KANDU-Net:A Dual-Channel U-Net with KAN for Medical Image Segmentation

TL;DR

This paper introduces KANDU-Net, a novel dual-channel U-Net architecture integrating KAN networks to enhance feature extraction for improved medical image segmentation accuracy.

Contribution

The paper proposes a dual-channel U-Net with KAN integration and an auxiliary network for effective feature fusion, advancing medical image segmentation methods.

Findings

Improved segmentation accuracy across multiple datasets.

Effective local and global feature capture through dual-channel design.

Potential for significant impact in medical imaging applications.

Abstract

The U-Net model has consistently demonstrated strong performance in the field of medical image segmentation, with various improvements and enhancements made since its introduction. This paper presents a novel architecture that integrates KAN networks with U-Net, leveraging the powerful nonlinear representation capabilities of KAN networks alongside the established strengths of U-Net. We introduce a KAN-convolution dual-channel structure that enables the model to more effectively capture both local and global features. We explore effective methods for fusing features extracted by KAN with those obtained through convolutional layers, utilizing an auxiliary network to facilitate this integration process. Experiments conducted across multiple datasets show that our model performs well in terms of accuracy, indicating that the KAN-convolution dual-channel approach has significant potential in medical image segmentation tasks.