The Publication Database hosted by SPL
|
All Publications
Upload
Advanced Search
Gallery View
Download Statistics
Help
Import
Log in
Manifold Modeling for Brain Population Analysis
|
|
Institution: |
Scientific Computing and Imaging Institute, University of Utah, Salt Lake City, UT, USA. sgerber@cs.utah.edu |
Publisher: |
Elsevier |
Publication Date: |
Oct-2010 |
Journal: |
Med Image Anal |
Volume Number: |
14 |
Issue Number: |
5 |
Pages: |
643-53 |
Citation: |
Med Image Anal. 2010 Oct;14(5):643-53. |
PubMed ID: |
20579930 |
PMCID: |
PMC3020141 |
Keywords: |
Neurological Image Analysis, Population Analysis, Brain MRI, Manifold Learning, Computer Aided Clinical Diagnosis |
Appears in Collections: |
NA-MIC |
Sponsors: |
R01 EB007688-02 (EB) funded by NIBIB NIH HHS P01 AG03991 (AG) funded by NIA NIH HHS P20 MH071616 (MH) funded by NIMH NIH HHS P50 AG05681 (AG) funded by NIA NIH HHS R01 AG021910 (AG) funded by NIA NIH HHS U01 AG024904 (AG) funded by NIA NIH HHS U24 RR021382 (RR) funded by NCRR NIH HHS U54 EB005149 (EB) funded by NIBIB NIH HHS |
Generated Citation: |
Gerber S., Tasdizen T., Thomas Fletcher P., Joshi S., Whitaker R. Manifold Modeling for Brain Population Analysis. Med Image Anal. 2010 Oct;14(5):643-53. PMID: 20579930. PMCID: PMC3020141. |
| Downloaded: | 81 times. [view map] |
| Paper: | Download, View online |
| Export citation: |
This paper describes a method for building efficient representations of large sets of brain images. Our hypothesis is that the space spanned by a set of brain images can be captured, to a close approximation, by a low-dimensional, nonlinear manifold. This paper presents a method to learn such a low-dimensional manifold from a given data set. The manifold model is generative-brain images can be constructed from a relatively small set of parameters, and new brain images can be projected onto the manifold. This allows to quantify the geometric accuracy of the manifold approximation in terms of projection distance. The manifold coordinates induce a Euclidean coordinate system on the population data that can be used to perform statistical analysis of the population. We evaluate the proposed method on the OASIS and ADNI brain databases of head MR images in two ways. First, the geometric fit of the method is qualitatively and quantitatively evaluated. Second, the ability of the brain manifold model to explain clinical measures is analyzed by linear regression in the manifold coordinate space. The regression models show that the manifold model is a statistically significant descriptor of clinical parameters.
Additional Material
1 File (199.761kB)
Gerber-MedIA2010-fig6.jpg (199.761kB)