CMS-net: Edge-aware multimodal MRI feature fusion for brain tumor segmentation

Abstract

With the growing application of artificial intelligence in medical image processing, multimodal MRI brain tumor segmentation has become crucial for clinical diagnosis and treatment. Accurate segmentation relies heavily on the effective utilization of multimodal information. However, most existing methods primarily focus on global and local deep semantic features, often overlooking critical aspects such as edge information and cross-channel correlations. To address these limitations while retaining the strengths of existing methods, we propose a novel brain tumor segmentation approach: an edge-aware feature fusion model based on a dual-encoder architecture. CMS-Net is a novel brain tumor segmentation model that integrates edge-aware fusion, cross-channel interaction, and spatial state feature extraction to fully leverage multimodal information for improved segmentation accuracy. The architecture comprises two main components: an encoder and a decoder. The encoder utilizes both convolutional downsampling and Smart Swin Transformer downsampling, with the latter employing Shifted Spatial Multi-Head Self-Attention (SSW-MSA) to capture global features and enhance long-range dependencies. The decoder reconstructs the image via the CMS-Block, which consists of three key modules: the Multi-Scale Deep Convolutional Cross-Channel Attention module (MDTA), the Spatial State Module (SSM), and the Boundary-Aware Feature Fusion module (SWA). CMS-Net's dual-encoder architecture allows for deep extraction of both local and global features, enhancing segmentation performance. MDTA generates attention maps through cross-channel covariance, while SSM models spatial context to improve the understanding of complex structures. The SWA module, combining SSW-MSA with pooling, subtraction, and convolution, facilitates feature fusion and edge extraction. Dice and Focal loss functions were introduced to optimize cross-channel and spatial feature extraction. Experimental results on the BraTS2018, BraTS2019, and BraTS2020 datasets demonstrate that CMS-Net effectively integrates spatial state, cross-channel, and boundary information, significantly improving multimodal brain tumor segmentation accuracy.