论文标题
用于神经影像学中形状分类的图神经网络的比较研究
A Comparative Study of Graph Neural Networks for Shape Classification in Neuroimaging
论文作者
论文摘要
图形神经网络已成为一种有前途的方法，用于分析非欧盟数据（例如网格）。在医学成像中，类似网状的数据在建模解剖结构中起着重要作用，形状分类可用于计算机辅助诊断和疾病检测。但是，借助大量选择，使用GNN进行医学形状分析的最佳体系结构选择尚不清楚。我们进行了比较分析，为从业人员提供了几何深度学习中最新的最新概述，以进行神经影像学中的形状分类。使用生物学分类作为概念验证任务，我们发现使用FPFH作为节点特征可大大提高GNN的性能和概括到分布数据的数据。我们比较了三个替代卷积层的性能；我们加强了数据增强对基于图的学习的重要性。然后，我们使用阿尔茨海默氏病的分类确认这些结果对临床相关的任务持续存在。
Graph neural networks have emerged as a promising approach for the analysis of non-Euclidean data such as meshes. In medical imaging, mesh-like data plays an important role for modelling anatomical structures, and shape classification can be used in computer aided diagnosis and disease detection. However, with a plethora of options, the best architectural choices for medical shape analysis using GNNs remain unclear. We conduct a comparative analysis to provide practitioners with an overview of the current state-of-the-art in geometric deep learning for shape classification in neuroimaging. Using biological sex classification as a proof-of-concept task, we find that using FPFH as node features substantially improves GNN performance and generalisation to out-of-distribution data; we compare the performance of three alternative convolutional layers; and we reinforce the importance of data augmentation for graph based learning. We then confirm these results hold for a clinically relevant task, using the classification of Alzheimer's disease.
