Name
Abstract | ||
|---|---|---|
Non-linear image registration is one of the most challenging task in medical image analysis. In this work, we propose an extension of the well-established diffeomorphic Demons registration algorithm to take into account geometric constraints. Combining the deformation field induced by the image and the geometry, we define a mathematically sound framework to jointly register images and geometric descriptors such as fibers or sulcal lines. We demonstrate this framework by registering simultaneously T1 images and 50 fiber bundles consistently extracted in 12 subjects. Results show the improvement of fibers alignment while maintaining, and sometimes improving image registration. Further comparisons with non-linear T1 and tensor registration demonstrate the superiority of the Geometric Demons over their purely iconic counterparts. |
Year | DOI | Venue |
|---|---|---|
2011 | 10.1007/978-3-642-24446-9_2 | MBIA |
Keywords | Field | DocType |
joint t1,image registration,geometric demons,tensor registration,account geometric constraint,non-linear image registration,geometric descriptors,medical image analysis,well-established diffeomorphic demons registration,t1 image,brain fiber diffeomorphic registration,fibers alignment,diffeomorphism | Computer vision,Tensor,Fiber,Artificial intelligence,Deformation (mechanics),Image registration,Mathematics,Diffeomorphism,Fiber bundle | Conference |
Volume | ISSN | Citations |
7012 | 0302-9743 | 3 |
PageRank | References | Authors |
0.43 | 14 | 4 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Viviana Siless | 1 | 37 | 3.51 |
| Pamela Guevara | 2 | 174 | 13.40 |
| Xavier Pennec | 3 | 5021 | 357.08 |
| P Fillard | 4 | 1238 | 75.70 |