Real-Time Active Shape Models for Segmentation of 3D Cardiac Ultrasound
We present a fully automatic real-time algorithm for robust and accurate left ventricular segmentation in three-dimensional (3D) cardiac ultrasound. Segmentation is performed in a sequential state estimation fashion using an extended Kalman filter to recursively predict and update the parameters of a 3D Active Shape Model (ASM) in real-time. The ASM was trained by tracing the left ventricle in 31 patients, and provided a compact and physiological realistic shape space. The feasibility of the proposed algorithm was evaluated in 21 patients, and compared to manually verified segmentations from a custom-made semi-automatic segmentation algorithm. Successful segmentation was achieved in all cases. The limits of agreement (mean±1.96SD) for the point-to-surface distance were 2.2±1.1mm. For volumes, the correlation coefficient was 0.95 and the limits of agreement were 3.4±20 ml. Real-time segmentation of 25 frames per second was achieved with a CPU load of 22%.
KeywordsQuadrilateral Mesh Active Shape Model Spline Interpolant Left Ventricular Shape Left Ventricular Model
Unable to display preview. Download preview PDF.
- 1.Jacobs, L.D., Salgo, I.S., Goonewardena, S., Weinert, L., Coon, P., Bardo, D., Gerard, O., Allain, P., Zamorano, J.L., de Isla, L.P., Mor-Avi, V., Lang, R.M.: Rapid online quantification of left ventricular volume from real-time three-dimensional echocardiographic data. European Heart Journal 27, 460–468 (2006)CrossRefGoogle Scholar
- 2.Sugeng, L., Mor-Avi, V., Weinert, L., Niel, J., Ebner, C., Steringer-Mascherbauer, R., Schmidt, F., Galuschky, C., Schummers, G., Lang, R.M., Nesser, H.J.: Quantitative assessment of left ventricular size and function. Side-by-side comparison of real-time three-dimensional echocardiography and computed tomography width magnetic resonance reference. Circulation 114, 654–661 (2006)CrossRefGoogle Scholar
- 4.Blake, A., Isard, M.: Active Contours: The Application of Techniques from Graphics, Vision, Control Theory and Statistics to Visual Tracking of Shapes in Motion. Springer-Verlag New York, Inc., Secaucus, NJ, USA (1998)Google Scholar
- 8.van Assen, H.C., Danilouchkine, M.G., Behloul, F., Lamb, H.J., van der Geest, R., Reiber, J.H.C., Lelieveldt, B.P.F.: Cardiac LV segmentation using a 3D active shape model driven by fuzzy inference. In: Ellis, R.E., Peters, T.M. (eds.) MICCAI 2003. LNCS, vol. 2878, pp. 533–540. Springer, Heidelberg (2003)Google Scholar
- 9.Orderud, F.: A framework for real-time left ventricular tracking in 3D+T echocardiography, using nonlinear deformable contours and kalman filter based tracking. In: Computers in Cardiology (2006)Google Scholar
- 10.Orderud, F., Hansegård, J., Rabben, S.I.: Real-time tracking of the left ventricle in 3D echocardiography using a state estimation approach: Medical Image Computing and Computer-Assisted Intervention - MICCAI (submitted, 2007)Google Scholar