3D active shape modeling for cardiac MR and CT image segmentation

Leiden Repository

3D active shape modeling for cardiac MR and CT image segmentation

Type: Doctoral Thesis
Title: 3D active shape modeling for cardiac MR and CT image segmentation
Author: Assen, Hans Christiaan van
Publisher: Department Radiology, Faculty of Medicine / Leiden University Medical Center (LUMC), Leiden University
Issue Date: 2006-05-10
Keywords: Active Shape Model
Grid-computing
Data density
Fuzzy
Sparse
Image orientation
Abstract: 3D Active Shape Modeling is a technique to capture shape information from a training set containing characteristic shapes of, e.g., a heart. The description contains a mean shape, and shape variations (e.g. eigen deformations and eigen values). Many models based on these statistics, and used for medical purposes, are limited in their application by properties of the training set. These properties are, the radiological modality used for image acquisition (1), the orientation of the images (2), and the density of the data (3). In our model of the cardiac left ventricle, the limits above were relieved by not training on gray level information (1,2), using a Fuzzy Inference System for finding image features in CT and MR data (1), and weighted propagation of image features along the model surfaces (3). Evalutation of our model on both CT and MR showed almost equal performance. Evaluation of three different point-correspondences used for model- building did not clearly indicate one as best. By extended tuning using a grid-computing approach, and propagation of image features, we managed to achieve segmentation results on sparse data comparable to those of others on dense data. Our model is more widely applicable thanks to these developments.
Description: Promotor: J.H.C. Reiber, Co-promotor: B.P.F. Lelieveldt
Faculty: LUMC
Citation: Assen, H.C. van, 2006, Doctoral thesis, Leiden University
ISBN: 9085591635
Sponsor: Stichting Beeldverwerking Leiden Medis medical imaging systems bv Philips Medical Systems Nederland B.V. (Healthcare IT - Advanced Development)
Handle: http://hdl.handle.net/1887/4460
 

Files in this item

Description Size View
text/html Links to published articles 16.56Kb View/Open
application/pdf Cover 116.1Kb View/Open
application/pdf Propositions 27.95Kb View/Open
application/pdf Full text 16.76Mb View/Open
application/pdf Title page_Contents 114.0Kb View/Open
application/pdf Chapter 1 Introduction 2.036Mb View/Open
application/pdf Chapter 2 1.322Mb View/Open
application/pdf Chapter 3 1.041Mb View/Open
application/pdf Chapter 4 733.6Kb View/Open
application/pdf Chapter 5 3.242Mb View/Open
application/pdf Chapter 6 1.969Mb View/Open
application/pdf Chapter 7 6.117Mb View/Open
application/pdf Chapter 8 891.4Kb View/Open
application/pdf Chapter 9 Summary_Conclusions 106.7Kb View/Open
application/pdf Chapter 10 Summary in Dutch_Conclusions 111.3Kb View/Open
application/pdf Bibliography 141.8Kb View/Open
application/pdf List of publications 76.99Kb View/Open
application/pdf Acknowledgements 52.00Kb View/Open
application/pdf Curriculum Vitae 32.86Kb View/Open

This item appears in the following Collection(s)