AFFUNet: adaptive feature fusion Transformer U-Net with joint loss function for medical image segmentation
Mingming Pang, Chu Yang, Yanlong Luo · 2026
Read AFFUNet: adaptive feature fusion Transformer U-Net with joint loss function for medical image segmentation by Mingming Pang, Chu Yang, Yanlong Luo (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/PMC13545588.txt.
Description
Mingming Pang, Chu Yang, and Yanlong Luo proposed in 2026 a new neural network design for outlining organs and tumors in medical scans, a step that guides diagnosis and treatment planning. Their design, AFFUNet, changes how features from different depths of the network are blended, letting the model learn the blend rather than fixing it. Two added training penalties push the model to work harder on difficult pixels and on exact boundaries.
Tested on a multi-organ CT benchmark and a heart MRI benchmark, the design edged past a strong recent rival on overlap scores while adding almost no computing cost. Tests that removed one piece at a time confirmed each change helped, especially for small organs. Clinical evaluation still lies ahead, the authors note.
Catalog record
| CREATOR | Mingming Pang, Chu Yang, Yanlong Luo |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 53 KB |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |