The Publication Database hosted by SPL
|
All Publications
Upload
Advanced Search
Gallery View
Download Statistics
Help
Import
Log in
Tractography Segmentation Using a Hierarchical Dirichlet Processes Mixture Model
|
|
Institution: |
1Computer Science and Artificial Intelligence Lab, Massachusetts Institute of Technology, Cambridge, MA, 02139, USA 2Laboratory of Mathematical Imaging, Department of Radiology, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, USA. |
Publisher: |
Inf Process Med Imaging IPMI 2009 |
Publication Date: |
Jul-2009 |
Citation: |
Inf Process Med Imaging. 2009;21:101-13. |
PubMed ID: |
19694256 |
Appears in Collections: |
NAC, NA-MIC, NCIGT |
Generated Citation: |
Wang X, Grimson W, Westin C. Tractography Segmentation Using a Hierarchical Dirichlet Processes Mixture Model. Inf Process Med Imaging. 2009;21:101-13. PMID: 19694256. |
| Downloaded: | 195 times. [view map] |
| Paper: | Download, View online |
| Export citation: |
In this paper, we propose a new nonparametric Bayesian framework to cluster white matter fiber tracts into bundles using a hi- erarchical Dirichlet processes mixture (HDPM) model. The number of clusters is automatically learnt from data with a Dirichlet process (DP) prior instead of being manually specified. After the models of bundles have been learnt from training data without supervision, they can be used as priors to cluster/classify fibers of new subjects. When cluster- ing fibers of new subjects, new clusters can be created for structures not observed in the training data. Our approach does not require com- puting pairwise distances between fibers and can cluster a huge set of fibers across multiple subjects without subsampling. We present results on multiple data sets, the largest of which has more than 120,000 fibers.
Additional Material
1 File (271.042kB)
XWang-IPMI2009-fig6.jpg (271.042kB)