Article

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

ABSTRACT 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.

0 Followers
 · 
133 Views
  • Source
    [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 · 6.13 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Neuroimaging markers have been widely used to predict the cognitive functions relevant to the progression of Alzheimer's disease (AD). Most previous studies identify the imaging markers without considering the brain structural correlations between neuroimaging measures. However, many neuroimaging markers interrelate and work together to reveal the cognitive functions, such that these relevant markers should be selected together as the phenotypic markers. To solve this problem, in this paper, we propose a novel network constrained feature selection (NCFS) model to identify the neuroimaging markers guided by the structural brain network, which is constructed by the sparse representation method such that the interrelations between neuroimaging features are encoded into probabilities. Our new methods are evaluated by the MRI and AV45-PET data from ADNI-GO and ADNI-2 (Alzheimer's Disease Neuroimaging Initiative). In all cognitive function prediction tasks, our new NCFS method outperforms other state-of-the-art regression approaches. Meanwhile, we show that the new method can select the correlated imaging markers, which are ignored by the competing approaches.
    Information processing in medical imaging : proceedings of the ... conference; 01/2013
  • [Show abstract] [Hide abstract]
    ABSTRACT: In a previous report, we proposed a method for combining multiple markers of atrophy caused by Alzheimer's disease into a single atrophy score that is more powerful than any one feature. We applied the method to expansion rates of the lateral ventricles, achieving the most powerful ventricular atrophy measure to date. Here, we expand our method's application to tensor-based morphometry measures. We also combine the volumetric tensor-based morphometry measures with previously computed ventricular surface measures into a combined atrophy score. We show that our atrophy scores are longitudinally unbiased with the intercept bias estimated at 2 orders of magnitude below the mean atrophy of control subjects at 1 year. Both approaches yield the most powerful biomarker of atrophy not only for ventricular measures but also for all published unbiased imaging measures to date. A 2-year trial using our measures requires only 31 (22, 43) Alzheimer's disease subjects or 56 (44, 64) subjects with mild cognitive impairment to detect 25% slowing in atrophy with 80% power and 95% confidence.
    Neurobiology of Aging 08/2014; 36. DOI:10.1016/j.neurobiolaging.2014.05.038 · 4.85 Impact Factor

Full-text (2 Sources)

Download
36 Downloads
Available from
May 28, 2014