DeNAS-ViT: Data Efficient NAS-Optimized Vision Transformer for Ultrasound Image Segmentation
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (4) · 3002-3010
DOI: 10.1609/aaai.v40i4.37292 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Renqi Chen und 3 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref).
Abstract (Originalsprache)
Accurate segmentation of ultrasound images is essential for reliable medical diagnoses but is challenged by poor image quality and scarce labeled data. Prior approaches have relied on manually designed, complex network architectures to improve multi-scale feature extraction. However, such handcrafted models offer limited gains when prior knowledge is inadequate and are prone to overfitting on small datasets. In this paper, we introduce DeNAS-ViT, a Data efficient NAS-optimized Vision Transformer, the first method to leverage neural architecture search (NAS) for ultrasound image segmentation by automatically optimizing model architecture through token-level search. Specifically, we propose an efficient NAS module that performs multi-scale token search prior to the ViT’s attention mechanism, effectively capturing both contextual and local features while minimizing computational costs. Given ultrasound’s data scarcity and NAS’s inherent data demands, we further develop a NAS-guided semi-supervised learning (SSL) framework. This approach integrates network independence and contrastive learning within a stage-wise optimization strategy, significantly enhancing model robustness under limited-data conditions. Extensive experiments on public datasets demonstrate that DeNAS-ViT achieves state-of-the-art performance, maintaining robustness with minimal labeled data. Moreover, we highlight DeNAS-ViT’s generalization potential beyond ultrasound imaging, underscoring its broader applicability.
Zitieren
APA
Chen, R., Zheng, X., Su, H., & Wu, K. (2026). DeNAS-ViT: Data Efficient NAS-Optimized Vision Transformer for Ultrasound Image Segmentation. Proceedings of the AAAI Conference on Artificial Intelligence, 40(4), 3002-3010. https://doi.org/10.1609/aaai.v40i4.37292
Vancouver
Chen R, Zheng X, Su H, Wu K. DeNAS-ViT: Data Efficient NAS-Optimized Vision Transformer for Ultrasound Image Segmentation. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(4):3002-3010. doi:10.1609/aaai.v40i4.37292
BibTeX
@article{Chen2026,
author = {Chen, Renqi and Zheng, Xinzhe and Su, Haoyang and Wu, Kehan},
title = {DeNAS-ViT: Data Efficient NAS-Optimized Vision Transformer for Ultrasound Image Segmentation},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {4},
pages = {3002--3010},
doi = {10.1609/aaai.v40i4.37292}
}
EUVIMED