EUVIMEDEUVIMED entdecken
Crossref

U-KAN Makes Strong Backbone for Medical Image Segmentation and Generation

Chenxin Li, Xinyu Liu, Wuyang Li, Cheng Wang, Hengyu Liu, Yifan Liu, Zhen Chen, Yixuan Yuan

Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (5) · 4652-4660

DOI: 10.1609/aaai.v39i5.32491 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Chenxin Li und 7 weiteren Autor:innen. Die Arbeit wurde bisher 338-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

U-Net has become a cornerstone in various visual applications such as image segmentation and diffusion probability models. While numerous innovative designs and improvements have been introduced by incorporating transformers or MLPs, the networks are still limited to linearly modeling patterns as well as the deficient interpretability. To address these challenges, our intuition is inspired by the impressive results of the Kolmogorov-Arnold Networks (KANs) in terms of accuracy and interpretability, which reshape the neural network learning via the stack of non-linear learnable activation functions derived from the Kolmogorov-Anold representation theorem. Specifically, in this paper, we explore the untapped potential of KANs in improving backbones for vision tasks. We investigate, modify and re-design the established U-Net pipeline by integrating the dedicated KAN layers on the tokenized intermediate representation, termed U-KAN. Rigorous medical image segmentation benchmarks verify the superiority of UKAN by higher accuracy even with less computation cost. We further delved into the potential of U-KAN as an alternative U-Net noise predictor in diffusion models, demonstrating its applicability in generating task-oriented model architectures.

Zitieren

APA

Li, C., Liu, X., Li, W., Wang, C., Liu, H., Liu, Y., Chen, Z., & Yuan, Y. (2025). U-KAN Makes Strong Backbone for Medical Image Segmentation and Generation. Proceedings of the AAAI Conference on Artificial Intelligence, 39(5), 4652-4660. https://doi.org/10.1609/aaai.v39i5.32491

Vancouver

Li C, Liu X, Li W, Wang C, Liu H, Liu Y, et al. U-KAN Makes Strong Backbone for Medical Image Segmentation and Generation. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(5):4652-4660. doi:10.1609/aaai.v39i5.32491

BibTeX
@article{Li2025,
  author = {Li, Chenxin and Liu, Xinyu and Li, Wuyang and Wang, Cheng and Liu, Hengyu and Liu, Yifan and Chen, Zhen and Yuan, Yixuan},
  title = {U-KAN Makes Strong Backbone for Medical Image Segmentation and Generation},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2025},
  volume = {39},
  number = {5},
  pages = {4652--4660},
  doi = {10.1609/aaai.v39i5.32491}
}
Kostenlos starten →