MedVKAN: Efficient Feature Extraction with Mamba and KAN for Medical Image Segmentation

TL;DR

MedVKAN introduces a novel, efficient feature extraction framework combining Mamba and KAN architectures within a U-Net for superior medical image segmentation performance across multiple datasets.

Contribution

This paper presents MedVKAN, a new medical image segmentation model that integrates VSS-enhanced KAN with Mamba, achieving state-of-the-art results with improved efficiency.

Findings

Achieves state-of-the-art performance on four public datasets.

Ranks second on one dataset, demonstrating competitive accuracy.

Validates the effectiveness of combining Mamba and KAN architectures.

Abstract

Medical image segmentation has traditionally relied on convolutional neural networks (CNNs) and Transformer-based models. CNNs, however, are constrained by limited receptive fields, while Transformers face scalability challenges due to quadratic computational complexity. To over-come these issues, recent studies have explored alternative architectures. The Mamba model, a selective state-space design, achieves near-linear complexity and effectively captures long-range dependencies. Its vision-oriented variant, the Visual State Space (VSS) model, extends these strengths to image feature learning. In parallel, the Kolmogorov-Arnold Network (KAN) enhanc-es nonlinear expressiveness by replacing fixed activation functions with learnable ones. Moti-vated by these advances, we propose the VSS-Enhanced KAN (VKAN) module, which integrates VSS with the Expanded Field Convolutional KAN (EFC-KAN) as a replacement for Transformer modules, thereby strengthening feature extraction. We further embed VKAN into a U-Net frame-work, resulting in MedVKAN, an efficient medical image segmentation model. Extensive exper-iments on five public datasets demonstrate that MedVKAN achieves state-of-the-art performance on four datasets and ranks second on the remaining one. These results underscore the effective-ness of combining Mamba and KAN while introducing a novel and computationally efficient feature extraction framework. The source code is available at: https://github.com/beginner-cjh/MedVKAN.