Abstract
The presence of speckle in ultrasound images causes many spurious local minima in the energy function of active contours. These minima trap the segmentation prematurely under gradient descent and cause the algorithm to fail. This paper presents a substantially new reformulation of Tunneling Descent, which is a deterministic technique to escape from unwanted local minima. In the new formulation, the evolving curve is represented by level sets, and the evolution strategy is obtained as a sequence of constrained minimizations.
The algorithm is used to segment the endocardium in 115 short axis cardiac ultrasound images. All segmentations are achieved without tweaking the energy function or numerical parameters. Experimental evaluation of the results shows that the algorithm overcomes multiple local minima to give segmentations that are considerably more accurate than conventional techniques.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Wagner, R.F., Smith, S.W., Sandrick, J.M., Lopez, H.: Statistics of speckle in ultrasound B-scans. I.E.E.E. Trans. Son. Ultra. 30, 156–163 (1983)
Shankar, P.M.: A general statistical model for ultrasonic scattering from tissues. IEEE Trans. Ultrasonic, Ferro., Freq. Contr. 47(3), 727–736 (2000)
Tao, Z., Beaty, J., Jaffe, C.C., Tagare, H.D.: Gray level models for segmentating myocardium and blood in cardiac ultrasound images. In: Proceedings ISBI 2002 (2002)
Tao, Z., Jaffe, C.C., Tagare, H.D.: Tunneling Descent: A new algorithm for active aontour segmentation of ultrasound images. In: Proceedings, IPMI 2003 (2003)
Butkhardt, C.B.: Speckle in ultrasound B-mode scans. I.E.E.E. Trans. Son. Ultra. SU-25, 1–6 (1978)
Belohlacek, M., Greenleaf, J.F.: Detection of cardiac boundaries in echocardiographic images using a customized order statistics filter. Ultrasonic Imaging 19(2), 127–137 (1997)
Bamber, J.C., Daft, C.: Adaptive filtering for reduction of speckle in ultrasonic pulse-echo images. In: Ultrasonics, January 1986, pp. 41–44 (1986)
Muzzolini, R., Yang, Y., Pierson, R.: Multiresolution texture segmentation with application to diagnostic ultrasound images. IEEE Trans. Med. Img. 12(1) (March 1993)
Czerwinski, N., Jones, D.L., O’Brien Jr., W.D.: Line and boundary detection in speckle images-Application to medical ultrasound. IEEE Trans. Med. Img. 8(2), 126–136 (1999)
Parker, A.D., Hill, A., Taylor, C.J., Cootes, T.F., Jin, X.Y., Gibson, D.G.: Application of point distribution models to the automated analysis of echocardiograms. In: Computers in Cardiology, 1994, September 1994, pp. 25–28 (1994)
Hill, A., Taylor, C.J.: Model-based image interpretation using genetic algorithms. Image and Vision Computing 10(5) (June 1992)
Mulet-Parada, M., Noble, J.A.: Intensity-invariant 2D+T acoustic boundary detection. In: Proceedings, Workshop on Biomedical Image Analysis 1998 (June 1998)
Bertsekas, D.P.: Nonlinear Programming. Athena Scientific, Belmont (1996)
Perkins, C.: A convergence analysis of Dykstra’s algorithm for phlyhedral sets. SIAM. J. Numer. Anal. 40(2), 792–804 (2002)
Chan, T., Vese, L.A.: Active contours without edges. IEEE Trans. Image Processing 10(2) (Febuary 2001)
Tao, Z., Tagare, H.D.: Stopping rules for active contour segmentation of ultrasound images. In: Proceedings, SPIE Medical Imaging 2005 (2005)
Tao, Z., Tagare, H.D.: Tunneling descent for M.A.P. active contour segmentation., Technical Report No. 05.01 (2005)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Tao, Z., Tagare, H.D. (2005). Tunneling Descent Level Set Segmentation of Ultrasound Images. In: Christensen, G.E., Sonka, M. (eds) Information Processing in Medical Imaging. IPMI 2005. Lecture Notes in Computer Science, vol 3565. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11505730_62
Download citation
DOI: https://doi.org/10.1007/11505730_62
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-26545-0
Online ISBN: 978-3-540-31676-3
eBook Packages: Computer ScienceComputer Science (R0)