ProPL: Universal Semi-Supervised Ultrasound Image Segmentation via Prompt-Guided Pseudo-Labeling
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (4) · 3101-3110
DOI: 10.1609/aaai.v40i4.37303 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Yaxiong Chen und 7 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref).
Abstract (Originalsprache)
Existing approaches for the problem of ultrasound image segmentation, whether supervised or semi-supervised, are typically specialized for specific anatomical structures or tasks, limiting their practical utility in clinical settings. In this paper, we pioneer the task of universal semi-supervised ultrasound image segmentation and propose ProPL, a framework that can handle multiple organs and segmentation tasks while leveraging both labeled and unlabeled data. At its core, ProPL employs a shared vision encoder coupled with prompt-guided dual decoders, enabling flexible task adaptation through a prompting-upon-decoding mechanism and reliable self-training via an uncertainty-driven pseudo-label calibration (UPLC) module. To facilitate research in this direction, we introduce a comprehensive ultrasound dataset spanning 5 organs and 8 segmentation tasks. Extensive experiments demonstrate that ProPL outperforms state-of-the-art methods across various metrics, establishing a new benchmark for universal ultrasound image segmentation.
Zitieren
APA
Chen, Y., Wang, Q., Li, C., Hu, J., Shi, Y., Xiong, S., Zhu, X. X., & Mou, L. (2026). ProPL: Universal Semi-Supervised Ultrasound Image Segmentation via Prompt-Guided Pseudo-Labeling. Proceedings of the AAAI Conference on Artificial Intelligence, 40(4), 3101-3110. https://doi.org/10.1609/aaai.v40i4.37303
Vancouver
Chen Y, Wang Q, Li C, Hu J, Shi Y, Xiong S, et al. ProPL: Universal Semi-Supervised Ultrasound Image Segmentation via Prompt-Guided Pseudo-Labeling. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(4):3101-3110. doi:10.1609/aaai.v40i4.37303
BibTeX
@article{Chen2026,
author = {Chen, Yaxiong and Wang, Qicong and Li, Chunlei and Hu, Jingliang and Shi, Yilei and Xiong, Shengwu and Zhu, Xiao Xiang and Mou, Lichao},
title = {ProPL: Universal Semi-Supervised Ultrasound Image Segmentation via Prompt-Guided Pseudo-Labeling},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {4},
pages = {3101--3110},
doi = {10.1609/aaai.v40i4.37303}
}
EUVIMED