Voxel selection framework based on meta-heuristic search and mutual information for brain decoding

TL;DR

This paper introduces a novel meta-heuristic framework for selecting informative brain voxels from fMRI data to improve visual stimulus decoding accuracy, outperforming existing methods in brain-computer interface applications.

Contribution

It proposes a new voxel selection method combining meta-heuristics and mutual information, enhancing brain decoding performance over prior approaches.

Findings

Achieved decoding accuracy of approximately 90-91%.

Outperformed most existing brain decoders in validation.

Demonstrated potential for brain-computer interface use.

Abstract

Visual stimulus decoding is an increasingly important challenge in neuroscience. The goal is to classify the activity patterns from the human brain; during the sighting of visual objects. One of the crucial problems in the brain decoder is the selecting informative voxels. We propose a meta-heuristic voxel selection framework for brain decoding. It is composed of four phases: preprocessing of fMRI data; filtering insignificant voxels; postprocessing; and meta-heuristics selection. The main contribution is benefiting a meta-heuristics search algorithm to guide a wrapper voxel selection. The main criterion to nominate a voxel is based on its mutual information with the provided stimulus label. The results show impressive accuracy rates which are 90.66 +/- 3.66 and 91.61 +/- 8.24 for DS105 and DS107, respectively. This outperforms the most of existing brain decoders in similar validation conditions. The experimental results are very encouraging which can be successfully useId in the brain-computer interface.