farooq Khan,
Mohsin Bashir,
Muhammad Mansoor Ayub,
Fatima Ashraf,
Shoaib Hashmi,
Fareeha Zahoor,
Fawwad Hassan Jaskani
Publication year - 2021
Publication title -
international journal of engineering applied science and technology
Language(s) - English
Resource type - Journals
ISSN - 2455-2143
DOI - 10.33564/ijeast.2021.v06i04.015
Subject(s) - osteoporosis , confidence interval , classifier (uml) , artificial intelligence , computer science , machine learning , mathematics , statistics , medicine
Osteoporosis is a bone issue which happens inlight of low bone mass, debasement of bone smaller scaledesign and high powerlessness to break. It is a criticalprosperity stress over the world, especially in moreestablished people. In this paper a significant learningmodel reliant on a ResNet50 and XGBoost Classifier hasbeen used for predicting gouts or osteoporosis in MURAV2 dataset by using RADTorch library in order to preprocess image of X-rays to identify the defects easily. Therandomly provided images were of osteoporosis and themodel predicted it correctly with a 99.9% confidence level.There are also some images that the model was not able topredict it with full confidence. Results shows that, themodel predicted the Bones correctly and confidence levelwas impressive. These images show the model predictablythe Bones correctly with the confidence level 98% and91% respectively with ResNet50 and with Hybrid model ofResNet50 and XGBoost Classifiers. Similarly, our modeldoes not only detect Bones, but it can also detect otherosteoporosis with an impressive confidence level