Functional Mesh Model with Temporal Measurements for brain decoding

Abstract

We propose a method called Functional Mesh Model with Temporal Measurements (FMM-TM) to estimate a functional relationship among voxels using temporal data, and employ these relationships for brain decoding. For each sample, we measure Blood Oxygenation Level Dependent (BOLD) responses from each voxel, and construct a functional mesh around each voxel (called seed voxel) with its nearest neighbors selected using distance metrics namely Pearson correlation, cosine similarity and Euclidean distance. Then, we represent the BOLD response of a seed voxel in terms of linear combination of BOLD responses of its p-nearest neighbors. The relationship between the seed voxel and its neighbors is represented using a set of weights which are estimated by employing linear regression. We train Support Vector Machine and k-Nearest Neighbor classifiers using the estimated weights as features. We test our model in an event-related design experiment, namely object recognition, and observe that our features perform better than raw voxel intensity values, features obtained using various pairwise distance metrics, and local mesh model features extracted using stationary and temporal measurements.

Hierarchical multi-resolution mesh networks for brain decoding

“…For each time resolution, we estimate an independent network, where the nodes correspond to the anatomic regions and the arc weights represent the local relationship of an anatomic region with its neighbors. The brain network is defined as an ensemble of meshes formed in the functional neighborhood of the anatomic regions which has been shown to perform slightly better than spatial neighborhood in [10]. The arc weights of each mesh are estimated using ridge regression.…”

“…They represent the BOLD response recorded at each voxel (node) as a linear combination of the BOLD responses of its neighboring voxels. The arc weights of each mesh are then estimated by Ridge regression to represent the relationship among the voxels within their spatial [9] or functional [10] neighborhood. Finally, they embed the arc weights of local meshes into a feature vector to train a classifier for brain decoding.…”