Name
Title | ||
|---|---|---|
3D elastic registration improves HARDI-derived fiber alignment and automated tract clustering |
Abstract | ||
|---|---|---|
High angular resolution diffusion imaging (HARDI) allows population studies of fiber integrity and connectivity. Tractography can extract individual fibers. For group studies, fibers must be clustered into recognizable bundles found consistently across subjects. Nonlinear image registration may improve population clustering. To test this, we performed whole-brain tractography with an orientation distribution function based Hough transform method in 20 young adults scanned with 4 Tesla, 105-gradient HARDI. We warped all extracted fibers to a geometrically-centered template using a 3D elastic registration driven by fractional anisotropy maps, to align embedded tracts. Fiber alignment was evaluated by calculating distances among corresponding fibers across subjects. Before and after warping, we performed spectral clustering of the fibers using a k-means method, based on eigenvectors of a fiber similarity matrix. In tests with an overlap metric, non-rigid fiber warping yielded more robust clustering results. Non-rigid warping is therefore advantageous for population studies using multi-subject tract clustering. |
Year | DOI | Venue |
|---|---|---|
2011 | 10.1109/ISBI.2011.5872531 | ISBI |
Keywords | Field | DocType |
population clustering,pattern clustering,tractography,nonrigid fiber warping,biodiffusion,k-means method,fiber integrity,hardi,whole brain tractography,spectral clustering,fiber similarity matrix,3d elastic registration,fiber connectivity,image registration,non-rigid fiber warping,fractional anisotropy maps,biomedical mri,high angular resolution diffusion imaging,hardi-derived fiber alignment,eigenvectors,brain,hough transform,fiber alignment,automated tract clustering,eigenvalues and eigenfunctions,medical image processing,nonlinear image registration,hough transforms,multisubject tract clustering,k means,fractional anisotropy,image resolution,clustering algorithms,young adult,biomedical imaging,population study | Spectral clustering,Computer vision,Population,Image warping,Pattern recognition,Fiber,Computer science,Hough transform,Artificial intelligence,Cluster analysis,Tractography,Image registration | Conference |
ISSN | ISBN | Citations |
1945-7928 E-ISBN : 978-1-4244-4128-0 | 978-1-4244-4128-0 | 7 |
PageRank | References | Authors |
0.64 | 11 | 7 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Yan Jin | 1 | 81 | 7.65 |
| Yonggang Shi | 2 | 598 | 54.47 |
| Neda Jahanshad | 3 | 336 | 42.81 |
| Iman Aganj | 4 | 195 | 18.93 |
| Guillermo Sapiro | 5 | 14813 | 1051.92 |
| Arthur W. Toga | 6 | 3128 | 261.46 |
| Paul Thompson | 7 | 3860 | 321.32 |