Analysis of Longitudinal Change Patterns in Developing Brain Using Functional and Structural Magnetic Resonance Imaging via Multimodal Fusion.

Functional and structural magnetic resonance imaging (fMRI and sMRI) are complementary approaches that can be used to study longitudinal brain changes in adolescents. Each individual modality offers distinct insights into the brain. Each individual modality may overlook crucial aspects of brain analysis. By combining them, we can uncover hidden brain connections and gain a more comprehensive understanding. In previous work, we identified multivariate patterns of change in whole-brain function during adolescence. In this work, we focus on linking functional change patterns (FCPs) to brain structure. We introduce two approaches and applied them to data from the Adolescent Brain and Cognitive Development (ABCD) dataset. First, we evaluate voxelwise sMRI-FCP coupling to identify structural patterns linked to our previously identified FCPs. Our approach revealed multiple interesting patterns in functional network connectivity (FNC) and gray matter volume (GMV) data that were linked to subject level variation. FCP components 2 and 4 exhibit extensive associations between their loadings and voxel-wise GMV data. Secondly, we leveraged a symmetric multimodal fusion technique called multiset canonical correlation analysis (mCCA) + joint independent component analysis (jICA). Using this approach, we identify structured FCPs such as one showing increased connectivity between visual and sensorimotor domains and decreased connectivity between sensorimotor and cognitive control domains, linked to structural change patterns (SCPs) including alterations in the bilateral sensorimotor cortex. Interestingly, females exhibit stronger coupling between brain functional and structural changes than males, highlighting sex-related differences. The combined results from both asymmetric and symmetric multimodal fusion methods underscore the intricate sex-specific nuances in neural dynamics. By utilizing two complementary multimodal approaches, our study enhances our understanding of the dynamic nature of brain connectivity and structure during the adolescent period, shedding light on the nuanced processes underlying adolescent brain development.

Functional and Structural Longitudinal Change Patterns in Adolescent Brain.

Functional magnetic resonance imaging (fMRI) and structural magnetic resonance imaging (sMRI) are two widely used techniques to analyze longitudinal brain functional and structural change in adolescents. Although longitudinal changes in intrinsic functional and structural changes have been studied separately, most studies focus on univariate change rather than estimating multivariate patterns of functional network connectivity (FNC) and gray matter (GM) changes with increased age. To analyze whole-brain structural and functional changes with increased age, we suggest two complementary techniques (1: linking of functional change pattern (FCP) to voxel-wise ∆GM and 2: the connection between FCP and structural change pattern (SCP)). In this study, we apply our approaches to the functional and GM data from the large-scale Adolescent Brain and Cognitive Development (ABCD) data. We find a significant correlation between FCP and voxel-wise ∆GM for two components. We also investigate the links between FCP and SCP and hypothesize that functional connectivity and GM continue to exhibit linked changes during adolescence.Clinical Relevance- This work captures the whole-brain functional and structural change patterns link by introducing two complementary techniques.

Evaluation of Comt2, Comt3, Cyp1b1, and Esr1 gene polymorphisms as risk factor for endometrial polyp.

The aim of this study is to evaluate COMT2, COMT3, CYP1B1, and ESR1 gene polymorphisms and occurrence of endometrial polyps. In addition, we intended to evaluate the clinical and epidemiological features of patients with and without the presence of the disease, characterizing the possible risk factors. A cross-sectional study was performed, with a total of 309 women, including 236 in the group of women with endometrial polyp confirmed by hysteroscopy and anatomical pathological examination and 73 in the group of people with diagnostic hysteroscopy without abnormal findings from the macroscopic point of view. Polymorphisms of four genes were studied: COMT2 (rs4680), COMT3 (rs5031015), CYP1B1 (rs1056836), and ESR1 (rs2234693). Polymorphism genotyping was determined using real-time polymerase chain reaction. Considering the results, no differences were identified between the two groups with respect to age, body mass index, diabetes, dyslipidemia, or smoking. The group of women without endometrial polyps showed higher use of hormone therapy than the other group (16.4 percent versus 3.8 percent, p < .001). The COMT2, COMT3, CYP1B1, and ESR1 genes exhibited no significant difference for the occurrence of endometrial polyp between the two groups. The research concluded that no correlation was identified between the genetic polymorphisms evaluated and the presence of endometrial polyps.

dcSBM: A federated constrained source-based morphometry approach for multivariate brain structure mapping.

The examination of multivariate brain morphometry patterns has gained attention in recent years, especially for their powerful exploratory capabilities in the study of differences between patients and controls. Among the many existing methods and tools for the analysis of brain anatomy based on structural magnetic resonance imaging data, data-driven source-based morphometry (SBM) focuses on the exploratory detection of such patterns. Here, we implement a semi-blind extension of SBM, called constrained source-based morphometry (constrained SBM), which enables the extraction of maximally independent reference-alike sources using the constrained independent component analysis (ICA) approach. To do this, we combine SBM with a set of reference components covering the full brain, derived from a large independent data set (UKBiobank), to provide a fully automated SBM framework. This also allows us to implement a federated version of constrained SBM (cSBM) to allow analysis of data that is not locally accessible. In our proposed decentralized constrained source-based morphometry (dcSBM), the original data never leaves the local site. Each site operates constrained ICA on its private local data using a common distributed computation platform. Next, an aggregator/master node aggregates the results estimated from each local site and applies statistical analysis to estimate the significance of the sources. Finally, we utilize two additional multisite patient data sets to validate our model by comparing the resulting group difference estimates from both cSBM and dcSBM.

Multimodal subspace independent vector analysis captures latent subspace structures in large multimodal neuroimaging studies.

We present Multimodal Subspace Independent Vector Analysis (MSIVA), a methodology to capture both joint and unique vector sources across multiple data modalities by defining linked and modality-specific subspaces. In particular, MSIVA enables the estimation of independent subspaces of various sizes within modalities and their one-to-one linkage to corresponding subspaces across modalities. We compare MSIVA to a fully unimodal initialization baseline and a fully multimodal initialization baseline, and evaluate all three approaches with five distinct subspace structures on synthetic and neuroimaging datasets. We first demonstrate that MSIVA and the unimodal baseline can identify the correct ground-truth subspace structures from the incorrect ones in multiple synthetic datasets, while the multimodal baseline fails at detecting high-dimensional subspace structures. We then show that MSIVA can better capture the latent subspace structure with the minimum loss value in two large multimodal neuroimaging datasets compared to the unimodal baseline. Our results from subsequent per-subspace canonical correlation analysis (CCA) and brain-phenotype modeling demonstrate that the sources from the optimal subspace structure are strongly associated with phenotype measures, including age, sex and schizophrenia-related effects. Our proposed methodology MSIVA can be applied to capture linked and unique biomarkers from multimodal neuroimaging data.

Genomic patterns linked to gray matter alterations underlying working memory deficits in adults and adolescents with attention-deficit/hyperactivity disorder.

Attention-deficit/hyperactivity disorder (ADHD) is a highly heritable neurodevelopmental disorder, with onset in childhood and a considerable likelihood to persist into adulthood. Our previous work has identified that across adults and adolescents with ADHD, gray matter volume (GMV) alteration in the frontal cortex was consistently associated with working memory underperformance, and GMV alteration in the cerebellum was associated with inattention. Recent knowledge regarding ADHD genetic risk loci makes it feasible to investigate genomic factors underlying these persistent GMV alterations, potentially illuminating the pathology of ADHD persistence. Based on this, we applied a sparsity-constrained multivariate data fusion approach, sparse parallel independent component analysis, to GMV variations in the frontal and cerebellum regions and candidate risk single nucleotide polymorphisms (SNPs) data from 341 unrelated adult participants, including 167 individuals with ADHD, 47 unaffected siblings, and 127 healthy controls. We identified one SNP component significantly associated with one GMV component in superior/middle frontal regions and replicated this association in 317 adolescents from ADHD families. The association was stronger in individuals with ADHD than in controls, and stronger in adults and older adolescents than in younger ones. The SNP component highlights 93 SNPs in long non-coding RNAs mainly in chromosome 5 and 21 protein-coding genes that are significantly enriched in human neuron cells. Eighteen identified SNPs have regulation effects on gene expression, transcript expression, isoform percentage, or methylation level in frontal regions. Identified genes highlight MEF2C, CADM2, and CADPS2, which are relevant for modulating neuronal substrates underlying high-level cognition in ADHD, and their causality effects on ADHD persistence await further investigations. Overall, through a multivariate analysis, we have revealed a genomic pattern underpinning the frontal gray matter variation related to working memory deficit in ADHD.

Individualized spatial network predictions using Siamese convolutional neural networks: A resting-state fMRI study of over 11,000 unaffected individuals.

Individuals can be characterized in a population according to their brain measurements and activity, given the inter-subject variability in brain anatomy, structure-function relationships, or life experience. Many neuroimaging studies have demonstrated the potential of functional network connectivity patterns estimated from resting functional magnetic resonance imaging (fMRI) to discriminate groups and predict information about individual subjects. However, the predictive signal present in the spatial heterogeneity of brain connectivity networks is yet to be extensively studied. In this study, we investigate, for the first time, the use of pairwise-relationships between resting-state independent spatial maps to characterize individuals. To do this, we develop a deep Siamese framework comprising three-dimensional convolution neural networks for contrastive learning based on individual-level spatial maps estimated via a fully automated fMRI independent component analysis approach. The proposed framework evaluates whether pairs of spatial networks (e.g., visual network and auditory network) are capable of subject identification and assesses the spatial variability in different network pairs' predictive power in an extensive whole-brain analysis. Our analysis on nearly 12,000 unaffected individuals from the UK Biobank study demonstrates that the proposed approach can discriminate subjects with an accuracy of up to 88% for a single network pair on the test set (best model, after several runs), and 82% average accuracy at the subcortical domain level, notably the highest average domain level accuracy attained. Further investigation of our network's learned features revealed a higher spatial variability in predictive accuracy among younger brains and significantly higher discriminative power among males. In sum, the relationship among spatial networks appears to be both informative and discriminative of individuals and should be studied further as putative brain-based biomarkers.

Three-way parallel group independent component analysis: Fusion of spatial and spatiotemporal magnetic resonance imaging data.

Advances in imaging acquisition techniques allow multiple imaging modalities to be collected from the same subject. Each individual modality offers limited yet unique views of the functional, structural, or dynamic temporal features of the brain. Multimodal fusion provides effective ways to leverage these complementary perspectives from multiple modalities. However, the majority of current multimodal fusion approaches involving functional magnetic resonance imaging (fMRI) are limited to 3D feature summaries that do not incorporate its rich temporal information. Thus, we propose a novel three-way parallel group independent component analysis (pGICA) fusion method that incorporates the first-level 4D fMRI data (temporal information included) by parallelizing group ICA into parallel ICA via a unified optimization framework. A new variability matrix was defined to capture subject-wise functional variability and then link it to the mixing matrices of the other two modalities. Simulation results show that the three-way pGICA provides highly accurate cross-modality linkage estimation under both weakly and strongly correlated conditions, as well as comparable source estimation under different noise levels. Results using real brain imaging data identified one linked functional-structural-diffusion component associated to differences between schizophrenia and controls. This was replicated in an independent cohort, and the identified components were also correlated with major cognitive domains. Functional network connectivity revealed visual-subcortical and default mode-cerebellum pairs that discriminate between schizophrenia and controls. Overall, both simulation and real data results support the use of three-way pGICA to identify multimodal spatiotemporal links and to pursue the study of brain disorders under a single unifying multimodal framework.

A multimodal IVA fusion approach to identify linked neuroimaging markers.

In this study, we introduce a method to perform independent vector analysis (IVA) fusion to estimate linked independent sources and apply to a large multimodal dataset of over 3000 subjects in the UK Biobank study, including structural (gray matter), diffusion (fractional anisotropy), and functional (amplitude of low frequency fluctuations) magnetic resonance imaging data from each subject. The approach reveals a number of linked sources showing significant and meaningful covariation with subject phenotypes. One such mode shows significant linear association with age across all three modalities. Robust age-associated reductions in gray matter density were observed in thalamus, caudate, and insular regions, as well as visual and cingulate regions, with covarying reductions of fractional anisotropy in the periventricular region, in addition to reductions in amplitude of low frequency fluctuations in visual and parietal regions. Another mode identified multimodal patterns that differentiated subjects in their time-to-recall during a prospective memory test. In sum, the proposed IVA-based approach provides a flexible, interpretable, and powerful approach for revealing links between multimodal neuroimaging data.

Modular and state-relevant functional network connectivity in high-frequency eyes open vs eyes closed resting fMRI data.

BACKGROUND: Resting-state fMRI (rs-fMRI) is employed to assess "functional connections" of signal between brain regions. However, multiple rs-fMRI paradigms and data-filtering strategies have been used, highlighting the need to explore BOLD signal across the spectrum. Rs-fMRI data is typically filtered at frequencies ranging between 0.008∼0.2 Hz to mitigate nuisance signal (e.g. cardiac, respiratory) and maximize neuronal BOLD signal. However, some argue neuronal BOLD signal may be parsed at higher frequencies. NEW METHOD: To assess the contributions of rs-fMRI along the BOLD spectra on functional network connectivity (FNC) matrices, a spatially constrained independent component analysis (ICA) was performed at seven different frequency "bins", after which FNC values and FNC measures of matrix-randomness were assessed using linear mixed models. RESULTS: Results show FNCs at higher-frequency bins display similar randomness to those from the typical frequency bins (0.01-0.15), while the largest values are in the 0.31-0.46 Hz bin. Eyes open (EO) vs eyes closed (EC) comparison found EC was less random than EO across most frequency bins. Further, FNC was greater in EC across auditory and cognitive control pairings while EO values were greater in somatomotor, visual, and default mode FNC. COMPARISON WITH EXISTING METHODS: Effect sizes of frequency and resting-state paradigm vary from small to large, but the most notable results are specific to frequency ranges and resting-state paradigm with artifacts like motion displaying negligible effect sizes. CONCLUSIONS: These suggest unique information may be derived from FNC matrices across frequencies and paradigms, but additional data is necessary prior to any definitive conclusions.

Reward Processing in Novelty Seekers: A Transdiagnostic Psychiatric Imaging Biomarker.

BACKGROUND: Dysfunctional reward processing is implicated in multiple mental disorders. Novelty seeking (NS) assesses preference for seeking novel experiences, which is linked to sensitivity to reward environmental cues. METHODS: A subset of 14-year-old adolescents (IMAGEN) with the top 20% ranked high-NS scores was used to identify high-NS-associated multimodal components by supervised fusion. These features were then used to longitudinally predict five different risk scales for the same and unseen subjects (an independent dataset of subjects at 19 years of age that was not used in predictive modeling training at 14 years of age) (within IMAGEN, n ≈1100) and even for the corresponding symptom scores of five types of patient cohorts (non-IMAGEN), including drinking (n = 313), smoking (n = 104), attention-deficit/hyperactivity disorder (n = 320), major depressive disorder (n = 81), and schizophrenia (n = 147), as well as to classify different patient groups with diagnostic labels. RESULTS: Multimodal biomarkers, including the prefrontal cortex, striatum, amygdala, and hippocampus, associated with high NS in 14-year-old adolescents were identified. The prediction models built on these features are able to longitudinally predict five different risk scales, including alcohol drinking, smoking, hyperactivity, depression, and psychosis for the same and unseen 19-year-old adolescents and even predict the corresponding symptom scores of five types of patient cohorts. Furthermore, the identified reward-related multimodal features can classify among attention-deficit/hyperactivity disorder, major depressive disorder, and schizophrenia with an accuracy of 87.2%. CONCLUSIONS: Adolescents with higher NS scores can be used to reveal brain alterations in the reward-related system, implicating potential higher risk for subsequent development of multiple disorders. The identified high-NS-associated multimodal reward-related signatures may serve as a transdiagnostic neuroimaging biomarker to predict disease risks or severity.

Deep learning encodes robust discriminative neuroimaging representations to outperform standard machine learning.

Recent critical commentaries unfavorably compare deep learning (DL) with standard machine learning (SML) approaches for brain imaging data analysis. However, their conclusions are often based on pre-engineered features depriving DL of its main advantage - representation learning. We conduct a large-scale systematic comparison profiled in multiple classification and regression tasks on structural MRI images and show the importance of representation learning for DL. Results show that if trained following prevalent DL practices, DL methods have the potential to scale particularly well and substantially improve compared to SML methods, while also presenting a lower asymptotic complexity in relative computational time, despite being more complex. We also demonstrate that DL embeddings span comprehensible task-specific projection spectra and that DL consistently localizes task-discriminative brain biomarkers. Our findings highlight the presence of nonlinearities in neuroimaging data that DL can exploit to generate superior task-discriminative representations for characterizing the human brain.

A Correlated Noise-assisted Decentralized Differentially Private Estimation Protocol, and its application to fMRI Source Separation.

Blind source separation algorithms such as independent component analysis (ICA) are widely used in the analysis of neuroimaging data. To leverage larger sample sizes, different data holders/sites may wish to collaboratively learn feature representations. However, such datasets are often privacy-sensitive, precluding centralized analyses that pool the data at one site. In this work, we propose a differentially private algorithm for performing ICA in a decentralized data setting. Due to the high dimension and small sample size, conventional approaches to decentralized differentially private algorithms suffer in terms of utility. When centralizing the data is not possible, we investigate the benefit of enabling limited collaboration in the form of generating jointly distributed random noise. We show that such (anti) correlated noise improves the privacy-utility trade-off, and can reach the same level of utility as the corresponding non-private algorithm for certain parameter choices. We validate this benefit using synthetic and real neuroimaging datasets. We conclude that it is possible to achieve meaningful utility while preserving privacy, even in complex signal processing systems.

Multidataset Independent Subspace Analysis With Application to Multimodal Fusion.

Unsupervised latent variable models-blind source separation (BSS) especially-enjoy a strong reputation for their interpretability. But they seldom combine the rich diversity of information available in multiple datasets, even though multidatasets yield insightful joint solutions otherwise unavailable in isolation. We present a direct, principled approach to multidataset combination that takes advantage of multidimensional subspace structures. In turn, we extend BSS models to capture the underlying modes of shared and unique variability across and within datasets. Our approach leverages joint information from heterogeneous datasets in a flexible and synergistic fashion. We call this method multidataset independent subspace analysis (MISA). Methodological innovations exploiting the Kotz distribution for subspace modeling, in conjunction with a novel combinatorial optimization for evasion of local minima, enable MISA to produce a robust generalization of independent component analysis (ICA), independent vector analysis (IVA), and independent subspace analysis (ISA) in a single unified model. We highlight the utility of MISA for multimodal information fusion, including sample-poor regimes ( N = 600 ) and low signal-to-noise ratio, promoting novel applications in both unimodal and multimodal brain imaging data.

aNy-way Independent Component Analysis.

Multimodal data fusion is a topic of great interest. Several fusion methods have been proposed to investigate coherent patterns and corresponding linkages across modalities, such as joint independent component analysis (jICA), multiset canonical correlation analysis (mCCA), mCCA+jICA, disjoint subspace using ICA (DS-ICA) and parallel ICA. JICA exploits source independence but assumes shared loading parameters. MCCA maximizes correlation linkage across modalities directly but is limited to orthogonal features. While there is no theoretical limit to the number of modalities analyzed together by jICA, mCCA, or the two-step approach mCCA+jICA, these approaches can only extract common features and require the same number of sources/components for all modalities. On the other hand, DS-ICA and parallel ICA can identify both common and distinct features but are limited to two modalities. DS-ICA assumes shared loading parameters among common features, which works well when links are strong. Parallel ICA simultaneously maximizes correlation between modalities and independence of sources, while allowing different number of sources for each modality. However, only a very limited number of modalities and linkage pairs can be optimized. To overcome these limitations, we propose aNy-way ICA, a new model to simultaneously maximize the independence of sources and correlations across modalities. aNy-way ICA combines infomax ICA and Gaussian independent vector analysis (IVA-G) via a shared weight matrix model without orthogonality constraints. Simulation results demonstrate that aNy-way ICA not only accurately recovers sources and loadings, but also the true covariance/linkage patterns, whether different modalities have the same or different number of sources. Moreover, aNy-way ICA outperforms mCCA and mCCA+jICA in terms of source and loading recovery accuracy, especially under noisy conditions.Clinical Relevance-This establishes a model for N-way data fusion of any number of modalities and linkage pairs, allowing different number of non-orthogonal sources for different modalities.

Frequency-Aware Summarization of Resting-State fMRI Data.

Many brain imaging modalities reveal interpretable patterns after the data dimensionality is reduced and summarized via data-driven approaches. In functional magnetic resonance imaging (fMRI) studies, such summarization is often achieved through independent component analysis (ICA). ICA transforms the original data into a relatively small number of interpretable bases in voxel space (referred to as ICA spatial components, or spatial maps) and corresponding bases in the time domain (referred to as time-courses of corresponding spatial maps) In this work, we use the word "basis" to broadly refer to either of the two factors resulting from the transformation. A precise summarization for fMRI requires accurately detecting co-activation of voxels by measuring temporal dependence. Accurate measurement of dependence requires a proper understanding of the underlying temporal characteristics of the data. One way to understand such characteristics is to study the frequency spectrum of fMRI data. Researchers have argued that information regarding the underlying neuronal activity might be spread over a range of frequencies as a result of the heterogeneous temporal nature of the neuronal activity, which is reflected in its frequency spectrum. Many studies have accounted for heterogeneous characteristics of the frequency of the signal by either directly inspecting the contents of frequency domain-transformed data or augmenting their analyses with such information. For example, studies on fMRI data have investigated brain functional connectivity by leveraging frequency-adjusted measures of dependence (e.g., when a correlation is measured as a function of frequency, as with "coherence"). Although these studies measure dependence as a function of frequency, the formulation does not capture all characteristics of the frequency-based dependence. Incorporating frequency information into a summarization approach would enable the retention of important frequency-related information that exists in the original space but might be lost after performing a frequency-independent summarization. We propose a novel data-driven approach built upon ICA, which is based on measuring dependence as a generalized function of frequency. Applying this approach to fMRI data provides evidence of existing cross-frequency functional connectivity between different areas of the brain.

Decentralized dynamic functional network connectivity: State analysis in collaborative settings.

As neuroimaging data increase in complexity and related analytical problems follow suite, more researchers are drawn to collaborative frameworks that leverage data sets from multiple data-collection sites to balance out the complexity with an increased sample size. Although centralized data-collection approaches have dominated the collaborative scene, a number of decentralized approaches-those that avoid gathering data at a shared central store-have grown in popularity. We expect the prevalence of decentralized approaches to continue as privacy risks and communication overhead become increasingly important for researchers. In this article, we develop, implement and evaluate a decentralized version of one such widely used tool: dynamic functional network connectivity. Our resulting algorithm, decentralized dynamic functional network connectivity (ddFNC), synthesizes a new, decentralized group independent component analysis algorithm (dgICA) with algorithms for decentralized k-means clustering. We compare both individual decentralized components and the full resulting decentralized analysis pipeline against centralized counterparts on the same data, and show that both provide comparable performance. Additionally, we perform several experiments which evaluate the communication overhead and convergence behavior of various decentralization strategies and decentralized clustering algorithms. Our analysis indicates that ddFNC is a fine candidate for facilitating decentralized collaboration between neuroimaging researchers, and stands ready for the inclusion of privacy-enabling modifications, such as differential privacy.

Covarying structural alterations in laterality of the temporal lobe in schizophrenia: A case for source-based laterality.

The human brain is asymmetrically lateralized for certain functions (such as language processing) to regions in one hemisphere relative to the other. Asymmetries are measured with a laterality index (LI). However, traditional LI measures are limited by a lack of consensus on metrics used for its calculation. To address this limitation, source-based laterality (SBL) leverages an independent component analysis for the identification of laterality-specific alterations, identifying covarying components between hemispheres across subjects. SBL is successfully implemented with simulated data with inherent differences in laterality. SBL is then compared with a voxel-wise analysis utilizing structural data from a sample of patients with schizophrenia and controls without schizophrenia. SBL group comparisons identified three distinct temporal regions and one cerebellar region with significantly altered laterality in patients with schizophrenia relative to controls. Previous work highlights reductions in laterality (ie, reduced left gray matter volume) in patients with schizophrenia compared with controls without schizophrenia. Results from this pilot SBL project are the first, to our knowledge, to identify covarying laterality differences within discrete temporal brain regions. The authors argue SBL provides a unique focus to detect covarying laterality differences in patients with schizophrenia, facilitating the discovery of laterality aspects undetected in previous work.

SPARSE INFOMAX BASED ON HOYER PROJECTION AND ITS APPLICATION TO SIMULATED STRUCTURAL MRI AND SNP DATA.

Independent component analysis has been widely applied to brain imaging and genetic data analyses for its ability to identify interpretable latent sources. Nevertheless, leveraging source sparsity in a more granular way may further improve its ability to optimize the solution for certain data types. For this purpose, we propose a sparse infomax algorithm based on nonlinear Hoyer projection, leveraging both sparsity and statistical independence of latent sources. The proposed algorithm iteratively updates the unmixing matrix by infomax (for independence) and the sources by Hoyer projection (for sparsity), feeding the sparse sources back as input data for the next iteration. Consequently, sparseness propagates effectively through infomax iterations, producing sources with more desirable properties. Simulation results on both brain imaging and genetic data demonstrate that the proposed algorithm yields improved pattern recovery, particularly under low signal-to-noise ratio conditions, as well as improved sparseness compared to traditional infomax.

Parallel group ICA+ICA: Joint estimation of linked functional network variability and structural covariation with application to schizophrenia.

There is growing evidence that rather than using a single brain imaging modality to study its association with physiological or symptomatic features, the field is paying more attention to fusion of multimodal information. However, most current multimodal fusion approaches that incorporate functional magnetic resonance imaging (fMRI) are restricted to second-level 3D features, rather than the original 4D fMRI data. This trade-off is that the valuable temporal information is not utilized during the fusion step. Here we are motivated to propose a novel approach called "parallel group ICA+ICA" that incorporates temporal fMRI information from group independent component analysis (GICA) into a parallel independent component analysis (ICA) framework, aiming to enable direct fusion of first-level fMRI features with other modalities (e.g., structural MRI), which thus can detect linked functional network variability and structural covariations. Simulation results show that the proposed method yields accurate intermodality linkage detection regardless of whether it is strong or weak. When applied to real data, we identified one pair of significantly associated fMRI-sMRI components that show group difference between schizophrenia and controls in both modalities, and this linkage can be replicated in an independent cohort. Finally, multiple cognitive domain scores can be predicted by the features identified in the linked component pair by our proposed method. We also show these multimodal brain features can predict multiple cognitive scores in an independent cohort. Overall, results demonstrate the ability of parallel GICA+ICA to estimate joint information from 4D and 3D data without discarding much of the available information up front, and the potential for using this approach to identify imaging biomarkers to study brain disorders.