The automated segmentation of cortical areas has been a long-standing challenge in medical image analysis. The complex geometry of the cortex is commonly represented as a polygon mesh, whose segmentation can be addressed by graph-based learning methods. When cortical meshes are misaligned across subjects, current methods produce significantly worse segmentation results, limiting their ability to handle multi-domain data. In this paper, we investigate the utility of E(n)-equivariant graph neural networks (EGNNs), comparing their performance against plain graph neural networks (GNNs). Our evaluation shows that GNNs outperform EGNNs on aligned meshes, due to their ability to leverage the presence of a global coordinate system. On misaligned meshes, the performance of plain GNNs drop considerably, while E(n)-equivariant message passing maintains the same segmentation results. The best results can also be obtained by using plain GNNs on realigned data (co-registered meshes in a global coordinate system).
翻译:在医学图像分析中,对皮层区域进行自动分割是一项长期挑战。皮层区域进行复杂的几何测量通常代表为多边形网状,其分解可以通过图形化的学习方法加以解决。当皮层环形网状体在各学科之间发生错配时,目前的方法会产生明显更差的分解结果,限制了它们处理多域数据的能力。在本文中,我们调查E(n)等离子图形神经网络(E(n)等离子图形神经网络)的效用,比较它们与平面图神经网络(GNNSs)的性能。我们的评估表明,由于它们有能力利用全球协调系统的存在,皮层环形网状网形网状比对齐的面网状网状网状网状GNNN(GNNSs)的性能要低得多,而E(n)等离子信息传递的性能保持同样的分解结果。在调整数据上使用普通的GNNN(在全球协调系统中共同注册的MES)也可以取得最佳的结果。