Abstract
This paper describes a segmentation technique to automatically extract the myocardium in 4D cardiac MR images for quantitative cardiac analysis and the diagnosis of patients. An approximate outline of the left ventricle is obtained either from automatic localization based on the maximum discrimination method or from copying a template shape during propagation. The histogram of the image is analyzed and divided into peaks using the EM algorithm to produce a region-based segmentation. This result and the image gradient are combined to obtain candidate boundaries for the left ventricle by deforming the contour using a graph search active contour approach. The final boundary is chosen using a minimum cut graph algorithm, spline fitting, or point pattern matching to maintain the shape of the template. We have experimented with the proposed method on a large number of patients and present some quantitative and qualitative results.
Chapter PDF
References
J. S. Duncan and N. Ayache, “Medical image analysis: Progress over two decades and the challenges ahead”, IEEE Trans. PAMI, 22(1):85–106, 2000.
S. R. Fleagle, D. R. Thedens, J. C. Ehrhardt, T. D. Scholz, and D. J. Skorton, “Automated identification of left ventricular borders from spin-echo resonance images”, Investigative Radiology, 26:295–303, 1991.
D. Geiger, A. Gupta, L. A. Costa, and J. Vlontzos, “Dynamic programming for detecting, tracking, and matching deformable contours”, IEEE Trans. PAMI, 17(3):294–302, 1995.
A. Goshtasby and D. A. Turner, “Segmentation of cardiac cine MR images for extraction of right and left ventricular chambers”, IEEE Trans. Medical Imaging, 14(1):56–64, 1995.
J. Weng, A. Singh, and M. Y. Chiu, “Learning-based ventricle detection from cardiac MR and CT images”, IEEE Trans. Medical Imaging, 16(4):378–391, 1997.
A. Colmenarez and T. Huang, “Face detection with information-based maximum discrimination”, Proc. IEEE CVPR, San Juan, Puerto Rico, pp 782–787, 1997.
N. Duta, A. K. Jain, and M.-P. Dubuisson-Jolly, “Learning-based object detection in cardiac MR images”, Proc. ICCV, Corfu, Greece, pp 1210–1216, 1999.
M.-P. Jolly, N. Duta, and G. Funka-Lea, “Segmentation of the left ventricle in cardiac MR images”, Proc. ICCV, Vancouver, Canada, 2001.
J. O. Ramsay and X. Li, “Curve registration”, Journal of the Royal Statistical Society Series B, 60:351–363, 1998.
R. A. Redner and H. F. Walker, “Mixture densities, maximum likelihood and the EM algorithm”, SIAM Review, 26:195–239, 1984.
E. N. Mortensen and W. A. Barrett, “Interactive segmentation with intelligent scissors”, Graphical Models and Image Processing, 60:349–384, 1998.
M. Kass, A. Witkin, and D. Terzopoulos, “Snakes: Active contour models”, International Journal of Computer Vision, 2:321–331, 1988.
N. Duta, A. K. Jain, M.-P. Dubuisson-Jolly, “Learning 2D shape models”, Proc. IEEE CVPR, Fort Collins, CO, vol. II, pp. 8–14, 1999.
C. Xu, A. Yezzi Jr., J. L. Prince, “On the relationship between parametric and geometric active contours”, Asilomar Conf. Signals, Systems, and Computers, pp. 483–489, 2000.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Jolly, MP. (2001). Combining Edge, Region, and Shape Information to Segment the Left Ventricle in Cardiac MR Images. In: Niessen, W.J., Viergever, M.A. (eds) Medical Image Computing and Computer-Assisted Intervention – MICCAI 2001. MICCAI 2001. Lecture Notes in Computer Science, vol 2208. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45468-3_58
Download citation
DOI: https://doi.org/10.1007/3-540-45468-3_58
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-42697-4
Online ISBN: 978-3-540-45468-7
eBook Packages: Springer Book Archive