Sparse Bayesian Learning for Identifying Imaging Biomarkers in AD Prediction

Center for Neuroimaging, Department of Radiology and Imaging Sciences, USA.
Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention 01/2010; 13(Pt 3):611-8. DOI: 10.1007/978-3-642-15711-0_76
Source: PubMed


We apply sparse Bayesian learning methods, automatic relevance determination (ARD) and predictive ARD (PARD), to Alzheimer's disease (AD) classification to make accurate prediction and identify critical imaging markers relevant to AD at the same time. ARD is one of the most successful Bayesian feature selection methods. PARD is a powerful Bayesian feature selection method, and provides sparse models that is easy to interpret. PARD selects the model with the best estimate of the predictive performance instead of choosing the one with the largest marginal model likelihood. Comparative study with support vector machine (SVM) shows that ARD/PARD in general outperform SVM in terms of prediction accuracy. Additional comparison with surface-based general linear model (GLM) analysis shows that regions with strongest signals are identified by both GLM and ARD/PARD. While GLM P-map returns significant regions all over the cortex, ARD/PARD provide a small number of relevant and meaningful imaging markers with predictive power, including both cortical and subcortical measures.

Download full-text


Available from: Andrew J Saykin, Oct 04, 2015
18 Reads
  • Source
    • "Sparse learning methods enjoy strong theoretical properties (Candès and Wakin, 2008; Donoho, 2006) and are receiving increased attention in many application areas (Beck and Teboulle, 2009; Candès et al., 2006; Figueiredo et al., 2007; Wu et al., 2009). Sparse learning has also been applied in neuroimaging to study genetic influences on the brain (Hibar et al., 2011; Kohannim et al., 2011; Le Floch et al., 2011; Vounou et al., 2010, 2012; Wang et al., 2012a), functional connectivity (Huang et al., 2010; Ryali et al., 2012), and for outcome predictions (Shen et al., 2010; Stonnington et al., 2010; Sun et al., 2009a; Wang et al., 2010a, 2010b, 2011a). In many computer vision, medical imaging and bioinformatics applications, using sparsity as a prior leads to state-of-the-art results (Liu and Ye, 2010; Liu et al., 2010b; Sun et al., 2009a; Wright et al., 2009). "
    [Show abstract] [Hide abstract]
    ABSTRACT: Many methods have been proposed for computer-assisted diagnostic classification. Full tensor information and machine learning with 3D maps derived from brain images may help detect subtle differences or classify subjects into different groups. Here we develop a new approach to apply tensor-based morphometry to parametric surface models for diagnostic classification. We use this approach to identify cortical surface features for use in diagnostic classifiers. First, with holomorphic 1-forms, we compute an efficient and accurate conformal mapping from a multiply connected mesh to the so-called slit domain. Next, the surface parameterization approach provides a natural way to register anatomical surfaces across subjects using a constrained harmonic map. To analyze anatomical differences, we then analyze the full Riemannian surface metric tensors, which retain multivariate information on local surface geometry. As the number of voxels in a 3D image is large, sparse learning is a promising method to select a subset of imaging features and to improve classification accuracy. Focusing on vertices with greatest effect sizes, we train a diagnostic classifier using the surface features selected by an L1-norm based sparse learning method. Stability selection is applied to validate the selected feature sets. We tested the algorithm on MRI-derived cortical surfaces from 42 subjects with genetically confirmed Williams syndrome and 40 age-matched controls, multivariate statistics on the local tensors gave greater effect sizes for detecting group differences relative to other TBM-based statistics including analysis of the Jacobian determinant and the largest eigenvalue of the surface metric. Our method also gave reasonable classification results relative to the Jacobian determinant, the pair of eigenvalues of the Jacobian matrix and volume features. This analysis pipeline may boost the power of morphometry studies, and may assist with image-based classification.
    NeuroImage 02/2013; 74:209–230. DOI:10.1016/j.neuroimage.2013.02.011 · 6.36 Impact Factor
  • Source
    • "Neuroimaging measures have been widely studied to predict disease status and/or cognitive performance (Batmanghelich et al., 2009; Shen et al., 2010a). However, whether these measures coupled with their longitudinal profiles have sufficient power to infer relevant genotype groups is still an under-explored yet important topic in AD research. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Motivation: Imaging genetic studies typically focus on identifying single-nucleotide polymorphism (SNP) markers associated with imaging phenotypes. Few studies perform regression of SNP values on phenotypic measures for examining how the SNP values change when phenotypic measures are varied. This alternative approach may have a potential to help us discover important imaging genetic associations from a different perspective. In addition, the imaging markers are often measured over time, and this longitudinal profile may provide increased power for differentiating genotype groups. How to identify the longitudinal phenotypic markers associated to disease sensitive SNPs is an important and challenging research topic. Results: Taking into account the temporal structure of the longitudinal imaging data and the interrelatedness among the SNPs, we propose a novel ‘task-correlated longitudinal sparse regression’ model to study the association between the phenotypic imaging markers and the genotypes encoded by SNPs. In our new association model, we extend the widely used ℓ2,1-norm for matrices to tensors to jointly select imaging markers that have common effects across all the regression tasks and time points, and meanwhile impose the trace-norm regularization onto the unfolded coefficient tensor to achieve low rank such that the interrelationship among SNPs can be addressed. The effectiveness of our method is demonstrated by both clearly improved prediction performance in empirical evaluations and a compact set of selected imaging predictors relevant to disease sensitive SNPs. Availability: Software is publicly available at: Contact: or
    Bioinformatics 09/2012; 28(18):i619-i625. DOI:10.1093/bioinformatics/bts411 · 4.98 Impact Factor
  • Source
    • "Machine learning methods have been widely employed to predict Alzheimer's disease (AD) status using imaging genetics measures (Batmanghelich et al., 2009; Fan et al., 2008; Hinrichs et al., 2009b; Shen et al., 2010a). Since AD is a neurodegenerative disorder characterized by progressive impairment of memory and other cognitive functions, regression models have also been investigated to predict clinical scores from structural, such as magnetic resonance imaging (MRI), and/or molecular, such as fluorodeoxyglucose positron emission tomography (FDG-PET), neuroimaging data (Stonnington et al., 2010; Walhovd et al., 2010). "
    [Show abstract] [Hide abstract]
    ABSTRACT: Recent advances in brain imaging and high-throughput genotyping techniques enable new approaches to study the influence of genetic and anatomical variations on brain functions and disorders. Traditional association studies typically perform independent and pairwise analysis among neuroimaging measures, cognitive scores and disease status, and ignore the important underlying interacting relationships between these units. To overcome this limitation, in this article, we propose a new sparse multimodal multitask learning method to reveal complex relationships from gene to brain to symptom. Our main contributions are three-fold: (i) introducing combined structured sparsity regularizations into multimodal multitask learning to integrate multidimensional heterogeneous imaging genetics data and identify multimodal biomarkers; (ii) utilizing a joint classification and regression learning model to identify disease-sensitive and cognition-relevant biomarkers; (iii) deriving a new efficient optimization algorithm to solve our non-smooth objective function and providing rigorous theoretical analysis on the global optimum convergency. Using the imaging genetics data from the Alzheimer's Disease Neuroimaging Initiative database, the effectiveness of the proposed method is demonstrated by clearly improved performance on predicting both cognitive scores and disease status. The identified multimodal biomarkers could predict not only disease status but also cognitive function to help elucidate the biological pathway from gene to brain structure and function, and to cognition and disease. Software is publicly available at:
    Bioinformatics 06/2012; 28(12):i127-36. DOI:10.1093/bioinformatics/bts228 · 4.98 Impact Factor
Show more