当前位置: X-MOL 学术Neuroinformatics › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Deep Learning‐based Classification of Resting‐state fMRI Independent‐component Analysis
Neuroinformatics ( IF 3 ) Pub Date : 2021-02-05 , DOI: 10.1007/s12021-021-09514-x
Victor Nozais 1, 2, 3, 4 , Philippe Boutinaud 1, 5 , Violaine Verrecchia 1, 2, 3, 4 , Marie-Fateye Gueye 1, 2, 3, 4 , Pierre-Yves Hervé 1, 5 , Christophe Tzourio 6, 7 , Bernard Mazoyer 1, 2, 3, 4, 7 , Marc Joliot 1, 2, 3, 4
Affiliation  

Functional connectivity analyses of fMRI data have shown that the activity of the brain at rest is spatially organized into resting-state networks (RSNs). RSNs appear as groups of anatomically distant but functionally tightly connected brain regions. Inter-RSN intrinsic connectivity analyses may provide an optimal spatial level of integration to analyze the variability of the functional connectome. Here we propose a deep learning approach to enable the automated classification of individual independent-component (IC) decompositions into a set of predefined RSNs. Two databases were used in this work, BIL&GIN and MRi-Share, with 427 and 1811 participants, respectively. We trained a multilayer perceptron (MLP) to classify each IC as one of 45 RSNs, using the IC classification of 282 participants in BIL&GIN for training and a 5-dimensional parameter grid search for hyperparameter optimization. It reached an accuracy of 92 %. Predictions for the remaining individuals in BIL&GIN were tested against the original classification and demonstrated good spatial overlap between the cortical RSNs. As a first application, we created an RSN atlas based on MRi-Share. This atlas defined a brain parcellation in 29 RSNs covering 96 % of the gray matter. Second, we proposed an individual-based analysis of the subdivision of the default-mode network into 4 networks. Minimal overlap between RSNs was found except in the angular gyrus and potentially in the precuneus. We thus provide the community with an individual IC classifier that can be used to analyze one dataset or to statistically compare different datasets for RSN spatial definitions.



中文翻译:

基于深度学习的静息态 fMRI 独立成分分析分类

fMRI 数据的功能连接分析表明,休息时大脑的活动在空间上组织成静息状态网络 (RSN)。RSN 表现为一组解剖学上相距遥远但功能上紧密相连的大脑区域。RSN 间内在连接分析可以提供最佳的空间整合水平,以分析功能连接组的可变性。在这里,我们提出了一种深度学习方法,可以将单个独立组件 (IC) 分解自动分类为一组预定义的 RSN。在这项工作中使用了两个数据库,BIL&GIN 和 MRi-Share,分别有 427 和 1811 名参与者。我们训练了一个多层感知器 (MLP),使用 BIL& 中 282 名参与者的 IC 分类,将每个 IC 分类为 45 个 RSN 之一。用于训练的 GIN 和用于超参数优化的 5 维参数网格搜索。它达到了 92% 的准确率。BIL&GIN 中剩余个体的预测针对原始分类进行了测试,并证明了皮质 RSN 之间的良好空间重叠。作为第一个应用程序,我们创建了一个基于 MRi-Share 的 RSN 图集。该图谱定义了 29 个 RSN 中的大脑分割,覆盖了 96% 的灰质。其次,我们提出了将默认模式网络细分为 4 个网络的基于个体的分析。除了角回和可能在 GIN 针对原始分类进行了测试,并证明了皮质 RSN 之间的良好空间重叠。作为第一个应用程序,我们创建了一个基于 MRi-Share 的 RSN 图集。该图谱定义了 29 个 RSN 中的大脑分割,覆盖了 96% 的灰质。其次,我们提出了将默认模式网络细分为 4 个网络的基于个体的分析。除了角回和可能在 GIN 针对原始分类进行了测试,并证明了皮质 RSN 之间的良好空间重叠。作为第一个应用程序,我们创建了一个基于 MRi-Share 的 RSN 图集。该图谱定义了 29 个 RSN 中的大脑分割,覆盖了 96% 的灰质。其次,我们提出了将默认模式网络细分为 4 个网络的基于个体的分析。除了角回和可能在楔前叶。因此,我们为社区提供了一个单独的 IC 分类器,可用于分析一个数据集或对 RSN 空间定义的不同数据集进行统计比较。

更新日期:2021-02-05
down
wechat
bug