Penalized Likelihood Phenotyping: Unifying Voxelwise Analyses and Multi-Voxel Pattern Analyses in Neuroimaging

University of Wisconsin-Madison, Madison, WI, USA, .
Neuroinformatics (Impact Factor: 3.1). 02/2013; 11(2). DOI: 10.1007/s12021-012-9175-9
Source: PubMed

ABSTRACT Neuroimage phenotyping for psychiatric and neurological disorders is performed using voxelwise analyses also known as voxel based analyses or morphometry (VBM). A typical voxelwise analysis treats measurements at each voxel (e.g. fractional anisotropy, gray matter probability) as outcome measures to study the effects of possible explanatory variables (e.g. age, group) in a linear regression setting. Furthermore, each voxel is treated independently until the stage of correction for multiple comparisons. Recently, multi-voxel pattern analyses (MVPA), such as classification, have arisen as an alternative to VBM. The main advantage of MVPA over VBM is that the former employ multivariate methods which can account for interactions among voxels in identifying significant patterns. They also provide ways for computer-aided diagnosis and prognosis at individual subject level. However, compared to VBM, the results of MVPA are often more difficult to interpret and prone to arbitrary conclusions. In this paper, first we use penalized likelihood modeling to provide a unified framework for understanding both VBM and MVPA. We then utilize statistical learning theory to provide practical methods for interpreting the results of MVPA beyond commonly used performance metrics, such as leave-one-out-cross validation accuracy and area under the receiver operating characteristic (ROC) curve. Additionally, we demonstrate that there are challenges in MVPA when trying to obtain image phenotyping information in the form of statistical parametric maps (SPMs), which are commonly obtained from VBM, and provide a bootstrap strategy as a potential solution for generating SPMs using MVPA. This technique also allows us to maximize the use of available training data. We illustrate the empirical performance of the proposed framework using two different neuroimaging studies that pose different levels of challenge for classification using MVPA.

Download full-text


Available from: Nagesh Adluru, Aug 23, 2015
1 Follower
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: The diagonal and off-diagonal elements of the effective self-diffusion tensor, Deff, are related to the echo intensity in an NMR spin-echo experiment. This relationship is used to design experiments from which Deff is estimated. This estimate is validated using isotropic and anisotropic media, i.e., water and skeletal muscle. It is shown that significant errors are made in diffusion NMR spectroscopy and imaging of anisotropic skeletal muscle when off-diagonal elements of Deff are ignored, most notably the loss of information needed to determine fiber orientation. Estimation of Deff provides the theoretical basis for a new MRI modality, diffusion tensor imaging, which provides information about tissue microstructure and its physiologic state not contained in scalar quantities such as T1, T2, proton density, or the scalar apparent diffusion constant.
    Journal of Magnetic Resonance Series B 04/1994; 103(3):247-54. DOI:10.1006/jmrb.1994.1037 · 2.53 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: fMRI analysis techniques are presented that test functional hypotheses at the region of interest (ROI) level. An SPM-compatible Matlab toolbox has been developed that allows the creation of subject-specific ROI masks based on anatomical markers and the testing of functional hypotheses on the regional response using multivariate time-series analysis techniques. The combined application of subject-specific ROI definition and region-level functional analysis is shown to appropriately compensate for intersubject anatomical variability, offering finer localization and increased sensitivity to task-related effects than standard techniques based on whole-brain normalization and voxel or cluster-level functional analysis, while providing a more direct link between discrete brain region hypotheses and the statistical analyses used to test them.
    NeuroImage 09/2003; 19(4):1303-16. DOI:10.1016/S1053-8119(03)00188-5 · 6.36 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: This paper presents a general discriminative dimensionality reduction framework for multi-modal image-based classification in medical imaging datasets. The major goal is to use all modalities simultaneously to transform very high dimensional image to a lower dimensional representation in a discriminative way. In addition to being discriminative, the proposed approach has the advantage of being clinically interpretable. We propose a framework based on regularized tensor decomposition. We show that different variants of tensor factorization imply various hypothesis about data. Inspired by the idea of multi-view dimensionality reduction in machine learning community, two different kinds of tensor decomposition and their implications are presented. We have validated our method on a multi-modal longitudinal brain imaging study. We compared this method with a publically available classification software based on SVM that has shown state-of-the-art classification rate in number of publications.
Show more