Abstract
Osteoporosis is a condition, which results in weakness of bones, and its effects grow detrimental as the person ages. Currently, there is no proven cure for Osteoporosis, so early detection is the most prudent way to slow down its effects. The work implements classification models based on CNN and other deep learning models to detect and classify osteoporosis using human spine X-ray image datasets made publicly available by kaggle. This paper presents various deep learning models incorporating transfer learning on hybrid combinations to train and test for better results. Result conveyed through accuracy, Confusion Matrix, Precision, Recall, F1 score, AUC, and observes considerable improvement when compared to previous works.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have