Segmentation of the evolving left ventricle by learning the dynamics

Warning The system is temporarily closed to updates for reporting purpose.

Sun, Walter and Çetin, Müjdat and Chan, Ray and Willsky, Alan S. (2008) Segmentation of the evolving left ventricle by learning the dynamics. In: IEEE International Symposium on Biomedical Imaging, Paris, France

PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader

Official URL: http://dx.doi.org/10.1109/ISBI.2008.4540974


We propose a method for recursive segmentation of the left ventricle (LV) across a temporal sequence of magnetic resonance (MR) images. The approach involves a technique for learning the LV boundary dynamics together with a particle-based inference algorithm on a loopy graphical model capturing the temporal periodicity of the heart. The dynamic system state is a low-dimensional representation of the boundary, and boundary estimation involves incorporating curve evolution into state estimation. By formulating the problem as one of state estimation, the segmentation at each particular time is based not only on the data observed at that instant, but also on predictions based on past and future boundary estimates. We assess and demonstrate the effectiveness of the proposed framework on a large data set of breath-hold cardiac MR image sequences.

Item Type:Papers in Conference Proceedings
Uncontrolled Keywords:Magnetic resonance imaging cardiac imaging curve evolution graphical models image segmentation learning left ventricle particle filtering recursive estimation
Subjects:T Technology > TK Electrical engineering. Electronics Nuclear engineering
ID Code:10529
Deposited By:Müjdat Çetin
Deposited On:11 Nov 2008 23:02
Last Modified:22 Jul 2019 10:19

Repository Staff Only: item control page