PM-DUnet: Fusing long-range dependencies and attention in a dual-U architecture for thyroid nodule segmentation
Shaoqiang Wang, Linhao Zhang, Guiling Shi, Zhongran Liu, Yuanyuan Zhang, Tiyao Liu, Yawu Zhao, Yuchen Wang · 2026
Read PM-DUnet: Fusing long-range dependencies and attention in a dual-U architecture for thyroid nodule segmentation by Shaoqiang Wang, Linhao Zhang, Guiling Shi, Zhongran Liu, Yuanyuan Zhang, Tiyao Liu, Yawu Zhao, Yuchen Wang (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-0353684.txt.
Description
Shaoqiang Wang led a team of eight authors on this 2026 medical imaging paper about outlining thyroid lumps in ultrasound scans. Nodules vary in size and blur at the edges, so software has to hold fine detail and wide context together. Their network stacks two U-shaped stages for a rough then refined outline, with modules that model long-range patterns cheaply and spotlight key features.
On standard tests the design beat leading rival methods on most core measures. Wang releases the code openly, aiming at more reliable computer help for thyroid diagnosis.
Catalog record
| CREATOR | Shaoqiang Wang, Linhao Zhang, Guiling Shi, Zhongran Liu, Yuanyuan Zhang, Tiyao Liu, Yawu Zhao, Yuchen Wang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 38805 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |