EUVIMEDEUVIMED entdecken
Crossref

E³SAM2: Entropy-Aware and Edge-Guided Adaptation of SAM2 for Echocardiography Video Segmentation

Long Zheng, Zhi Li, Weidong Wang, Zhenyu Dai, Shuyun Li

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (16) · 13423-13431

DOI: 10.1609/aaai.v40i16.38346 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Long Zheng und 4 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Foundation segmentation models, such as SAM and its video-oriented variant SAM2, have achieved remarkable success in natural image and video segmentation. However, their direct application to echocardiography video is challenged by structural uncertainty arising from severe speckle noise and blurry anatomical boundaries. To address this, we propose E³SAM2, a lightweight adaptation framework that introduces a novel entropy-based methodology to explicitly model and mitigate such uncertainty. Specifically, an entropy-guided attention mechanism is introduced to steer the model’s focus toward structurally reliable features, particularly in speckle-dominated regions. Additionally, an entropy regularization loss is introduced to further enhance target-background discrimination. To better resolve indistinct anatomical contours, an edge-aware supervision module is incorporated to inject explicit boundary priors for sharper delineation. These components are efficiently integrated through a global-local feature adapter. Experiments on CAMUS and EchoNet-Dynamic datasets demonstrate that E³SAM2 achieves state-of-the-art segmentation and clinical estimation performance, while maintaining high computational efficiency.

Zitieren

APA

Zheng, L., Li, Z., Wang, W., Dai, Z., & Li, S. (2026). E³SAM2: Entropy-Aware and Edge-Guided Adaptation of SAM2 for Echocardiography Video Segmentation. Proceedings of the AAAI Conference on Artificial Intelligence, 40(16), 13423-13431. https://doi.org/10.1609/aaai.v40i16.38346

Vancouver

Zheng L, Li Z, Wang W, Dai Z, Li S. E³SAM2: Entropy-Aware and Edge-Guided Adaptation of SAM2 for Echocardiography Video Segmentation. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(16):13423-13431. doi:10.1609/aaai.v40i16.38346

BibTeX
@article{Zheng2026,
  author = {Zheng, Long and Li, Zhi and Wang, Weidong and Dai, Zhenyu and Li, Shuyun},
  title = {E³SAM2: Entropy-Aware and Edge-Guided Adaptation of SAM2 for Echocardiography Video Segmentation},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {16},
  pages = {13423--13431},
  doi = {10.1609/aaai.v40i16.38346}
}
Kostenlos starten →