Transferable CNN-Based Data Mining Approaches for Medical Imaging: Application to Spine DXA Scans for Osteoporosis Detection

Awad Bin Naeem^1,2Onur Osman³Shtwai Alsubai⁴Nazife Çevik⁵Abdelhamid Taieb ZAIDI⁶Amir Seyyedabbasi⁷Jawad Rasheed^10,11,8,9*

• ¹National College of Business Administration and Economics, Multan, Pakistan
• ²Universita degli Studi di Bologna, Bologna, Italy
• ³Istanbul Topkapi Universitesi, Istanbul, Türkiye
• ⁴Prince Sattam bin Abdulaziz University, Al Kharj, Saudi Arabia
• ⁵Istanbul Arel Universitesi, Istanbul, Türkiye
• ⁶Qassim University, Buraydah, Saudi Arabia
• ⁷Istinye Universitesi, Istanbul, Türkiye
• ⁸Istanbul Sabahattin Zaim University, Istanbul, Türkiye
• ⁹Istanbul Nisantasi Universitesi, Sarıyer, Türkiye
• ¹⁰Istanbul Medipol University, Istanbul, Türkiye
• ¹¹Applied Science Private University, Amman, Jordan

Osteoporosis is the leading cause of sudden bone fractures. This is a silent and deadly disease that can affect any part of the body, such as the spine, hips, and knee bones. Aim: To measure bone mineral density, dual-energy X-ray absorptiometry (DXA ) scans help radiologists and other medical professionals identify the early signs of osteoporosis in the spine. Methods: A proposed 21-layer convolutional neural network (CNN) model is implemented and validated for automatically detecting osteoporosis from spine DXA images. The dataset contains 174 spine DXA images, including 114 affected by osteoporosis and the rest normal or non-fractured. To improve training, the dataset is expanded using various data augmentation techniques. Results: The classification performance of the proposed model is compared with that of four popular pre-trained models: ResNet-50, VGG-16, VGG-19, and Inception-v3. With an F1-score of 97.16%, recall of 95.41%, classification accuracy of 97.14%, and precision of 99.04%, the proposed model consistently outperforms competing approaches. Conclusion: The proposed paradigm would therefore be very valuable to radiologists and other medical professionals. The capacity of the proposed approach to detect, monitor, and diagnose osteoporosis may lower the chance of developing the condition.