Automatic 2D segmentation of the left ventricle in tagged cardiac MRI using motion information

A new algorithm is presented to automatically segment the left ventricle from tagged MR images using motion information. This segmentation method is based on a deformable template which is fitted to tags' envelope image through an iterative process. Motion information is used for initializing the template. The method has been evaluated both on simulated and 5 in vivo datasets. A 5 slice levels, 36 frames per slice dataset is fully segmented in less than 10 minutes. The method proposed here has the potential to overcome the main drawbacks of previous approaches, such as user supervision and computing time, to foresee routine clinical use of tagged cardiac MRI.

[1]  E. McVeigh,et al.  Model‐free reconstruction of three‐dimensional myocardial strain from planar tagged MR images , 1997, Journal of magnetic resonance imaging : JMRI.

[2]  E. McVeigh,et al.  Differentiation of viable and nonviable myocardium by the use of three-dimensional tagged MRI in 2-day-old reperfused canine infarcts. , 1999, Circulation.

[3]  Alistair A. Young,et al.  Tracking and finite element analysis of stripe deformation in magnetic resonance tagging , 1995, IEEE Trans. Medical Imaging.

[4]  Patrick Clarysse,et al.  Two-dimensional spatial and temporal displacement and deformation field fitting from cardiac magnetic resonance tagging , 2000, Medical Image Anal..

[5]  Jerry L. Prince,et al.  Snakes, shapes, and gradient vector flow , 1998, IEEE Trans. Image Process..

[6]  Demetri Terzopoulos,et al.  Deformable models in medical image analysis: a survey , 1996, Medical Image Anal..

[7]  E. McVeigh,et al.  Four-dimensional B-spline based motion analysis of tagged MR images: introduction and in vivo validation. , 2000, Physics in medicine and biology.

[8]  Jerry L Prince,et al.  Tracking MR tag surfaces using a spatiotemporal filter and interpolator , 1999, Int. J. Imaging Syst. Technol..

[9]  Litao Yan,et al.  Unsupervised reconstruction of a three‐dimensional left ventricular strain from parallel tagged cardiac images , 2003, Magnetic resonance in medicine.

[10]  Thomas S. Denney,et al.  Estimation and detection of myocardial tags in MR image without user-defined myocardial contours , 1999, IEEE Transactions on Medical Imaging.

[11]  L. Axel,et al.  Heart wall motion: improved method of spatial modulation of magnetization for MR imaging. , 1989, Radiology.

[12]  Jerry L. Prince,et al.  Imaging heart motion using harmonic phase MRI , 2000, IEEE Transactions on Medical Imaging.

[13]  W. O'Dell,et al.  Three-dimensional myocardial deformations: calculation with displacement field fitting to tagged MR images. , 1995, Radiology.

[14]  Amir A. Amini,et al.  Spatio-temporal tracking of myocardial deformations with a 4-D B-spline model from tagged MRI , 1999, IEEE Transactions on Medical Imaging.

[15]  E.R. McVeigh,et al.  Implementation of displacement field fitting for calculating 3D myocardial deformations from parallel-tagged MR images , 1994, Proceedings of 16th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[16]  Patrick Clarysse,et al.  An elasticity-based region model and its application to the estimation of the heart deformation in tagged MRI , 2000, Proceedings 2000 International Conference on Image Processing (Cat. No.00CH37101).

[17]  E. Zerhouni,et al.  Human heart: tagging with MR imaging--a method for noninvasive assessment of myocardial motion. , 1988, Radiology.