Deep Parametric Model for Discovering Group-cohesive Functional Brain Regions
Deep Parametric Model for Discovering Group-cohesive Functional Brain Regions
复制标题
DOI：
10.1137/1.9781611976236.71
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
J. B. Lee;Xiangnan Kong;C. Moore;Nesreen Ahmed
中科院分区：
文献类型：
--
作者：
J. B. Lee;Xiangnan Kong;C. Moore;Nesreen Ahmed
神经成像中的主要任务之一是简化大脑的时空扫描（即，fMRI扫描）通过将体素划分成一组功能性大脑区域。一个新兴的研究线利用多个功能磁共振成像扫描，从一组受试者，计算一个单一的群体共识功能分区。这种基于共识的方法很有前途，因为它允许模型提高数据中的信噪比。然而，现有的方法主要是非参数的，这在引入新样本时会带来问题。此外，大多数现有方法计算多个受试者的单个分区，这不能说明不同受试者之间的功能和解剖变异性。在这项工作中，我们研究的问题，群体凝聚力的功能脑区发现的目标是使用一组受试者的信息来学习“群体凝聚力”，但个性化的大脑分区多功能磁共振成像扫描。这个问题是具有挑战性的，因为神经成像数据集通常是相当小和嘈杂的。我们介绍了一种新的基于图卷积的深度参数模型，称为大脑区域提取网络（BREN）。通过将fMRI数据视为图形，我们能够在大脑区域发现过程中整合来自相邻体素的信息，这有助于减少每个受试者的噪声。我们的模型使用Siamese架构进行训练，以鼓励具有组内聚性的分区。合成和真实世界的数据上的实验表明，我们所提出的方法的有效性。
One of the primary tasks in neuroimaging is to simplify spatiotemporal scans of the brain (i.e., fMRI scans) by partitioning the voxels into a set of functional brain regions. An emerging line of research utilizes multiple fMRI scans, from a group of subjects, to calculate a single group consensus functional partition. This consensus-based approach is promising as it allows the model to improve the signalto-noise ratio in the data. However, existing approaches are primarily non-parametric which poses problems when new samples are introduced. Furthermore, most existing approaches calculate a single partition for multiple subjects which fails to account for the functional and anatomical variability between different subjects. In this work, we study the problem of group-cohesive functional brain region discovery where the goal is to use information from a group of subjects to learn “group-cohesive” but individualized brain partitions for multiple fMRI scans. This problem is challenging since neuroimaging datasets are usually quite small and noisy. We introduce a novel deep parametric model based upon graph convolution, called the Brain Region Extraction Network (BREN). By treating the fMRI data as a graph, we are able to integrate information from neighboring voxels during brain region discovery which helps reduce noise for each subject. Our model is trained with a Siamese architecture to encourage partitions that are group-cohesive. Experiments on both synthetic and real-world data show the effectiveness of our proposed approach.