From automatic detection to segmentation: A label-efficient SAM pipeline with feature-guided star-shape priors for breast ultrasound
Biomedical Signal Processing and Control · 2027-02 · 130 · 111604
DOI: 10.1016/j.bspc.2026.111604 ↗Kurz gefasst
Fachartikel in der Zeitschrift Biomedical Signal Processing and Control, 2027-02. Verfasst von Shoujun Huang und 6 weiteren Autor:innen. Die Arbeit nennt 48 Literaturangaben. Gefördert von: Natural Science Foundation of Zhejiang Province, National Natural Science Foundation of China, Jinhua City Science and Technology Bureau.
Abstract (Originalsprache)
Accurate segmentation of breast lesions in ultrasound images is important for quantitative lesion assessment, but remains difficult because of low contrast, noise, and artifacts. The Segment Anything Model (SAM) provides a flexible prompt-based segmentation framework, yet its performance on ultrasound images depends strongly on prompt quality and may require further boundary refinement. We propose a label-efficient automated pipeline that trains only an object detector with bounding-box annotations, keeps SAM frozen, and uses pixel-level masks only for benchmark evaluation. Detector-derived boxes are refined with a Chan–Vese (CV) model, and foreground/background point prompts are generated automatically without manual clicks or ground-truth prompts. After SAM prediction, a CV-inspired adaptive energy functional constructed on frozen SAM feature maps is jointly optimized with a multi-center star-shape constraint. This design uses SAM’s pretrained zero-shot segmentation capability without target-domain mask fine-tuning and retains an explicit, interpretable inference-time refinement process. The method was evaluated on three public breast ultrasound datasets, with a dermoscopic skin-lesion dataset included only as auxiliary out-of-domain validation. Relative to the best listed SAM-family baseline, the Dice improvements were 2.60, 1.93, and 1.07 percentage points on BUSI, BUS-UCLM, and UDIAT, respectively. Code is available at https://github.com/JeffJFZ/SAMwithStarShape .
Förderung
- Natural Science Foundation of Zhejiang Province
- National Natural Science Foundation of China
- Jinhua City Science and Technology Bureau
Zitieren
APA
Huang, S., Liu, J., Luo, S., Xie, H., Yuan, J., Kong, D., & Zhang, J. (2027). From automatic detection to segmentation: A label-efficient SAM pipeline with feature-guided star-shape priors for breast ultrasound. Biomedical Signal Processing and Control, 130, 111604. https://doi.org/10.1016/j.bspc.2026.111604
Vancouver
Huang S, Liu J, Luo S, Xie H, Yuan J, Kong D, et al. From automatic detection to segmentation: A label-efficient SAM pipeline with feature-guided star-shape priors for breast ultrasound. Biomedical Signal Processing and Control. 2027;130:111604. doi:10.1016/j.bspc.2026.111604
BibTeX
@article{Huang2027,
author = {Huang, Shoujun and Liu, Junjie and Luo, Shousheng and Xie, Huafeng and Yuan, Jing and Kong, Dexing and Zhang, Jianfeng},
title = {From automatic detection to segmentation: A label-efficient SAM pipeline with feature-guided star-shape priors for breast ultrasound},
journal = {Biomedical Signal Processing and Control},
year = {2027},
volume = {130},
pages = {111604},
doi = {10.1016/j.bspc.2026.111604}
}
EUVIMED