Automated Renal Tumor Segmentation in Computed Tomography Images Using a Global Attention–Based DeepLabV3+ Model: Algorithm Development and Validation
Yueyan Zhao, Jianqiang Liu, Lingyu Shao, Lin Li, Zhaoqing Liu, Yujie Liu, Jiaxin Wen, Xinyao Hao, Shuyan Li, Jianhong Zhao, Boming Song, Andrew Coristine · 2026
Read Automated Renal Tumor Segmentation in Computed Tomography Images Using a Global Attention–Based DeepLabV3+ Model: Algorithm Development and Validation by Yueyan Zhao, Jianqiang Liu, Lingyu Shao, Lin Li, Zhaoqing Liu, Yujie Liu, Jiaxin Wen, Xinyao Hao, Shuyan Li, Jianhong Zhao, Boming Song, Andrew Coristine (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/pmc-13579559.txt.
Description
Yueyan Zhao and co-authors built an automated tool in 2026 that outlines kidney tumors in CT scans. Such tools are needed because these tumors are rising worldwide, while hand outlining is slow and varies between doctors. Clear outlines guide surgery that spares the kidney and guide radiation planning.
Their model pairs a light backbone suited to clinic computers with a module that reads the scan at several scales at once. A global attention step in the decoder sharpens tumor edges and mutes background noise. Tested on a private set of 218 cases and a public set of 210, the model beat leading rivals, with an overlap score of about 0.94 on the private set. The team sees it as ready for clinical use.
Catalog record
| CREATOR | Yueyan Zhao, Jianqiang Liu, Lingyu Shao, Lin Li, Zhaoqing Liu, Yujie Liu, Jiaxin Wen, Xinyao Hao, Shuyan Li, Jianhong Zhao, Boming Song, Andrew Coristine |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 70 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |