Local Discriminant Hyperalignment for multi-subject fMRI data alignment

TL;DR

This paper introduces Local Discriminant Hyperalignment (LDHA), a supervised method that improves multi-subject fMRI data alignment for multivariate pattern analysis by maximizing within-category correlations and minimizing between-category correlations.

Contribution

The paper proposes LDHA, a novel supervised hyperalignment technique that incorporates local discriminant analysis into CCA to enhance functional alignment for MVP analysis.

Findings

LDHA outperforms existing hyperalignment methods in MVP classification accuracy.

LDHA improves the robustness of multi-subject fMRI data analysis.

Experimental results demonstrate superior alignment quality with LDHA.

Abstract

Multivariate Pattern (MVP) classification can map different cognitive states to the brain tasks. One of the main challenges in MVP analysis is validating the generated results across subjects. However, analyzing multi-subject fMRI data requires accurate functional alignments between neuronal activities of different subjects, which can rapidly increase the performance and robustness of the final results. Hyperalignment (HA) is one of the most effective functional alignment methods, which can be mathematically formulated by the Canonical Correlation Analysis (CCA) methods. Since HA mostly uses the unsupervised CCA techniques, its solution may not be optimized for MVP analysis. By incorporating the idea of Local Discriminant Analysis (LDA) into CCA, this paper proposes Local Discriminant Hyperalignment (LDHA) as a novel supervised HA method, which can provide better functional alignment for MVP analysis. Indeed, the locality is defined based on the stimuli categories in the train-set, where the correlation between all stimuli in the same category will be maximized and the correlation between distinct categories of stimuli approaches to near zero. Experimental studies on multi-subject MVP analysis confirm that the LDHA method achieves superior performance to other state-of-the-art HA algorithms.