Abstract
A novel method for segmentation of cardiac structures in temporal echocardiographic sequences based on the snake model is presented. The method is motivated by the observation that the structures of neighboring frames have consistent locations and shapes that aid in segmentation. To cooperate with the constraining information provided by the neighboring frames, we combine the template matching with the conventional snake model. It means that the model not only is driven by conventional internal and external forces, but also combines an additional constraint, the matching degree to measure the similarity between the neighboring prior shape and the derived contour. Furthermore, in order to auto or semi-automatically segment the sequent images without manually drawing the initial contours in each image, generalized Hough transformation (GHT) is used to roughly estimate the initial contour by transforming the neighboring prior shape. The method is particularly useful in case of the large frame-to-frame displacement of structure such as mitral valve. As a result, the active contour can easily detect the desirable boundaries in ultrasound images and has a high penetrability through the interference of various undesirables, such as the speckle, the tissue-related textures and the artifacts.
Similar content being viewed by others
Abbreviations
- GHT:
-
generalized Hough transformation
- MAD:
-
mean absolute distance
- ROI:
-
region of interest
- SD:
-
standard deviation
References
DB Sher, S Revankar and S Rosenthal, Computer methods in quantitation of cardiac wall parameters from two-dimensional echocardiograms: a survey. Int J Cardiac Imaging 8 (1992) 11-26
JMB Dias and JMN Leitao, Wall position and thickness estimation from sequence of echocardiographic images. IEEE Trans Med Imaging 15 (1996) 25-38
C Kotropolulos, Nonlinear ultrasonic image processing based on signal-adaptive filters and self-organizing neural networks. IEEE Trans Image Process 3 (1994) 65-77
JG Thomas, RA Peters and P Jeanty, Automatic segmentation of ultrasound images using morphological operators. IEEE Trans Med Imaging 10 (1991) 180-186
C Hass, H Ermert and S Holt, Segmentation of 3-D intravascular ultrasonic images based on a random field model. Ultrasound Med Biol 26 (2000) 297-306
GB Johan, CM Steven and PF Boudewijn, Automatic segmentation of echocardiographic sequences by active appearance motion models. IEEE Trans Med Imaging 21 (2002) 1374-1383
M Kass, A Witkin and D Terzopoulos, Snakes: active contour models. Int J Comput Vision 1 (1987) 321-331
CM Chen and HHS Lu, Cell-based dual snake model: a new approach to extracting highly winding boundaries in the ultrasound images. Ultrasound Med Biol 28 (2002) 1061-1073
C Xu and JL Prince, Snakes, shapes, and gradient vector flow. IEEE Trans Image Process 7 (1998) 359-369
SR Gunn and MS Nixon, A robust snake implementation: a dual active contour. IEEE Trans PAMI 19 (1997) 63-68
CM Chen and HHS Lu, A dual-snake model of high penetrability for ultrasound image boundary extraction. Ultrasound Med Biol 27 (2001) 1651-1665
S Lobregt and MA Viergever, A discrete active contour model. IEEE Trans Med Imaging 14 (1995) 12-24
CM Chen, HSS Lu and YC Lin, An early vision based snake model for ultrasound image segmentation. Ultrasound Med Biol 26 (2000) 273-285
DH Ballard, Generalizing the Hough transform to detect arbitrary shapes. Pattern Recogn 13 (1981) 111-122
PK Ser and WC Siu, A new generalized Hough transform for the detection of irregular objects. J Visual Commun Image Represent 6 (1995) 256-264
M Sonka, W Liang and P Kanani, Intracardiac echocardiography: computerized detection of left ventricular borders. Int J Cardiac Imaging 14 (1998) 397-411
TF Cootes, A Hill, CJ Taylor and J Haslam, Use of active shape models for locating structures in medical images. Image Visual Comput 12 (1994) 355-365
L Staib and J Duncan, Boundary finding with parametrically deformable models. IEEE Trans PAMI 14 (1992) 1061-1075
Zeng X, Staib H, Schultz RT, Duncan JS. Volumetric layer segmentation using coupled surfaces propagation. In: Proceedings of the IEEE Conf. Comp. Vision Pattern Recognition 1998, Santa Barbara, CA, pp. 708–715
J Yang, H Staib and JS Duncan, Neighbor-constrained segmentation with level set based 3-D deformable models. IEEE Trans Med Imaging 23 (2004) 940-948
JS Duncan, R Owen, P Anandan and L. Staib, Shape-based tracking of left ventricular wall motion. In: Computers in Cardiology 1990. Chicago, Illinois: IEEE Computer Society (1990 September) pp. 23-26
Cohen I, Ayache N and Sulger P. Tracking points on deformable curves. Proceedings of the Second Euro. Conf. Computer Vision 1992, Santa Margherita Ligure, Italy, May 1992
AA Amini and JS Duncan, Bending and stretching models for LV wall motion, analysis from curves and surfaces. Image Vision Comput 10 (1992) 418-430
AS Aguado, E Montiel and MS Nixon, Invariant characterization of the Hough transform for pose estimation of arbitrary shapes. Pattern Recogn 35 (2002) 1083-1097
FL Kok and TC Roland, Deformable contours: modelling and extraction. IEEE Trans PAMI 17 (1995) 1084-1090
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Sheng, C., Xin, Y., Liping, Y. et al. Segmentation in Echocardiographic Sequences using Shape-based Snake Model Combined with Generalized Hough Transformation. Int J Cardiovasc Imaging 22, 33–45 (2006). https://doi.org/10.1007/s10554-005-4933-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10554-005-4933-5