Convolutional neural networks (CNNs) are usually used as a backbone to design methods in biomedical image segmentation. However, the limitation of receptive field and large number of parameters limit the performance of these methods. In this paper, we propose a graph neural network (GNN) based method named GNN-SEG for the segmentation of brain tissues. Different to conventional CNN based methods, GNN-SEG takes superpixels as basic processing units and uses GNNs to learn the structure of brain tissues. Besides, inspired by the interaction mechanism in biological vision systems, we propose two kinds of interaction modules for feature enhancement and integration. In the experiments, we compared GNN-SEG with state-of-the-art CNN based methods on four datasets of brain magnetic resonance images. The experimental results show the superiority of GNN-SEG.
@article{arxiv.2209.12764,
title = {Graph Neural Network and Superpixel Based Brain Tissue Segmentation (Corrected Version)},
author = {Chong Wu and Zhenan Feng and Houwang Zhang and Hong Yan},
journal= {arXiv preprint arXiv:2209.12764},
year = {2022}
}
Comments
The original version of this paper was accepted and presented at 2022 International Joint Conference on Neural Networks (IJCNN). This version corrects the mistakes in Figs. 7 and 8