M
Mehmet Üzümcü
Researcher at Leiden University Medical Center
Publications - 8
Citations - 335
Mehmet Üzümcü is an academic researcher from Leiden University Medical Center. The author has contributed to research in topics: Active appearance model & Point distribution model. The author has an hindex of 8, co-authored 8 publications receiving 328 citations. Previous affiliations of Mehmet Üzümcü include Leiden University.
Papers
More filters
Journal ArticleDOI
Time continuous tracking and segmentation of cardiovascular magnetic resonance images using multidimensional dynamic programming.
Mehmet Üzümcü,Rob J. van der Geest,Cory Swingen,Johan H. C. Reiber,Boudewijn P. F. Lelieveldt +4 more
TL;DR: A semiautomatic method for time-continuous contour detection in all phases of the cardiac cycle in magnetic resonance sequences based on multidimensional dynamic programming, which compares favorable to the best-reported results in recent literature.
Proceedings ArticleDOI
Independent component analysis in statistical shape models
TL;DR: This paper explores the use of an alternative shape decomposition, Independent Component Analysis (ICA), which does not assume a Gaussian distribution of the input data and investigates four methods for sorting the ICA vectors.
Book ChapterDOI
ICA vs. PCA Active Appearance Models: Application to Cardiac MR Segmentation
TL;DR: The use of ICA results in a substantial improvement in border localization accuracy over a PCA-based model, and a method for ordering the Independent Components is presented.
Journal ArticleDOI
Multi-view active appearance models for consistent segmentation of multiple standard views: application to long- and short-axis cardiac MR images
TL;DR: The presented validation shows that the AAM method combines a high robustness with clinically acceptable accuracy, and therefore is a promising tool to further automate the integral quantitative analysis of cardiac MR patient examinations.
Journal ArticleDOI
Multiview active appearance models for simultaneous segmentation of cardiac 2- and 4-chamber long-axis magnetic resonance images
Mehmet Üzümcü,Rob J. van der Geest,Milan Sonka,Hildo J. Lamb,Johan H. C. Reiber,Boudewijn P. F. Lelieveldt +5 more
TL;DR: It is concluded that this model-based method for the simultaneous detection of 2- and 4-chamber endocardial and epicardial contours in end-diastolic and end-systolic phases of MR images enables rapid analysis of the cardiac left ventricular function with little user interaction.