KANDU-Net:A Dual-Channel U-Net with KAN for Medical Image Segmentation
This is an incremental improvement for medical image segmentation, potentially offering better accuracy for medical professionals and diagnostic tools.
This paper introduces KANDU-Net, a dual-channel U-Net architecture that integrates KAN networks to enhance medical image segmentation. The model effectively captures local and global features by fusing KAN-extracted features with those from convolutional layers, demonstrating good accuracy across multiple datasets.
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.