Browsing by Author "Risacher, Shannon L"

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    Identifying diagnosis-specific genotype–phenotype associations via joint multitask sparse canonical correlation analysis and classification
    (Oxford, 2020-07-13) Du, Lei; Liu, Fang; Liu, Kefei; Yao, Xiaohui; Risacher, Shannon L; Han, Junwei; Guo, Lei; Saykin, Andrew J; Shen, Li; Radiology and Imaging Sciences, School of Medicine
    Motivation Brain imaging genetics studies the complex associations between genotypic data such as single nucleotide polymorphisms (SNPs) and imaging quantitative traits (QTs). The neurodegenerative disorders usually exhibit the diversity and heterogeneity, originating from which different diagnostic groups might carry distinct imaging QTs, SNPs and their interactions. Sparse canonical correlation analysis (SCCA) is widely used to identify bi-multivariate genotype–phenotype associations. However, most existing SCCA methods are unsupervised, leading to an inability to identify diagnosis-specific genotype–phenotype associations. Results In this article, we propose a new joint multitask learning method, named MT–SCCALR, which absorbs the merits of both SCCA and logistic regression. MT–SCCALR learns genotype–phenotype associations of multiple tasks jointly, with each task focusing on identifying one diagnosis-specific genotype–phenotype pattern. Meanwhile, MT–SCCALR cannot only select relevant SNPs and imaging QTs for each diagnostic group alone, but also allows the selection of those shared by multiple diagnostic groups. We derive an efficient optimization algorithm whose convergence to a local optimum is guaranteed. Compared with two state-of-the-art methods, MT–SCCALR yields better or similar canonical correlation coefficients and classification performances. In addition, it owns much better discriminative canonical weight patterns of great interest than competitors. This demonstrates the power and capability of MTSCCAR in identifying diagnostically heterogeneous genotype–phenotype patterns, which would be helpful to understand the pathophysiology of brain disorders.
  • Thumbnail Image
    Item
    A Novel SCCA Approach via Truncated ℓ1-norm and Truncated Group Lasso for Brain Imaging Genetics
    (Oxford University Press, 2017-09-18) Du, Lei; Liu, Kefei; Zhang, Tuo; Yao, Xiaohui; Yan, Jingwen; Risacher, Shannon L; Han, Junwei; Guo, Lei; Saykin, Andrew J.; Shen, Li; Radiology and Imaging Sciences, School of Medicine
    Motivation: Brain imaging genetics, which studies the linkage between genetic variations and structural or functional measures of the human brain, has become increasingly important in recent years. Discovering the bi-multivariate relationship between genetic markers such as single-nucleotide polymorphisms (SNPs) and neuroimaging quantitative traits (QTs) is one major task in imaging genetics. Sparse Canonical Correlation Analysis (SCCA) has been a popular technique in this area for its powerful capability in identifying bi-multivariate relationships coupled with feature selection. The existing SCCA methods impose either the ℓ 1 -norm or its variants to induce sparsity. The ℓ 0 -norm penalty is a perfect sparsity-inducing tool which, however, is an NP-hard problem. Results: In this paper, we propose the truncated ℓ 1 -norm penalized SCCA to improve the performance and effectiveness of the ℓ 1 -norm based SCCA methods. Besides, we propose an efficient optimization algorithms to solve this novel SCCA problem. The proposed method is an adaptive shrinkage method via tuning τ . It can avoid the time intensive parameter tuning if given a reasonable small τ . Furthermore, we extend it to the truncated group-lasso (TGL), and propose TGL-SCCA model to improve the group-lasso-based SCCA methods. The experimental results, compared with four benchmark methods, show that our SCCA methods identify better or similar correlation coefficients, and better canonical loading profiles than the competing methods. This demonstrates the effectiveness and efficiency of our methods in discovering interesting imaging genetic associations. Availability: The Matlab code and sample data are freely available at http://www.iu.edu/∼shenlab/tools/tlpscca/ .
  • Thumbnail Image
    Item
    Visual contrast sensitivity is associated with the presence of cerebral amyloid and tau deposition
    (Oxford University Press, 2020) Risacher, Shannon L; WuDunn, Darrell; Tallman, Eileen F.; West, John D.; Gao, Sujuan; Farlow, Martin R.; Brosch, Jared R.; Apostolova, Liana G.; Saykin, Andrew J.; Radiology and Imaging Sciences, School of Medicine
    Visual deficits are common in neurodegenerative diseases including Alzheimer’s disease. We sought to determine the association between visual contrast sensitivity and neuroimaging measures of Alzheimer’s disease-related pathophysiology, including cerebral amyloid and tau deposition and neurodegeneration. A total of 74 participants (7 Alzheimer’s disease, 16 mild cognitive impairment, 20 subjective cognitive decline, 31 cognitively normal older adults) underwent the frequency doubling technology 24-2 examination, a structural MRI scan and amyloid PET imaging for the assessment of visual contrast sensitivity. Of these participants, 46 participants (2 Alzheimer’s disease, 9 mild cognitive impairment, 12 subjective cognitive decline, 23 cognitively normal older adults) also underwent tau PET imaging with [18F]flortaucipir. The relationships between visual contrast sensitivity and cerebral amyloid and tau, as well as neurodegeneration, were assessed using partial Pearson correlations, covaried for age, sex and race and ethnicity. Voxel-wise associations were also evaluated for amyloid and tau. The ability of visual contrast sensitivity to predict amyloid and tau positivity were assessed using forward conditional logistic regression and receiver operating curve analysis. All analyses first were done in the full sample and then in the non-demented at-risk individuals (subjective cognitive decline and mild cognitive impairment) only. Significant associations between visual contrast sensitivity and regional amyloid and tau deposition were observed across the full sample and within subjective cognitive decline and mild cognitive impairment only. Voxel-wise analysis demonstrated strong associations of visual contrast sensitivity with amyloid and tau, primarily in temporal, parietal and occipital brain regions. Finally, visual contrast sensitivity accurately predicted amyloid and tau positivity. Alterations in visual contrast sensitivity were related to cerebral deposition of amyloid and tau, suggesting that this measure may be a good biomarker for detecting Alzheimer’s disease-related pathophysiology. Future studies in larger patient samples are needed, but these findings support the power of these measures of visual contrast sensitivity as a potential novel, inexpensive and easy-to-administer biomarker for Alzheimer’s disease-related pathology in older adults at risk for cognitive decline.