Category Guided Attention Network for Brain Tumor Segmentation in MRI

TL;DR

This paper introduces CGA U-Net, a novel brain tumor segmentation network that employs a category-guided attention mechanism and intra-class feature updating to improve accuracy and efficiency in MRI analysis.

Contribution

The paper presents a new segmentation network with a supervised attention module and intra-class update approach, enhancing global semantic capture and reducing computational cost.

Findings

Outperforms state-of-the-art algorithms on BraTS 2019 dataset

Achieves higher segmentation accuracy

Reduces computational complexity

Abstract

Objective: Magnetic resonance imaging (MRI) has been widely used for the analysis and diagnosis of brain diseases. Accurate and automatic brain tumor segmentation is of paramount importance for radiation treatment. However, low tissue contrast in tumor regions makes it a challenging task.Approach: We propose a novel segmentation network named Category Guided Attention U-Net (CGA U-Net). In this model, we design a Supervised Attention Module (SAM) based on the attention mechanism, which can capture more accurate and stable long-range dependency in feature maps without introducing much computational cost. Moreover, we propose an intra-class update approach to reconstruct feature maps by aggregating pixels of the same category. Main results: Experimental results on the BraTS 2019 datasets show that the proposed method outperformers the state-of-the-art algorithms in both segmentation performance and computational complexity. Significance: The CGA U-Net can effectively capture the global semantic information in the MRI image by using the SAM module, while significantly reducing the computational cost. Code is available at https://github.com/delugewalker/CGA-U-Net.