Constrained Independent Component Analysis Based on Entropy Bound Minimization for Subgroup Identification from Multi-subject fMRI Data

Abstract

Identification of subgroups of subjects homogeneous functional networks is a key step for precision medicine. Independent vector analysis (IVA) is shown to be effective for this task, however, it has a substantial computing cost. We propose a constrained independent component analysis algorithm based on minimizing the entropy bound (c-EBM) to overcome the computational complexity limitation of IVA. A set of spatial maps used as constraints provides a connection across the datasets, provides alignment across subjectwise ICA analyses and serves as a foundation for subgroup identification. The approach makes use of the available prior knowledge while allowing flexible density modeling without an orthogonality requirement for the demixing matrix. Synthetic data and large scale multi-subject resting state fMRI data have both been used to evaluate the performance of the new algorithm, c-EBM. The findings demonstrate that c-EBM is adaptable in terms of various settings for the constraint parameter on the synthetic data. With multi-subject resting state fMRI data, c-EBM can effectively identify subgroups and discover meaningful brain networks that show significant group differences between subgroups.

A Scalable Approach to Independent Vector Analysis by Shared Subspace Separation for Multi-Subject fMRI Analysis

“…Our findings indicate the IVA-S3 offers the potential for improved subgroup identification with fMRI data, as we demonstrated that the IVA-S3 is able to better preserve subject variability. A more detailed investigation of subgroup identification is beyond the scope of this work but is an emerging new area of research [4,[42][43][44][45]. Furthermore, as discussed in the previous section, the IVA might be prone to overfitting when analyzing large numbers of datasets.…”