Article

Unbiased Tensor-Based Morphometry: Improved Robustness and Sample Size Estimates for Alzheimer's Disease Clinical Trials.

Imaging Genetics Center, Laboratory of Neuro Imaging, Dept. of Neurology, UCLA School of Medicine, Los Angeles, CA.
NeuroImage (Impact Factor: 6.13). 11/2012; 66. DOI: 10.1016/j.neuroimage.2012.10.086
Source: PubMed

ABSTRACT Various neuroimaging measures are being evaluated for tracking Alzheimer's disease progression in therapeutic trials, including measures of structural brain change based on repeated scanning of patients with magnetic resonance imaging (MRI). Methods to compute brain change must be robust to scan quality. Biases may arise if any scans are thrown out, as this can lead to the true changes being overestimated or underestimated. Here we analyzed the full ADNI-1 MRI dataset and assessed several sources of bias that can arise when tracking brain changes with structural brain imaging methods, as part of a pipeline for tensor-based morphometry (TBM). In all healthy subjects who completed MRI scanning at screening, 6, 12, and 24months, brain atrophy was essentially linear with no detectable bias in longitudinal measures. In power analyses for clinical trials based on these change measures, only 39AD and 95 MCI subjects were needed for a 24-month trial to detect a 25% reduction in the average rate of change using a two-sided test (α=0.05, power=80%). Further sample size reductions were achieved by stratifying the data into Apolipoprotein E (ApoE) ε4 carriers vs. non-carriers. We show how selective data exclusion affects sample size estimates, motivating an objective comparison of different analysis techniques based on statistical power and robustness. TBM is an unbiased, robust, high-throughput imaging surrogate marker for large, multi-site neuroimaging studies and clinical trials of AD and MCI.

Download full-text

Full-text

Available from: Clifford R Jack, Jun 16, 2014
1 Follower
 · 
173 Views
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Multi-atlas based methods have been recently used for classification of Alzheimer's disease (AD) and its prodromal stage, that is, mild cognitive impairment (MCI). Compared with traditional single-atlas based methods, multiatlas based methods adopt multiple predefined atlases and thus are less biased by a certain atlas. However, most existing multiatlas based methods simply average or concatenate the features from multiple atlases, which may ignore the potentially important diagnosis information related to the anatomical differences among different atlases. In this paper, we propose a novel view (i.e., atlas) centralized multi-atlas classification method, which can better exploit useful information in multiple feature representations from different atlases. Specifically, all brain images are registered onto multiple atlases individually, to extract feature representations in each atlas space. Then, the proposed view-centralized multi-atlas feature selection method is used to select the most discriminative features from each atlas with extra guidance from other atlases. Next, we design a support vector machine (SVM) classifier using the selected features in each atlas space. Finally, we combine multiple SVM classifiers for multiple atlases through a classifier ensemble strategy for making a final decision. We have evaluated our method on 459 subjects [including 97 AD, 117 progressive MCI (p-MCI), 117 stable MCI (s-MCI), and 128 normal controls (NC)] from the Alzheimer's Disease Neuroimaging Initiative database, and achieved an accuracy of 92.51% for AD versus NC classification and an accuracy of 78.88% for p-MCI versus s-MCI classification. These results demonstrate that the proposed method can significantly outperform the previous multi-atlas based classification methods. Hum Brain Mapp, 2015. © 2014 Wiley Periodicals, Inc.
    Human Brain Mapping 01/2015; 36(5). DOI:10.1002/hbm.22741 · 6.92 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: The presence of brain atrophy and its progression in early Parkinson's disease (PD) are still a matter of debate, particularly in patients without cognitive impairment. The aim of this longitudinal study was to assess whether PD patients who remain cognitively intact develop progressive atrophic changes in the early stages of the disease. For this purpose, we employed high-resolution T1-weighted MR imaging to compare 22 drug-naïve de novo PD patients without cognitive impairment to 17 age-matched control subjects, both at baseline and at three-year follow-up. We used tensor-based morphometry to explore the presence of atrophic changes at baseline and to compute yearly atrophy rates, after which we performed voxel-wise group comparisons using threshold-free cluster enhancement. At baseline, we did not observe significant differences in regional atrophy in PD patients with respect to control subjects. In contrast, PD patients showed significantly higher yearly atrophy rates in the prefrontal cortex, anterior cingulum, caudate nucleus, and thalamus when compared to control subjects. Our results indicate that even cognitively preserved PD patients show progressive cortical and subcortical atrophic changes in regions related to cognitive functions and that these changes are already detectable in the early stages of the disease. Hum Brain Mapp, 2014. © 2014 Wiley Periodicals, Inc.
    Human Brain Mapping 08/2014; 35(8). DOI:10.1002/hbm.22449 · 6.92 Impact Factor
  • 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