A new paradigm for the characterization of structure appearance is proposed, based on a combination of grey-level intensity data and a shape descriptor derived from a priori Principal Components Analysis of 3D deformation vector fields. Generated without external intervention, it extends more classical, 2D manual landmark-based shape models. Application of this novel concept leads to a method for the segmentation of medial temporal lobe structures from brain magnetic resonance images. The strategy employed for segmentation is similar to that used in other appearance-based approaches, while the resulting output data is identical to ANIMAL, a non-linear registration and segmentation technique. The proposed method was tested on a data set of 80 normal subjects for which manual and ANIMAL segmentated structures were available. Experimental results demonstrated the robustness and flexibility of this method. Segmentation accuracy, measured by overlap statistics, is marginally lower (<2%) than ANIMAL, while processing time is 6 times faster. Finally, the applicability of this concept towards shape deformation analysis is presented.
| Identifer | oai:union.ndltd.org:LACETR/oai:collectionscanada.gc.ca:QMM.33753 |
| Date | January 2001 |
| Creators | Duchesne, Simon. |
| Contributors | Pike, G. B. (advisor), Collins, D. L. (advisor) |
| Publisher | McGill University |
| Source Sets | Library and Archives Canada ETDs Repository / Centre d'archives des thèses électroniques de Bibliothèque et Archives Canada |
| Language | English |
| Detected Language | English |
| Type | Electronic Thesis or Dissertation |
| Format | application/pdf |
| Coverage | Master of Science (Department of Medical Radiation Physics.) |
| Rights | All items in eScholarship@McGill are protected by copyright with all rights reserved unless otherwise indicated. |
| Relation | alephsysno: 001862710, proquestno: MQ78870, Theses scanned by UMI/ProQuest. |
Page generated in 0.0011 seconds