Ses: a Swin-Unet Edge-aware Segmentation network for uterine fibroid ultrasound images
Xiaotong Wang, Liling Shi, Wenjuan Wang, Lijuan Guo · 2026
Read Ses: a Swin-Unet Edge-aware Segmentation network for uterine fibroid ultrasound images by Xiaotong Wang, Liling Shi, Wenjuan Wang, Lijuan Guo (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-13289386.txt.
Description
Xiaotong Wang and co-authors sharpen AI outlines of uterine fibroids on ultrasound. Their 2026 paper introduces the SES network, built on a Swin-Unet backbone, to handle fibroid images whose borders blur and shapes twist.
Two additions do the work. A channel attention block reweights features so the lesion stands out. A richer convolution module keeps fine spatial detail at several scales, aimed at the fuzzy border zones where pixel calls go wrong. On hospital ultrasound images the network beat four established rivals on overlap, similarity, and accuracy scores, topping ninety-four percent on the Dice measure. Tests removing each block confirmed both earn their place. The authors present the system as a sturdier aid for fibroid assessment.
Catalog record
| CREATOR | Xiaotong Wang, Liling Shi, Wenjuan Wang, Lijuan Guo |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 49 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |