APASA: adaptive selection of informative peritumoral regions for improved automated cancer lesion analysis
Xiaoyang Duan, Patrice Monkam, Xu Wang, Yabin Zhang, Shouliang Qi, Dan Zhao, Tao Yu, Mkiramweni Mbazingwa Elirehema, Deogratias Mzurikwao, Wei Qian · 2026
Read APASA: adaptive selection of informative peritumoral regions for improved automated cancer lesion analysis by Xiaoyang Duan, Patrice Monkam, Xu Wang, Yabin Zhang, Shouliang Qi, Dan Zhao, Tao Yu, Mkiramweni Mbazingwa Elirehema, Deogratias Mzurikwao, Wei Qian (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/PMC13578222.txt.
Description
Xiaoyang Duan and colleagues introduce a 2026 imaging method that picks the ring of tissue around a tumor with the most useful signal for computer diagnosis. Tissue just outside a growth is known to hold clues, yet fixed rules for how wide that ring should be often waste data or add noise.
Their method, called APASA, builds a graph from the tumor outline and grows the outer region only where it adds value. Tested inside five machine learning models on breast and thyroid ultrasound scans, the picked regions beat simple ring widening by wide margins on key scores. Which model worked best shifted with region shape and cancer type, a point the authors flag for anyone building such tools.
Catalog record
| CREATOR | Xiaoyang Duan, Patrice Monkam, Xu Wang, Yabin Zhang, Shouliang Qi, Dan Zhao, Tao Yu, Mkiramweni Mbazingwa Elirehema, Deogratias Mzurikwao, Wei Qian |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 94448 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |