Multi-Head Graph Convolutional Network for Structural Connectome Classification.

Multi-Head Graph Convolutional Network for Structural Connectome Classification.
复制标题

用于结构连接组分类的多头图卷积网络。

DOI:
10.1007/978-3-031-55088-1_3
复制
发表时间:
2024
期刊:
Graphs in biomedical image analysis, and overlapped cell on tissue dataset for histopathology : 5th MICCAI Workshop, GRAIL 2023 and 1st MICCAI Challenge, OCELOT 2023, held in conjunction with MICCAI 2023, Vancouver, BC, Canada, Septembe...
影响因子:
--
通讯作者:
Aganj,Iman
Aganj,Iman
中科院分区:
--
文献类型:
--
作者:
Kazi,Anees;Mora,Jocelyn;Fischl,Bruce;Dalca,AdrianV;Aganj,Iman

文献摘要

参考文献

相似文献

我们解决了基于扩散磁共振图像衍生的大脑连通性的分类。我们提出了一种受图卷积网络(GCNs)启发的机器学习模型,该模型采用脑连接输入图,并通过具有多个头部的并行GCN机制分别处理数据。所提出的网络是一个简单的设计,它采用了不同的头部,涉及集中在边缘和节点上的图卷积,从输入数据中彻底捕获表征。为了测试我们的模型从脑连接数据中提取互补和代表性特征的能力,我们选择了性别分类任务。这量化了连接组随性别变化的程度,这对提高我们对两性健康和疾病的理解很重要。我们展示了两个公开可用数据集的实验:prevention - ad(347名受试者)和OASIS3(771名受试者)。与我们测试的现有机器学习算法(包括经典方法和(图和非图)深度学习)相比,所提出的模型展示了最高的性能。我们对模型的每个组成部分进行了详细的分析。
We tackle classification based on brain connectivity derived from diffusion magnetic resonance images. We propose a machine-learning model inspired by graph convolutional networks (GCNs), which takes a brain-connectivity input graph and processes the data separately through a parallel GCN mechanism with multiple heads. The proposed network is a simple design that employs different heads involving graph convolutions focused on edges and nodes, thoroughly capturing representations from the input data. To test the ability of our model to extract complementary and representative features from brain connectivity data, we chose the task of sex classification. This quantifies the degree to which the connectome varies depending on the sex, which is important for improving our understanding of health and disease in both sexes. We show experiments on two publicly available datasets: PREVENT-AD (347 subjects) and OASIS3 (771 subjects). The proposed model demonstrates the highest performance compared to the existing machine-learning algorithms we tested, including classical methods and (graph and non-graph) deep learning. We provide a detailed analysis of each component of our model.
DOI: 10.1016/s0021-9258(17)43493-4
发表时间: 1984-02
期刊: The Journal of biological chemistry
影响因子: --
作者:
B. Mariani;R. Schimke
通讯作者: B. Mariani;R. Schimke
佛波酯显着增加小鼠细胞甲氨蝶呤耐药的发生率:可能的机制及其与肿瘤促进的相关性
DOI: --
发表时间: 1981
期刊: Cell
影响因子: 64.5
作者:
A. Varshavsky
通讯作者: A. Varshavsky
羟基脲处理的哺乳动物细胞中无 DNA 过量产生的染色体变化:对基因扩增的影响。
DOI: --
发表时间: 1986
期刊: Cancer research
影响因子: 11.2
作者:
Hahn,P;Kapp,LN;Morgan,WF;Painter,RB
通讯作者: Painter,RB
DOI: 10.1093/nar/7.6.1541
发表时间: 1979-01-01
影响因子: 14.9
作者:
KAFATOS, FC;JONES, CW;EFSTRATIADIS, A
通讯作者: EFSTRATIADIS, A
不同种类哺乳动物细胞复制子的合成率。
DOI: 10.1016/0022-2836(69)90306-4
发表时间: 1969
影响因子: 5.6
作者:
R. B. Painter;A. Schaefer
通讯作者: A. Schaefer