TY - JOUR
T1 - ODVBA
T2 - Optimally-discriminative voxel-based analysis
AU - Zhang, Tianhao
AU - Davatzikos, Christos
N1 - Funding Information:
Manuscript received December 22, 2010; revised January 29, 2011; accepted January 29, 2011. Date of publication February 14, 2011; date of current version August 03, 2011. This work was supported by the National Institutes of Health (NIH) under Grant R01AG14971. The authors would like to thank Alzheimer’s Disease Neuroimaging Initiative (ADNI) for the data collection and sharing (supported by NIH under Grant U01 AG024904). ADNI is funded by the National Institute on Aging, the National Institute of Biomedical Imaging and Bioengineering and through generous contributions from the organizations as listed at http://www.adni-info.org. ADNI data are disseminated by the Laboratory for Neuro Imaging at the University of California, Los Angeles. This work was also supported in part by the NIH under Grant P30 AG010129 and Grant K01 AG030514 and in part by the Dana Foundation. Asterisk indicates corresponding author. *T. Zhang is with the Section of Biomedical Image Analysis, Department of Radiology, University of Pennsylvania, Philadelphia, PA 19104 USA (e-mail: tianhao.zhang@uphs.upenn.edu).
PY - 2011/8
Y1 - 2011/8
N2 - 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.
AB - 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.
KW - Alzheimer's disease
KW - Alzheimer's disease neuroimaging initiative (ADNI)
KW - Gaussian smoothing
KW - nonnegative discriminative projection (NDP)
KW - optimally-discriminative voxel-based analysis
KW - statistical parametric mapping
KW - voxel-based morphometry
UR - http://www.scopus.com/inward/record.url?scp=79961179600&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=79961179600&partnerID=8YFLogxK
U2 - 10.1109/TMI.2011.2114362
DO - 10.1109/TMI.2011.2114362
M3 - Article
C2 - 21324774
AN - SCOPUS:79961179600
SN - 0278-0062
VL - 30
SP - 1441
EP - 1454
JO - IEEE transactions on medical imaging
JF - IEEE transactions on medical imaging
IS - 8
M1 - 5712211
ER -