Deep learning applications in osteosarcoma MRI: A systematic review of recent advances in AI-based osteosarcoma diagnosis
Galib Muhammad Shahriar Himel, Anusha Achuthan, Yusuf Abas Mohamed, Bee Ee Khoo, Mohd Ezane Bin Aziz · 2026
Read Deep learning applications in osteosarcoma MRI: A systematic review of recent advances in AI-based osteosarcoma diagnosis by Galib Muhammad Shahriar Himel, Anusha Achuthan, Yusuf Abas Mohamed, Bee Ee Khoo, Mohd Ezane Bin Aziz (2026) 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/plos-pone-0354896.txt.
Description
Galib Muhammad Shahriar Himel and four colleagues review how deep learning has been applied to MRI scans of osteosarcoma, the most common primary bone cancer of adolescence, in this 2026 review. Following standard reporting guidelines, they assessed thirty-eight studies from the past five years covering tumor outlining, sorting, and outlook. The methods sorted into seven families, from classic radiomics to convolutional networks, vision transformers, and multimodal systems.
Multimodal models achieved the best average overlap with expert tumor outlines, with standard convolutional networks close behind and lightweight networks performing well. Radiomics-based tools also predicted tumor death after chemotherapy with good accuracy. But the reviewers stress a stark gap: every model was tested only on past data at a single center. None has faced testing across many centers, as needed before use in care.
Catalog record
| CREATOR | Galib Muhammad Shahriar Himel, Anusha Achuthan, Yusuf Abas Mohamed, Bee Ee Khoo, Mohd Ezane Bin Aziz |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 97529 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |