Swin-WaveNet: frequency-guided boundary restoration for robust skin lesion segmentation
Zhiping Dan, Run Zhang, Tinglong Tang, Yirong Wu, Xiaosheng Yu, Shuifa Sun, Ben Wang · 2026
Read Swin-WaveNet: frequency-guided boundary restoration for robust skin lesion segmentation by Zhiping Dan, Run Zhang, Tinglong Tang, Yirong Wu, Xiaosheng Yu, Shuifa Sun, Ben 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/pmc-13680583.txt.
Description
Zhiping Dan and co-authors present, in a 2026 study, a vision model that traces the edges of skin lesions more faithfully. Outlining a lesion in a dermoscope photo is hard when hair crosses it, light falls unevenly, or the border fades. Their model, Swin-WaveNet, splits image features by frequency. Broad shapes ride the low band, while crisp edge detail rides the high band, and only the edge band gets sharpened before the picture is rebuilt.
That split keeps weak or broken borders from being washed out by noise and glare. On two public skin image sets and one gut polyp set, overlap scores landed around ninety percent. The model also held up on a second skin set it was never tuned for. Cleaner outlines could help doctors judge which spots need a biopsy.
Catalog record
| CREATOR | Zhiping Dan, Run Zhang, Tinglong Tang, Yirong Wu, Xiaosheng Yu, Shuifa Sun, Ben Wang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 60 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |