ODVBA: Optimally-Discriminative Voxel-Based Analysis

Department of Radiology, University of Pennsylvania, Philadelphia, PA 19104, USA.
IEEE transactions on medical imaging 02/2011; 30(8):1441-54. DOI: 10.1109/TMI.2011.2114362
Source: PubMed


Gaussian smoothing of images prior to applying voxel-based statistics is an important step in voxel-based analysis and statistical parametric mapping (VBA-SPM) and is used to account for registration errors, to Gaussianize the data and to integrate imaging signals from a region around each voxel. However, it has also become a limitation of VBA-SPM based methods, since it is often chosen empirically and lacks spatial adaptivity to the shape and spatial extent of the region of interest, such as a region of atrophy or functional activity. In this paper, we propose a new framework, named optimally-discriminative voxel-based analysis (ODVBA), for determining the optimal spatially adaptive smoothing of images, followed by applying voxel-based group analysis. In ODVBA, nonnegative discriminative projection is applied regionally to get the direction that best discriminates between two groups, e.g., patients and controls; this direction is equivalent to local filtering by an optimal kernel whose coefficients define the optimally discriminative direction. By considering all the neighborhoods that contain a given voxel, we then compose this information to produce the statistic for each voxel. Finally, permutation tests are used to obtain a statistical parametric map of group differences. ODVBA has been evaluated using simulated data in which the ground truth is known and with data from an Alzheimer's disease (AD) study. The experimental results have shown that the proposed ODVBA can precisely describe the shape and location of structural abnormality.

Download full-text


Available from: Tianhao Zhang, Oct 06, 2014
    • "Local techniques extend univariate analysis by taking into account the neighborhood of a feature when detecting its relevance to the condition. While the statistical analyses are multivariate , based on Mahalanobis distance in (Kriegeskorte et al., 2006) and optimal filtering through nonnegative discriminative projection in (Zhang and Davatzikos, 2011), they are confined to small neighborhoods around each feature location. Although both approaches are interesting, they only explore local relationships and do not account for long distance spatially distributed patterns. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Group analysis of neuroimaging data is a vital tool for identifying anatomical and functional variations related to diseases as well as normal biological processes. The analyses are often performed on a large number of highly correlated measurements using a relatively smaller number of samples. Despite the correlation structure, the most widely used approach is to analyze the data using univariate methods followed by post-hoc corrections that try to account for the data's multivariate nature. Although widely used, this approach may fail to recover from the adverse effects of the initial analysis when local effects are not strong. Multivariate pattern analysis (MVPA) is a powerful alternative to the univariate approach for identifying relevant variations. Jointly analyzing all the measures, MVPA techniques can detect global effects even when individual local effects are too weak to detect with univariate analysis. Current approaches are successful in identifying variations that yield highly predictive and compact models. However, they suffer from lessened sensitivity and instabilities in identification of relevant variations. Furthermore, current methods' user-defined parameters are often unintuitive and difficult to determine. In this article, we propose a novel MVPA method for group analysis of high-dimensional data that overcomes the drawbacks of the current techniques. Our approach explicitly aims to identify all relevant variations using a "knock-out" strategy and the Random Forest algorithm. In evaluations with synthetic datasets the proposed method achieved substantially higher sensitivity and accuracy than the state-of-the-art MVPA methods, and outperformed the univariate approach when the effect size is low. In experiments with real datasets the proposed method identified regions beyond the univariate approach, while other MVPA methods failed to replicate the univariate results. More importantly, in a reproducibility study with the well-known ADNI dataset the proposed method yielded higher stability and power than the univariate approach. Copyright © 2015. Published by Elsevier Inc.
    NeuroImage 08/2015; 122. DOI:10.1016/j.neuroimage.2015.08.006 · 6.36 Impact Factor
  • Source
    • "While the searchlight mapping approach is very attractive , it only explores local relationships and does not account for long distance spatially distributed patterns. A more recent method that has some similarities with searchlight is the optimally-discriminative voxel-based analysis (ODVBA) [20]. ODVBA is a framework proposed to determine the optimal spatially adaptive smoothing. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Feature selection (FS) methods play two important roles in the context of neuroimaging based classification: potentially increase classification accuracy by eliminating irrelevant features from the model and facilitate interpretation by identifying sets of meaningful features that best discriminate the classes. Although the development of FS techniques specifically tuned for neuroimaging data is an active area of research, up to date most of the studies have focused on finding a subset of features that maximizes accuracy. However, maximizing accuracy does not guarantee reliable interpretation as similar accuracies can be obtained from distinct sets of features. In the current paper we propose a new approach for selecting features: SCoRS (survival count on random subsamples) based on a recently proposed Stability Selection theory. SCoRS relies on the idea of choosing relevant features that are stable under data perturbation. Data are perturbed by iteratively sub-sampling both features (subspaces) and examples. We demonstrate the potential of the proposed method in a clinical application to classify depressed patients versus healthy individuals based on functional magnetic resonance imaging data acquired during visualization of happy faces.
    IEEE Transactions on Medical Imaging 01/2014; 33(1):85-98. DOI:10.1109/TMI.2013.2281398 · 3.39 Impact Factor
  • Source
    • "denotes that x is the i th element in N, and δ N denotes the discrimination degree [9]. "
    [Show abstract] [Hide abstract]
    ABSTRACT: This significantly extends Multi-Voxel Pattern Analysis (MVPA) methods, such as the Searchlight and related methods, by building on an approach that was recently proposed for structural brain images, and was named Optimally-Discriminative Voxel-Based Analysis (ODVBA), which uses machine learning models to determine the optimal anisotropic filtering of images that enhances group differences. Precise spatial maps of activation are computed by tallying the weights of each voxel to all of the neighborhood in which it belongs, and significance maps are obtained via permutation testing. We adapt this idea to both single and multi-subject fMRI analysis. Both simulated data and real data from 12 adolescent subjects who completed a standard working memory task demonstrated the use of ODVBA in fMRI improves accuracy and spatial specificity of activation detection over Searchlight.
    Pattern Recognition in NeuroImaging (PRNI), 2012 International Workshop on; 07/2012
Show more