BSBP-RWKV: Background Suppression with Boundary Preservation for Efficient Medical Image Segmentation

Xudong Zhou, Tianxiang Chen

Abstract:

Medical image segmentation is of great significance to disease diagnosis and treatment planning. Despite multiple progresses, most present methods (1) pay insufficient attention to suppressing background noise disturbance that impacts segmentation accuracy and (2) are not efficient enough, especially when the images are of large resolutions. To address the two challenges, we turn to a traditional de-noising method and a new efficient network structure and propose BSBP-RWKV for accurate and efficient medical image segmentation.
Specifically, we combine the advantages of Perona-Malik Diffusion (PMD) in noise suppression without losing boundary details and RWKV in its efficient structure, and devise the DWT-PMD RWKV Block across one of our encoder branches to preserve boundary details of lesion areas while suppressing background noise disturbance in an efficient structure. Then we feed the de-noised lesion boundary cues to our proposed Multi-Step Runge-Kutta convolutional Block to supplement the cues with more local details. We also propose a novel loss function for shape refinement that can align the shape of predicted lesion areas with GT masks in both spatial and frequency domains. Experiments on ISIC 2016 and Kvasir-SEG show the superior accuracy and efficiency of our BSBP-RWKV. Specifically, BSBP-RWKV reduces complexity of 5.8 times compared with the SOTA while also cutting down GPU memory usage by over 62.7% for each 1024×1024 image during inference.

Primary Subject Area: [Content] Vision and Language

Relevance To Conference: Medical image segmentation is an important research area. It facilitates pathological structure localization and analysis, treatment planning and navigation, automation and efficiency improvement, as well as driving medical research and innovation. Our work builds upon previous research and proposes an efficient medical image segmentation model called BSBP-RWKV (Background Suppression with Boundary Preservation Receptance Weighted Key Value), this model can simultaneously suppress image noise disturbance and preserve boundaries. To the best of our knowledge, this is the first medical image segmentation model based on RWKV. We hope that this work can provide inspiration for model accuracy and efficiency improvement in the field of medical multimodal imaging.

Submission Number: 2281