Coupled CP tensor decomposition with shared and distinct components for multi-task fMRI data fusion

TL;DR

This paper introduces a tensor-based multi-task fMRI data fusion method that directly recovers shared and dataset-specific components, improving interpretability and revealing meaningful group differences in schizophrenia research.

Contribution

It proposes a novel partially constrained CP decomposition framework that directly extracts shared and distinct features in multi-task fMRI data, unlike previous methods.

Findings

Identifies meaningful components differentiating schizophrenia patients from controls.

Demonstrates improved interpretability of shared and specific features.

Validates the method on real multi-task fMRI datasets.

Abstract

Discovering components that are shared in multiple datasets, next to dataset-specific features, has great potential for studying the relationships between different subjects or tasks in functional Magnetic Resonance Imaging (fMRI) data. Coupled matrix and tensor factorization approaches have been useful for flexible data fusion, or decomposition to extract features that can be used in multiple ways. However, existing methods do not directly recover shared and dataset-specific components, which requires post-processing steps involving additional hyperparameter selection. In this paper, we propose a tensor-based framework for multi-task fMRI data fusion, using a partially constrained canonical polyadic (CP) decomposition model. Differently from previous approaches, the proposed method directly recovers shared and dataset-specific components, leading to results that are directly interpretable. A strategy to select a highly reproducible solution to the decomposition is also proposed. We evaluate the proposed methodology on real fMRI data of three tasks, and show that the proposed method finds meaningful components that clearly identify group differences between patients with schizophrenia and healthy controls.