Back to all papers

A parallel UNet integrating KAN and mamba for medical image segmentation.

March 15, 2026pubmed logopapers

Authors

Liu J,Wu J,Xu L,Shi W,Zheng B

Affiliations (5)

  • School of Computer Science, China West Normal University, Nanchong, 637009, China.
  • Institute of Artificial Intelligence, China West Normal University, Nanchong, 637009, China.
  • Third Military Medical University, Chongqing, 400038, China.
  • School of Computer Science, China West Normal University, Nanchong, 637009, China. [email protected].
  • Institute of Artificial Intelligence, China West Normal University, Nanchong, 637009, China. [email protected].

Abstract

Medical image segmentation is fundamental for delineating lesion and organ boundaries in clinical workflows. While UNet-based models remain widely used, CNN-dominant designs are limited in modeling long-range context, and Transformer-based variants often introduce substantial computational overhead due to quadratic attention. To address this issue, we propose KMP-UNet, a parallel U-shaped framework that combines a Mamba-based state-space branch for linear-complexity contextual modeling and a Kolmogorov-Arnold Network (KAN) branch for nonlinear feature representation. We further introduce a task-oriented fusion block and a skip refinement module to better exploit hierarchical encoder-decoder features. KMP-UNet has a compact model size (about 1.0M parameters in our implementation). We evaluate the proposed method on four public datasets (ISIC2017, ISIC2018, CVC-ClinicDB, and BUSI) using standard segmentation metrics. On ISIC2018, KMP-UNet achieves 0.9038 DSC and 0.9600 accuracy under our protocol. Extensive comparisons and targeted ablations are conducted to analyze the contribution of each component.

Topics

Journal Article

Ready to Sharpen Your Edge?

Subscribe to join 11k+ peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.

We respect your privacy. Unsubscribe at any time.