MamNet-PT: A Mamba-enhanced hybrid architecture with selective state-space modeling for uncertainty-aware brain tumor segmentation
Yu Sun, Yihang Qin · 2026
Read MamNet-PT: A Mamba-enhanced hybrid architecture with selective state-space modeling for uncertainty-aware brain tumor segmentation by Yu Sun, Yihang Qin (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-0351667.txt.
Description
Yu Sun and Yihang Qin present a brain tumor outlining system in a 2026 PLOS ONE paper. Drawing tumor borders on MRI scans is hard because tumors vary in size, fade into healthy tissue, and occupy little of the image. Exact borders guide treatment planning.
Their system, MamNet-PT, blends several designs: a state-space model for long-range context, a pre-trained image encoder, and a gate that weighs global against local detail. A pyramid module handles tumors at many scales, and a dropout method maps where the system is unsure. On a standard two thousand and twenty benchmark, it beat comparison systems on overlap scores. Added parts each contributed to the gain.
Catalog record
| CREATOR | Yu Sun, Yihang Qin |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 77666 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |