Nilearn-based Multimodal Fusion Analysis for Integrating Brain Image Analysis

The integration of multiple brain imaging modalities has become a prominent research approach for understanding complex neural processes. The present study focuses on the application of Nilearn, a Python library for neuroimaging analysis in multimodal fusion analysis. The aim is to combine data from different modalities, including functional magnetic resonance imaging (fMRI), electroencephalography (EEG), and magnetoencephalography (MEG), to gain comprehensive insights into brain function. The research article presents a detailed workflow using Nilearn for multimodal fusion analysis. Two key multimodal fusion techniques, joint independent component analysis (jICA) and connectome-based fusion, implemented using Nilearn, are discussed in detail in this study. The workflow presented provides researchers with a systematic approach to integrate and interpret brain imaging data, facilitating a deeper understanding of the complex neural mechanisms underlying brain function and connectivity.