Multi-Paradigm fMRI Fusion via Sparse Tensor Decomposition in Brain Functional Connectivity Study

A Review of Fusion Methods for Omics and Imaging Data

The development of omics data and biomedical images has greatly advanced the progress of precision medicine in diagnosis, treatment, and prognosis. The fusion of omics and imaging data, i.e., omics-imaging fusion, offers a new strategy for understanding complex diseases. However, due to a variety of issues such as the limited number of samples, high dimensionality of features, and heterogeneity of different data types, efficiently learning complementary or associated discriminative fusion information from omics and imaging data remains a challenge. Recently, numerous machine learning methods have been proposed to alleviate these problems. In this review, from the perspective of fusion levels and fusion methods, we first provide an overview of preprocessing and feature extraction methods for omics and imaging data, and comprehensively analyze and summarize the basic forms and variations of commonly used and newly emerging fusion methods, along with their advantages, disadvantages and the applicable scope. We then describe public datasets and compare experimental results of various fusion methods on the ADNI and TCGA datasets. Finally, we discuss future prospects and highlight remaining challenges in the field.

A tale of two connectivities: intra- and inter-subject functional connectivity jointly enable better prediction of social abilities

Naturalistic functional magnetic resonance imaging (fMRI) paradigms, such as movie viewing, are attracting increased attention, given their ability to mimic the real-world cognitive demands on attention and multimodal sensory integration. Moreover, naturalistic paradigms allow for characterizing brain network responses associated with dynamic social cognition in a model-free manner using inter-subject functional connectivity (ISFC). While intra-subject functional connectivity (FC) characterizes the individual’s brain functional architecture, ISFC characterizes the neural coupling driven by time-locked extrinsic dynamic stimuli across individuals. Here, we hypothesized that ISFC and FC provide distinct and complementary information about individual differences in social cognition. To test this hypothesis, we examined a public movie-viewing fMRI dataset with 32 healthy adults and 90 typically developing children. Building three partial least squares regression (PLS) models to predict social abilities using FC and/or ISFC, we compared predictive performance to determine whether combining two connectivity measures could improve the prediction accuracy of individuals’ social-cognitive abilities measured by a Theory of Mind (ToM) assessment. Our results indicated that the joint model (ISFC + FC) yielded the highest predictive accuracy and significantly predicted individuals’ social cognitive abilities (rho = 0.34, p < 0.001). We also confirmed that the improved accuracy was not due to the increased feature dimensionality. In conclusion, we demonstrated that intra-/inter-subject connectivity encodes unique information about social abilities, and a joint investigation could help us gain a more complete understanding of the complex processes supporting social cognition.

Multi-Modal Imaging Genetics Data Fusion via a Hypergraph-Based Manifold Regularization: Application to Schizophrenia Study

Recent studies show that multi-modal data fusion techniques combine information from diverse sources for comprehensive diagnosis and prognosis of complex brain disorder, often resulting in improved accuracy compared to single-modality approaches. However, many existing data fusion methods extract features from homogeneous networs, ignoring heterogeneous structural information among multiple modalities. To this end, we propose a Hypergraph-based Multi-modal data Fusion algorithm, namely HMF. Specifically, we first generate a hypergraph similarity matrix to represent the high-order relationships among subjects, and then enforce the regularization term based upon both the inter- and intra-modality relationships of the subjects. Finally, we apply HMF to integrate imaging and genetics datasets. Validation of the proposed method is performed on both synthetic data and real samples from schizophrenia study. Results show that our algorithm outperforms several competing methods, and reveals significant interactions among risk genes, environmental factors and abnormal brain regions.