A non parametric mixed-effect model for population analysis: Application to Alzheimer's disease data

Published on May 2, 2012 in ISBI (International Symposium on Biomedical Imaging)
· DOI :10.1109/ISBI.2012.6235757
Juan David Ospina8
Estimated H-index: 8
(French Institute of Health and Medical Research),
Oscar Acosta21
Estimated H-index: 21
(French Institute of Health and Medical Research)
+ 2 AuthorsPascal Haigron21
Estimated H-index: 21
(French Institute of Health and Medical Research)
Sources
Abstract
In population analysis, the images of different groups can be compared to locate the effects of a particular disease or treatment and also to generate biomarkers that help in the diagnosis process. Voxel-Based Morphometry (VBM) is a set of widely extended techniques to compare groups of images. VBM involves image normalization, image smoothing, statistical map generation and correction for hypothesis testing. In this paper, we propose the use of a nonparametric mixed-effect model to study Alzheimer's Disease (AD). The proposed method can handle covariates and through the integration of the smoothing and statistical map generation, individual specificities can be controlled. Moreover, it allows the reconstruction of the typical shapes for each group and it can be advantageously used as another VBM implementation.
📖 Papers frequently viewed together
2010MICCAI: Medical Image Computing and Computer-Assisted Intervention
2 Citations
6 Citations
20135.90NeuroImage
6 Authors (Yimei Li, ..., Hongtu Zhu)
32 Citations
References21
Newest
Sep 18, 2011 in ICML (International Conference on Machine Learning)
#1Juan David Ospina (National University of Colombia)H-Index: 8
#2Oscar Acosta (University of Rennes)H-Index: 21
Last. Renaud de Crevoisier (University of Rennes)H-Index: 28
view all 8 authors...
Voxel-wise comparisons have been largely used in the analysis of populations to identify biomarkers for pathologies, disease progression, or to predict a treatment outcome. On the basis of a good interindividual spatial alignment, 3D maps are produced, allowing to localise regions where significant differences between groups exist. However, these techniques have received some criticism as they rely on conditions wich are not always met. Firstly, the results may be affected by misregistrations; s...
6 CitationsSource
#1Marnix G. Witte (NKI-AVL: Netherlands Cancer Institute)H-Index: 18
#2Wilma D. Heemsbergen (NKI-AVL: Netherlands Cancer Institute)H-Index: 29
Last. Marcel van Herk (NKI-AVL: Netherlands Cancer Institute)H-Index: 75
view all 7 authors...
Purpose For prostate cancer patients at risk for subclinical spread of the disease, we investigated whether incidental dose outside the target was associated with tumor control. Methods and Materials We selected 352 intermediate-risk (mainly T2b-T3a) and high-risk (mainly T3b) patients treated in a randomized trial. Target volume was prostate (68–78 Gy) and seminal vesicles (50–78 Gy). Failure (clinical or biochemical) was evaluated at 4 years. To compare three-dimensional dose distributions, an...
34 CitationsSource
#1Hidemasa Takao (UTokyo: University of Tokyo)H-Index: 30
#2Osamu Abe (UTokyo: University of Tokyo)H-Index: 67
Last. Kuni Ohtomo (UTokyo: University of Tokyo)H-Index: 74
view all 7 authors...
Abstract The hemispheres of the human brain are functionally and structurally asymmetric. The purpose of this study was to evaluate the effects of aging on gray and white matter asymmetry. Two hundred twenty-six right-handed normal volunteers aged 21–71 years were included in this study. The effects of aging on gray matter volume asymmetry and white matter fractional anisotropy asymmetry were evaluated with use of voxel-based morphometry and voxel-based analysis of fractional anisotropy maps der...
20 CitationsSource
#1Oscar Acosta (CSIRO: Commonwealth Scientific and Industrial Research Organisation)H-Index: 21
#2Pierrick Bourgeat (CSIRO: Commonwealth Scientific and Industrial Research Organisation)H-Index: 34
Last. Sebastien Ourselin (UCL: University College London)H-Index: 91
view all 6 authors...
Accurate cortical thickness estimation is important for the study of many neurodegenerative diseases. Many approaches have been previously proposed, which can be broadly categorised as mesh-based and voxel-based. While the mesh-based approaches can potentially achieve subvoxel resolution, they usually lack the computational efficiency needed for clinical applications and large database studies. In contrast, voxel-based approaches, are computationally efficient, but lack accuracy. The aim of this...
84 CitationsSource
#1Gerard R. Ridgway (UCL: University College London)H-Index: 49
#2Susie M.D. Henley (UCL: University College London)H-Index: 24
Last. Nick C. Fox (UCL: University College London)H-Index: 152
view all 6 authors...
Voxel-based morphometry [Ashburner, J. and Friston, K.J., 2000. Voxel-based morphometry—the methods. NeuroImage 11(6 Pt 1), 805–821] is a commonly used tool for studying patterns of brain change in development or disease and neuroanatomical correlates of subject characteristics. In performing a VBM study, many methodological options are available; if the study is to be easily interpretable and repeatable, the processing steps and decisions must be clearly described. Similarly, unusual methods an...
212 CitationsSource
#1Alexis RocheH-Index: 28
#2Sébastien MériauxH-Index: 22
Last. Bertrand Thirion (IRIA: French Institute for Research in Computer Science and Automation)H-Index: 49
view all 4 authors...
This technical note describes a collection of test statistics accounting for estimation uncertainties at the within-subject level, that can be used as alternatives to the standard t statistic in one-sample random-effect analyses, i.e. when testing the mean effect of a population. We build such test statistics by estimating the across-subject distribution of the effects using maximum likelihood under a nonparametric mixed-effect model. For inference purposes, the statistics are calibrated using p...
28 CitationsSource
#1Wilma D. Heemsbergen (NKI-AVL: Netherlands Cancer Institute)H-Index: 29
#2Mischa S. Hoogeman (EUR: Erasmus University Rotterdam)H-Index: 48
Last. Joos V. Lebesque (NKI-AVL: Netherlands Cancer Institute)H-Index: 18
view all 6 authors...
Purpose: To investigate whether a large rectum filling visible on the planning CT scan was associated with a decrease in freedom from any failure (FFF) and freedom from clinical failure (FFCF) for prostate cancer patients. Methods and Materials: Patients from the Dutch trial (78 Gy vs. 68 Gy) with available acute toxicity data were analyzed ( n = 549). A 10-mm margin was applied for the first 68 Gy and 0–5 mm for the 10-Gy boost. The dose in the seminal vesicles (SVs) was prescribed within four ...
144 CitationsSource
This article reviews four commonly used approaches to group modeling in fMRI. The methods differ in their computational intensity (FSL with its two-level estimation including MCM being the most intense) and assumptions (SPM2 with its assumption of spatially homogeneous covariance V/sub g/ being most restrictive). This study also distinguishes fixed-effects models from mixed-effects models and motivates the importance of a mixed-effects model for group fMRI analysis. The sections following that d...
67 CitationsSource
#1Hulin WuH-Index: 46
#2Jin-Ting ZhangH-Index: 1
Last. Zhang Jin‐TingH-Index: 1
view all 2 authors...
Preface. Acronyms. 1. Introduction. 2. Parametric Mixed-Effects Models. 3. Nonparametric Regression Smoothers. 4. Local Polynomial Methods. 5. Regression Spline Methods. 6. Smoothing Splines Methods. 7. Penalized Spline Methods. 8. Semiparametric Models. 9. Time-Varying Coefficient Models. 10. Discrete Longitudinal Data. References. Index.
112 Citations
#1Yoko HirataH-Index: 11
#2Hiroshi Matsuda (Saitama Medical University)H-Index: 50
Last. Hirotsugu SamejimaH-Index: 8
view all 9 authors...
Abstract We assessed the accuracy of voxel-based morphometry (VBM) using a three-dimensional T1-weighted MRI in discriminating Alzheimer's disease (AD) in the very early stage of amnestic type of mild cognitive impairment and age-matched healthy controls. We randomly divided these subjects into two groups. The first group comprising 30 AD patients and 41 controls was used to identify the area with the most significant gray matter loss in patients compared to normal controls based on the voxel-ba...
259 CitationsSource
Cited By1
Newest
#1Quentin Duché (University of Rennes)H-Index: 3
#2Hervé Saint-Jalmes (University of Rennes)H-Index: 18
Last. Olivier Salvado (CSIRO: Commonwealth Scientific and Industrial Research Organisation)H-Index: 44
view all 8 authors...
: MP2RAGE is a T1 weighted MRI sequence that estimates a composite image providing much reduction of the receiver bias, has a high intensity dynamic range, and provides an estimate of T1 mapping. It is, therefore, an appealing option for brain morphometry studies. However, previous studies have reported a difference in cortical thickness computed from MP2RAGE compared with widely used Multi-Echo MPRAGE. In this article, we demonstrated that using standard segmentation and partial volume estimati...
5 CitationsSource