Brain response pattern identification of fMRI data using a particle swarm optimization-based approach

Abstract

Many neuroscience studies have been devoted to understand brain neural responses correlating to cognition using functional magnetic resonance imaging (fMRI). In contrast to univariate analysis to identify response patterns, it is shown that multi-voxel pattern analysis (MVPA) of fMRI data becomes a relatively effective approach using machine learning techniques in the recent literature. MVPA can be considered as a multi-objective pattern classification problem with the aim to optimize response patterns, in which informative voxels interacting with each other are selected, achieving high classification accuracy associated with cognitive stimulus conditions. To solve the problem, we propose a feature interaction detection framework, integrating hierarchical heterogeneous particle swarm optimization and support vector machines, for voxel selection in MVPA. In the proposed approach, we first select the most informative voxels and then identify a response pattern based on the connectivity of the selected voxels. The effectiveness of the proposed approach was examined for the Haxby's dataset of object-level representations. The computational results demonstrated higher classification accuracy by the extracted response patterns, compared to state-of-the-art feature selection algorithms, such as forward selection and backward selection.

Keywords: Brain functional connectivity; Brain response pattern; Feature selection; Interaction selection; Particle swarm optimization; Pattern classification.

Fig. 1

An illustration of the proposed approach to response pattern identification from which a block-design experiment is carried out to examine visual function of fMRI data. Representative features are extracted by applying GLM to BOLD time series across all voxels in ventral temporal cortex in response to eight different stimuli. The feature interaction detection framework is applied to identify discriminating connectivity patterns of selected informative voxels

Fig. 2

A conceptual flowchart of the proposed feature interaction detection framework. FS Algorithm stands for feature selection algorithm

Fig. 3

Cross-validated solutions of PSO–SVM (in blue) and HHPSO–SVM (in red) from Stage I, where x-axis represents the number of selected voxels and y-axis represents the classification error. Lighter color means that the solution is obtained in earlier optimization iterations, while darker color denotes the solution is obtained in later optimization iterations. (Color figure online)

Fig. 4

Cross-validated solutions of PSO–SVM (in blue) and HHPSO–SVM (in red) from Stage II, where x-axis represents the number of selected voxels and y-axis represents the classification error. Lighter colormeans that the solution is obtained in earlier optimization iterations, while darker colordenotes the solution is obtained in later optimization iterations. (Color figure online)