Abstract
This paper introduces a novel groupwise data-driven algorithm for non-rigid registration. The motivation behind the algorithm is to enable the analysis of groups of registered images; to this end, the algorithm automatically constructs a low-dimensional, common representation of the warp fields. We demonstrate the algorithm on an example set of 2D medical images, and show that we can obtain good registration across the set, with automatic detection and correction of misaligned examples, whilst still maintaining a low-dimensional representation.
Original language | English |
---|---|
Title of host publication | Lecture Notes in Computer Science|Lect. Notes Comput. Sci. |
Editors | R.E. Ellis, T.M. Peters |
Pages | 771-779 |
Number of pages | 8 |
Volume | 2879 |
Publication status | Published - 2003 |
Event | Medical Image Computing and Computer-Assisted Intervention, MICCAI 2003 - 6th International Conference Proceedings - Montreal, Que. Duration: 1 Jul 2003 → … http://<Go to ISI>://000188180400094 |
Publication series
Name | Lecture Notes in Computer Science |
---|
Conference
Conference | Medical Image Computing and Computer-Assisted Intervention, MICCAI 2003 - 6th International Conference Proceedings |
---|---|
City | Montreal, Que. |
Period | 1/07/03 → … |
Internet address |