Journal of Digital Imaging

, Volume 25, Issue 2, pp 279–293 | Cite as

Group Average Difference: A Termination Criterion for Active Contour

Article
First Online:

Abstract

This paper presents a termination criterion for active contour that does not involve alteration of the energy functional. The criterion is based on the area difference of the contour during evolution. In this criterion, the evolution of the contour terminates when the area difference fluctuates around a constant. The termination criterion is tested using parametric gradient vector flow active contour with contour resampling and normal force selection. The usefulness of the criterion is shown through its trend, speed, accuracy, shape insensitivity, and insensitivity to contour resampling. The metric used in the proposed criterion demonstrated a steadily decreasing trend. For automatic implementation in which different shapes need to be segmented, the proposed criterion demonstrated almost 50% and 60% total time reduction while achieving similar accuracy as compared with the pixel movement-based method in the segmentation of synthetic and real medical images, respectively. Our results also show that the proposed termination criterion is insensitive to shape variation and contour resampling. The criterion also possesses potential to be used for other kinds of snakes.

Keywords

Termination criterion Active contour Gradient vector flow Area difference Group average 
This is a preview of subscription content, log in to check access.

Notes

Acknowledgments

T. K. Chuah would like to express his gratitude to the university for providing financial support through Nanyang President Graduate Scholarship. The authors thank the Ministry of Education (MOE), Singapore, for supporting the project through SUG09/07 and AcRF Tier 1 (RG34/07) grant.

References

  1. 1.
    Kass M, Witkin A, Terzopoulos D: Snakes: Active contour models. International Journal of Computer Vision 1:321–331, 1988CrossRefGoogle Scholar
  2. 2.
    Horritt MS, Mason DC, Luckman AJ: Flood boundary delineation from synthetic aperture radar imagery using a statistical active contour model. International Journal of Remote Sensing 22:2489–2507, 2001Google Scholar
  3. 3.
    Jiang H, Cheng Q: Automatic 3D segmentation of CT images based on active contour models. Proceedings of the 11th IEEE International Conference on Computer-Aided Design and Computer Graphics: CityGoogle Scholar
  4. 4.
    Jurcak V, et al: Automated segmentation of the quadratus lumborum muscle from magnetic resonance images using a hybrid atlas based-geodesic active contour scheme. Conference Proceedings: Annual International Conference of the IEEE EMBS 2008:867–870, 2008Google Scholar
  5. 5.
    Liu B, Cheng HD, Huang J, Tian J, Liu J, Tang X: Automated segmentation of ultrasonic breast lesions using statistical texture classification and active contour based on probability distance. Ultrasound in Medicine and Biology 35:1309–1324, 2009PubMedCrossRefGoogle Scholar
  6. 6.
    Chan TF, Vese LA: Active contours without edges. IEEE Transactions on Image Processing 10:266–277, 2001PubMedCrossRefGoogle Scholar
  7. 7.
    Acton ST, Ray N: Algorithm KWT: Morgan & Claypool Publishers, 2009Google Scholar
  8. 8.
    Chen Y, Zhao W, Wang Z: Level set segmentation algorithm based on image entropy and simulated annealing. Proc. ICBBE: CityGoogle Scholar
  9. 9.
    Lee SH, Seo JK: Level set-based bimodal segmentation with stationary global minimum. IEEE Transactions on Image Processing 15:2843–2852, 2006PubMedCrossRefGoogle Scholar
  10. 10.
    Ray N, Chanda B, Das J: A fast and flexible multiresolution snake with a definite termination criterion. Pattern Recognition 34:1483–1490, 2001CrossRefGoogle Scholar
  11. 11.
    Shuai Y, Sun H, Xu G: SAR image segmentation based on level set with stationary global minimum. IEEE Geoscience and Remote Sensing Letters 5:644–648, 2008CrossRefGoogle Scholar
  12. 12.
    Wang XF, Huang DS, Xu H: An efficient local Chan–Vese model for image segmentation. Pattern Recognition 43:603–618, 2010CrossRefGoogle Scholar
  13. 13.
    Liu J, Gao W, Huang S, Nowinski WL: A model-based, semi-global segmentation approach for automatic 3-D point landmark localization in neuroimages. IEEE Transactions on Medical Imaging 27:1034–1044, 2008PubMedCrossRefGoogle Scholar
  14. 14.
    Lobregt S, Viergever MA: Discrete dynamic contour model. IEEE Transactions on Medical Imaging 14:12–24, 1995PubMedCrossRefGoogle Scholar
  15. 15.
    Xu C, Prince JL: Snakes, shapes, and gradient vector flow. IEEE Transactions on Image Processing 7:359–369, 1998PubMedCrossRefGoogle Scholar
  16. 16.
    Dong X, Zheng G: Automatic extraction of proximal femur contours from calibrated X-ray images using 3D statistical models: An in vitro study. International Journal of Medical Robotics and Computer Assisted Surgery 5:213–222, 2009PubMedCrossRefGoogle Scholar
  17. 17.
    Baldwin MA, Langenderfer JE, Rullkoetter PJ, Laz PJ: Development of subject-specific and statistical shape models of the knee using an efficient segmentation and mesh-morphing approach. Computer Methods and Programs in Biomedicine 97:232–240, 2010PubMedCrossRefGoogle Scholar
  18. 18.
    Von Jan U, Sandkühler D, Kirsch L, Rühmann U, Overhoff HM: Surgical planning for the humeral part of a shoulder endoprosthesis based on landmarks determined from 3D ultrasound volumes. International Journal of Computer Assisted Radiology and Surgery 1:229–231, 2006CrossRefGoogle Scholar
  19. 19.
    Otsu N: Threshold selection method from gray-level histograms. IEEE Trans Syst Man Cybern SMC 9:62–66, 1979CrossRefGoogle Scholar
  20. 20.
    Lam L, Lee S-W, Suen CY: Thinning methodologies—A comprehensive survey. IEEE Transactions on Pattern Analysis and Machine Intelligence 14:page 879, bottom of first column through top of second column, 1992Google Scholar
  21. 21.
    Fripp J, Crozier S, Warfield SK, Ourselin S: Automatic segmentation of the bone and extraction of the bone–cartilage interface from magnetic resonance images of the knee. Physics in Medicine and Biology 52:1617–1631, 2007PubMedCrossRefGoogle Scholar
  22. 22.
    Cohen LD: On active contour models and balloons. CVGIP: Image Understanding 53:211–218, 1991CrossRefGoogle Scholar
  23. 23.
    Jehan-Besson S, Gastaud M, Barlaud M, Aubert G: Region-based active contours using geometrical and statistical features for image segmentation. Proceedings of the IEEE International Conference on Image Processing: CityGoogle Scholar

Copyright information

© Society for Imaging Informatics in Medicine 2011

Authors and Affiliations

  • Tong Kuan Chuah
    • 1
  • Jun Hong Lim
    • 1
  • Chueh Loo Poh
    • 1
  1. 1.Division of Bioengineering, School of Chemical & Biomedical EngineeringNanyang Technological UniversitySingaporeSingapore

Personalised recommendations