Multi-modal data analysis techniques, such as the Parallel Independent Component Analysis (pICA), are essential in neuroscience, medical imaging and genetic studies. The pICA algorithm allows the simultaneous decomposition of up to two data modalities achieving better performance than separate ICA decompositions and enabling the discovery of links between modalities. However, advances in data acquisition techniques facilitate the collection of more than two data modalities from each subject. Examples of commonly measured modalities include genetic information, structural magnetic resonance imaging (MRI) and functional MRI. In order to take full advantage of the available data, this work extends the pICA approach to incorporate three modalities in one comprehensive analysis. Simulations demonstrate the three-way pICA performance in identifying pairwise links between modalities and estimating independent components which more closely resemble the true sources than components found by pICA or separate ICA analyses. In addition, the three-way pICA algorithm is applied to real experimental data obtained from a study that investigate genetic effects on alcohol dependence. Considered data modalities include functional MRI (contrast images during alcohol exposure paradigm), gray matter concentration images from structural MRI and genetic single nucleotide polymorphism (SNP). The three-way pICA approach identified links between a SNP component (pointing to brain function and mental disorder associated genes, including BDNF, GRIN2B and NRG1), a functional component related to increased activation in the precuneus area, and a gray matter component comprising part of the default mode network and the caudate. Although such findings need further verification, the simulation and in-vivo results validate the three-way pICA algorithm presented here as a useful tool in biomedical data fusion applications.

To address the statistical challenges associated with genome-wide association studies, we present an independent component analysis (ICA) with reference approach to target a specific genetic variation and associated brain networks. First, a small set of single nucleotide polymorphisms (SNPs) are empirically chosen to reflect a feature of interest and these SNPs are used as a reference when applying ICA to a full genomic SNP array. After extracting the genetic component maximally representing the characteristics of the reference, we test its association with brain networks in functional magnetic resonance imaging (fMRI) data. The method was evaluated on both real and simulated datasets. Simulation demonstrates that ICA with reference can extract a specific genetic factor, even when the variance accounted for by such a factor is so small that a regular ICA fails. Our real data application from 48 schizophrenia patients (SZs) and 40 healthy controls (HCs) include 300K SNPs and fMRI images in an auditory oddball task. Using SNPs with allelic frequency difference in two groups as a reference, we extracted a genetic component that maximally differentiates patients from controls (p < 4 × 10−17), and discovered a brain functional network that was significantly associated with this genetic component (p < 1 × 10−4). The regions in the functional network mainly locate in the thalamus, anterior and posterior cingulate gyri. The contributing SNPs in the genetic factor mainly fall into two clusters centered at chromosome 7q21 and chromosome 5q35. The findings from the schizophrenia application are in concordance with previous knowledge about brain regions and gene function. All together, the results suggest that the ICA with reference can be particularly useful to explore the whole genome to find a specific factor of interest and further study its effect on brain.

This study investigates the relationship between genetic copy number variations and brain volume differences in an alcohol use disorder (AUD) population. We hypothesized that copy number variations may influence subject’s risk for alcohol use disorders through variations in regional gray and white matter brain volumes. Since genetic influences upon behavior are the result of many complicated interactions we focus on differences in brain volume as a putative intermediate phenotype between genetic variation and behavior. Copy number variation, alcohol use assessments and brain structural magnetic resonance images from 283 subjects, 199 male and 84 females who were enrolled in two AUD studies were obtained and analyzed using a combination of the Freesurfer image analysis suite and independent component analysis. Because brain volume varies by age we compared participant’s volume variation with that derived from a control cohort of 75 subjects. In addition we also regressed out the possible brain volume changes induced by long term alcohol consumption. Small cerebral cortex, cerebellar and caudate along with large cerebral white matter and 5th ventricle volumes are shown to be significantly associated with increased AUD severity. When these volume variations are compared with control subject volumes; the variations seen in subjects with AUD are markedly different from normal aging effects. CNVs at 11 q14.2 are marginally (p < 0.05 uncorrected) correlated with such brain volume variations and the correlation holds true after controlling for long-term alcohol consumption; deletion carriers have smaller cerebral cortex, cerebellar, caudate and larger cerebral white matter and 5th ventricle volumes than insertion carriers or subjects with no variation in this region. Similarly, deletion carriers also demonstrate higher AUD severity scores than insertion carriers or subjects with no variation. The results presented here suggest that copy number variation and in particular the variation at chromosome 11 q14.2 may have an impact in brain volume variation, potentially influencing AUD behavior.

Automatic modulation recognition is a topic of interest in many fields including signal surveillance, multi-user detection and radio frequency spectrum monitoring. In this paper, we present an algorithm for recognition of different types of continuous phase modulation signals that uses a combination of features extracted through cyclic spectral analysis and an ICA-SVM hybrid recognition system. Simulation results demonstrate the ability of the algorithm to correctly identify modulation types over a wide range of SNR scenarios. The effects of pulse shaping and partial response waveforms are also investigated.

Fusion of functional magnetic resonance imaging (fMRI) and genetic information is becoming increasingly important in biomarker discovery. These studies can contain vastly different types of information occupying different measurement spaces and in order to draw significant inferences and make meaningful predictions about genetic influence on brain activity; methodologies need to be developed that can accommodate the acute differences in data structures. One powerful, and occasionally overlooked, method of data fusion is canonical correlation analysis (CCA). Since the data modalities in question potentially contain millions of variables in each measurement, conventional CCA is not suitable for this task. This paper explores applying a sparse CCA algorithm to fMRI and genetic data fusion.