Alternating Diffusion Map Based Fusion of Multimodal Brain Connectivity Networks for IQ Prediction

Abstract

Objective: To explain individual differences in development, behavior, and cognition, most previous studies focused on projecting resting-state functional MRI (fMRI) based functional connectivity (FC) data into a low-dimensional space via linear dimensionality reduction techniques, followed by executing analysis operations. However, linear dimensionality analysis techniques may fail to capture nonlinearity of brain neuroactivity. Moreover, besides resting-state FC, FC based on task fMRI can be expected to provide complementary information. Motivated by these considerations, we nonlinearly fuse resting-state and task-based FC networks (FCNs) to seek a better representation in this paper. Methods: We propose a framework based on alternating diffusion map (ADM), which extracts geometry-preserving low-dimensional embeddings that successfully parameterize the intrinsic variables driving the phenomenon of interest. Specifically, we first separately build resting-state and task-based FCNs by symmetric positive definite matrices using sparse inverse covariance estimation for each subject, and then utilize the ADM to fuse them in order to extract significant low-dimensional embeddings, which are used as fingerprints to identify individuals. Results: The proposed framework is validated on the Philadelphia Neurodevelopmental Cohort data, where we conduct extensive experimental study on resting-state and fractal n-back task fMRI for the classification of intelligence quotient (IQ). The fusion of resting-state and nback task fMRI by the proposed framework achieves better classification accuracy than any single fMRI, and the proposed framework is shown to outperform several other data fusion methods. Conclusion and Significance: To our knowledge, this paper is the first to demonstrate a successful extension of the ADM to fuse resting-state and task-based fMRI data for accurate prediction of IQ.

Bootstrapping promotes the RSFC‐behavior associations: An application of individual cognitive traits prediction

“…In Qin et al () and Kashyap et al (), they decomposed RSFC (or timecourse) to extract individual‐specific RSFC (or timecourse) with different methods, which obtained obvious improvements in prediction. The second way is to combine various kinds of information with RSFC to enhance the prediction, such as task‐fMRI based FC (Elliott et al, ; Gao et al, ; Xiao, Stephen, Wilson, Calhoun, & Wang, ) and dynamic FC (Liegeois et al, ; Lim et al, ; Park et al, ), which could provide complementary information to the conventional FC. The third way is to decrease the influence of the possible noise in rs‐fMRI signal, for instance, the global signal regression (Li et al, ) and motion artifact correction (Nielsen et al, ) have been reported to advance the RSFC‐behavior prediction.…”

The Relevance of Ecological Transitions to Intelligence in Marine Mammals

“…It turns out that the correlation between brain size and neuron number across species is, while present, fairly variable (Herculano-Houzel et al, 2014). Further, the number of neurons, while important, is no more (and possibly less) important than the patterns of connections between those neurons and the regions they compose (e.g., in humans, Emerson and Cantlon, 2012;Xiang et al, 2012;Xiao et al, 2018). Here, research into marine mammal neurobiology is still in its infancy.…”

Beyond linear regression: mapping models in cognitive neuroscience should align with research goals

“…A number of studies have leveraged the power of ML methods to build flexible nonlinear mapping models and use them to identify neural correlates of brain disorders (e.g., Hasanzadeh et al, 2019;Kazemi & Houghten, 2018;Kim et al, 2016;Leming et al, 2020) and behavioral traits (e.g., Kumar et al, 2019;Morioka et al, 2020;Xiao et al, 2019). Yet the vast majority of cognitive neuroscience studies use linear mapping models (such as linear regression), resulting in a gap between different neuroscience subfields.…”

“…The concurrent increase in the size of available datasets (e.g., Chang et al, 2019;Majaj et al, 2015;Schoffelen et al, 2019) has enabled researchers to train large-scale mapping models without overfitting them. As a result, a number of applied neuroscience studies have leveraged the power of ML-based methods to build flexible nonlinear mapping models and use them to identify neural correlates of brain disorders (e.g., Hasanzadeh et al, 2019;Kazemi & Houghten, 2018;Kim et al, 2016;Leming et al, 2020) and of behavioral traits (e.g., Kumar et al, 2019;Morioka et al, 2020;Xiao et al, 2019).…”