Faculty Bibliography

Collecting multiple modalities of neuroimaging data on the same subject is increasingly becoming the norm in clinical practice and research. Fusing multiple modalities to find related patterns is a challenge in neuroimaging analysis. Canonical correlation analysis (CCA) is commonly used as a symmetric data fusion technique to find related patterns among multiple modalities. In CCA-based data fusion, principal component analysis (PCA) is frequently applied as a preprocessing step to reduce data dimension followed by CCA on dimension-reduced data. PCA, however, does not differentiate between informative voxels from non-informative voxels in the dimension reduction step. Sparse PCA (sPCA) extends traditional PCA by adding sparse regularization that assigns zero weights to non-informative voxels. In this study, sPCA is incorporated into CCA-based fusion analysis and applied on neuroimaging data. A cross-validation method is developed and validated to optimize the parameters in sPCA. Different simulations are carried out to evaluate the improvement by introducing sparsity constraint to PCA. Four fusion methods including sPCA+CCA, PCA+CCA, parallel ICA and sparse CCA were applied on structural and functional magnetic resonance imaging data of mild cognitive impairment subjects and normal controls. Our results indicate that sPCA significantly can reduce the impact of non-informative voxels and lead to improved statistical power in uncovering disease-related patterns by a fusion analysis.

Alzheimer's disease (AD), including its mild cognitive impairment (MCI) phase that may or may not progress into the AD, is the most ordinary form of dementia. It is extremely important to correctly identify patients during the MCI stage because this is the phase where AD may or may not develop. Thus, it is crucial to predict outcomes during this phase. Thus far, many researchers have worked on only using a single modality of a biomarker for the diagnosis of AD or MCI. Although recent studies show that a combination of one or more different biomarkers may provide complementary information for the diagnosis, it also increases the classification accuracy distinguishing between different groups. In this paper, we propose a novel machine learning-based framework to discriminate subjects with AD or MCI utilizing a combination of four different biomarkers: fluorodeoxyglucose positron emission tomography (FDG-PET), structural magnetic resonance imaging (sMRI), cerebrospinal fluid (CSF) protein levels, and Apolipoprotein-E (APOE) genotype. The Alzheimer's Disease Neuroimaging Initiative (ADNI) baseline dataset was used in this study. In total, there were 158 subjects for whom all four modalities of biomarker were available. Of the 158 subjects, 38 subjects were in the AD group, 82 subjects were in MCI groups (including 46 in MCIc [MCI converted; conversion to AD within 24 months of time period], and 36 in MCIs [MCI stable; no conversion to AD within 24 months of time period]), and the remaining 38 subjects were in the healthy control (HC) group. For each image, we extracted 246 regions of interest (as features) using the Brainnetome template image and NiftyReg toolbox, and later we combined these features with three CSF and two APOE genotype features obtained from the ADNI website for each subject using early fusion technique. Here, a different kernel-based multiclass support vector machine (SVM) classifier with a grid-search method was applied. Before passing the obtained features to the classifier, we have used truncated singular value decomposition (Truncated SVD) dimensionality reduction technique to reduce high dimensional features into a lower-dimensional feature. As a result, our combined method achieved an area under the receiver operating characteristic (AU-ROC) curve of 98.33, 93.59, 96.83, 94.64, 96.43, and 95.24% for AD vs. HC, MCIs vs. MCIc, AD vs. MCIs, AD vs. MCIc, HC vs. MCIc, and HC vs. MCIs subjects which are high relative to single modality results and other state-of-the-art approaches. Moreover, combined multimodal methods have improved the classification performance over the unimodal classification.

BACKGROUND:Non-invasive brain stimulation (NIBS) has been widely used to treat mild cognitive impairment (MCI). However, there exists no consensus on the best stimulation sites. OBJECTIVE:To explore potential stimulation locations for NIBS treatment in patients with MCI, combining meta- and resting state functional connectivity (rsFC) analyses. METHODS:The meta-analysis was conducted to identify brain regions associated with MCI. Regions of interest (ROIs) were extracted based on this meta-analysis. The rsFC analysis was applied to 45 MCI patients to determine brain surface regions that are functionally connected with the above ROIs. RESULTS:We found that the dorsolateral prefrontal cortex (DLPFC) and inferior frontal gyrus (IFG) were the overlapping brain regions between our results and those of previous studies. In addition, we recommend that the temporoparietal junction (including the angular gyrus), which was found in both the meta- and rsFC analysis, should be considered in NIBS treatment of MCI. Furthermore, the bilateral orbital prefrontal gyrus, inferior temporal gyrus, medial superior frontal gyrus, and right inferior occipital gyrus may be potential brain stimulation sites for NIBS treatment of MCI. CONCLUSION/CONCLUSIONS:Our results provide several potential sites for NIBS, such as the DLFPC and IFG, and may shed light on the locations of NIBS sites in the treatment of patients with MCI.

Mild cognitive impairment (MCI) is a transitional state between the cognitive changes in normal aging and Alzheimer's disease (AD), which induces abnormalities in specific brain regions. Previous studies showed that paired helical filaments Tau (PHF-Tau) protein is a potential pathogenic protein which may cause abnormal brain function and structure in MCI and AD patients. However, the understanding of the PHF-Tau protein network in MCI patients is limited. In this study, 225 subjects with PHF-Tau Positron Emission Tomography (PET) images were divided into four groups based on whether they carried Apolipoprotein E ε4 (APOE 4) or abnormal cerebrospinal fluid Total-Tau (CSF T-Tau). They are two important pathogenic factors that might cause cognitive function impairment. The four groups were: individuals harboring CSF T-Tau pathology but no APOE 4 (APOE 4-T+); APOE 4 carriers with normal CSF T-Tau (APOE 4+T-); APOE 4 carriers with abnormal CSF T-Tau (APOE 4+T+); and APOE 4 noncarriers with abnormal CSF T-Tau (APOE 4-T-). We explored the topological organization of PHF-Tau networks in these four groups and calculated five kinds of network properties: clustering coefficient, shortest path length, Q value of modularity, nodal centrality and degree. Our findings showed that compared with APOE 4-T- group, the other three groups showed different alterations in the clustering coefficient, shortest path length, Q value of modularity, nodal centrality and degree. Simultaneously, voxel-level analysis was conducted and the results showed that compared with APOE 4-T- group, the other three groups were found increased PHF-Tau distribution in some brain regions. For APOE 4+T+ group, positive correlation was found between the value of PHF-Tau distribution in altered regions and Functional Assessment Questionnaire (FAQ) score. Our results indicated that the effects of APOE 4 and abnormal CSF T-Tau may induce abnormalities of PHF-Tau protein and APOE 4 has a greater impact on PHF-Tau than abnormal CSF T-Tau. Our results may be particularly helpful in uncovering the pathophysiology underlying the cognitive dysfunction in MCI patients.

In the Alzheimer's disease (AD) continuum, the prodromal state of mild cognitive impairment (MCI) precedes AD dementia and identifying MCI individuals at risk of progression is important for clinical management. Our goal was to develop generalizable multivariate models that integrate high-dimensional data (multimodal neuroimaging and cerebrospinal fluid biomarkers, genetic factors, and measures of cognitive resilience) for identification of MCI individuals who progress to AD within 3 years. Our main findings were i) we were able to build generalizable models with clinically relevant accuracy (~93%) for identifying MCI individuals who progress to AD within 3 years; ii) markers of AD pathophysiology (amyloid, tau, neuronal injury) accounted for large shares of the variance in predicting progression; iii) our methodology allowed us to discover that expression of CR1 (complement receptor 1), an AD susceptibility gene involved in immune pathways, uniquely added independent predictive value. This work highlights the value of optimized machine learning approaches for analyzing multimodal patient information for making predictive assessments.

With the rapid growth of modern technology, many biomedical studies are being conducted to collect massive datasets with volumes of multi-modality imaging, genetic, neurocognitive, and clinical information from increasingly large cohorts. Simultaneously extracting and integrating rich and diverse heterogeneous information in neuroimaging and/or genomics from these big datasets could transform our understanding of how genetic variants impact brain structure and function, cognitive function, and brain-related disease risk across the lifespan. Such understanding is critical for diagnosis, prevention, and treatment of numerous complex brain-related disorders (e.g., schizophrenia and Alzheimer's disease). However, the development of analytical methods for the joint analysis of both high-dimensional imaging phenotypes and high-dimensional genetic data, a big data squared (BD2) problem, presents major computational and theoretical challenges for existing analytical methods. Besides the high-dimensional nature of BD2, various neuroimaging measures often exhibit strong spatial smoothness and dependence and genetic markers may have a natural dependence structure arising from linkage disequilibrium. We review some recent developments of various statistical techniques for imaging genetics, including massive univariate and voxel-wise approaches, reduced rank regression, mixture models, and group sparse multi-task regression. By doing so, we hope that this review may encourage others in the statistical community to enter into this new and exciting field of research.

Alzheimer's disease (AD) is the most common type of dementia in the elderly with no effective treatment currently. Recent studies of noninvasive neuroimaging, resting-state functional magnetic resonance imaging (rs-fMRI) with graph theoretical analysis have shown that patients with AD and mild cognitive impairment (MCI) exhibit disrupted topological organization in large-scale brain networks. In previous work, it is a common practice to threshold such networks. However, it is not only difficult to make a principled choice of threshold values, but also worse is the discard of potential important information. To address this issue, we propose a threshold-free feature by integrating a prior persistent homology-based topological feature (the zeroth Betti number) and a newly defined connected component aggregation cost feature to model brain networks over all possible scales. We show that the induced topological feature (Integrated Persistent Feature) follows a monotonically decreasing convergence function and further propose to use its slope as a concise and persistent brain network topological measure. We apply this measure to study rs-fMRI data from the Alzheimer's Disease Neuroimaging Initiative and compare our approach with five other widely used graph measures across five parcellation schemes ranging from 90 to 1,024 region-of-interests. The experimental results demonstrate that the proposed network measure shows more statistical power and stronger robustness in group difference studies in that the absolute values of the proposed measure of AD are lower than MCI and much lower than normal controls, providing empirical evidence for decreased functional integration in AD dementia and MCI.

The International Genomics of Alzheimer's Project (IGAP) is a consortium for characterizing the genetic landscape of Alzheimer's disease (AD). The identified and/or confirmed 19 single-nucleotide polymorphisms (SNPs) associated with AD are located on non-coding DNA regions, and their functional impacts on AD are as yet poorly understood. We evaluated the roles of the IGAP SNPs by integrating data from many resources, based on whether the IGAP SNP was (1) a proxy for a coding SNP or (2) associated with altered mRNA transcript levels. For (1), we confirmed that 12 AD-associated coding common SNPs and five nonsynonymous rare variants are in linkage disequilibrium with the IGAP SNPs. For (2), the IGAP SNPs in CELF1 and MS4A6A were associated with expression of their neighboring genes, MYBPC3 and MS4A6A, respectively, in blood. The IGAP SNP in DSG2 was an expression quantitative trait loci (eQTL) for DLGAP1 and NETO1 in the human frontal cortex. The IGAP SNPs in ABCA7, CD2AP, and CD33 each acted as eQTL for AD-associated genes in brain. Our approach for identifying proxies and examining eQTL highlighted potentially impactful, novel gene regulatory phenomena pertinent to the AD phenotype.

INTRODUCTION:Bile acids (BAs) are the end products of cholesterol metabolism produced by human and gut microbiome co-metabolism. Recent evidence suggests gut microbiota influence pathological features of Alzheimer's disease (AD) including neuroinflammation and amyloid-β deposition. METHOD:F]FDG PET). RESULTS:("A") and three with CSF p-tau181 ("T") (corrected P < .05). Furthermore, three, twelve, and fourteen BA signatures were associated with CSF t-tau, glucose metabolism, and atrophy ("N"), respectively (corrected P < .05). DISCUSSION:This is the first study to show serum-based BA metabolites are associated with "A/T/N" AD biomarkers, providing further support for a role of BA pathways in AD pathophysiology. Prospective clinical observations and validation in model systems are needed to assess causality and specific mechanisms underlying this association.