Transferable CNN-based data mining approaches for medical imaging: application to spine DXA scans for osteoporosis detection
Awad Bin Naeem, Onur Osman, Shtwai Alsubai, Nazife Çevik, Abdelhamid Taieb Zaidi, Amir Seyyedabbasi, Jawad Rasheed · 2025
Read Transferable CNN-based data mining approaches for medical imaging: application to spine DXA scans for osteoporosis detection by Awad Bin Naeem, Onur Osman, Shtwai Alsubai, Nazife Çevik, Abdelhamid Taieb Zaidi, Amir Seyyedabbasi, Jawad Rasheed (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-12797949.txt.
Description
Awad Bin Naeem and colleagues apply convolutional networks to spot osteoporosis in spine scans. Their 2025 paper uses DXA images from clinical practice. Osteoporosis silently weakens bones until sudden fractures occur. Spine density scans help radiologists catch it early. The team built a 21-layer network for automatic detection.
The dataset held 174 spine images, most with osteoporosis. Augmentation expanded the data for stronger training. Four famous pre-trained models served as comparison baselines. The custom network beat them on the reported scores. Its F1 score and recall both ran very high. Transferable mining methods are the wider theme of the work. Clinics with few specialists could gain screening support.
Catalog record
| CREATOR | Awad Bin Naeem, Onur Osman, Shtwai Alsubai, Nazife Çevik, Abdelhamid Taieb Zaidi, Amir Seyyedabbasi, Jawad Rasheed |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 46 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |