Automatic initialization of active contours in ultrasound images of breast cancer | Pattern Analysis and Applications Skip to main content
Springer Nature Link
Log in

Automatic initialization of active contours in ultrasound images of breast cancer

  • Short paper
  • Published:
Pattern Analysis and Applications Aims and scope Submit manuscript

Abstract

Gradient vector flow (GVF) snakes are an efficient method for segmentation of ultrasound images of breast cancer. However, the method produces inaccurate results if the seeds are initialized improperly (far from the true boundaries and close to the false boundaries). Therefore, we propose a novel initialization method designed for GVF-type snakes based on walking particles. At the first step, the algorithm locates the seeds at converging and diverging configurations of the vector field. At the second step, the seeds “explode,” generating a set of random walking particles designed to differentiate between the seeds located inside and outside the object. The method has been tested against five state-of-the-art initialization methods on sixty ultrasound images from a database collected by Thammasat University Hospital of Thailand (http://onlinemedicalimages.com). The ground truth was hand-drawn by leading radiologists of the hospital. The competing methods were: trial snake method (TS), centers of divergence method (CoD), force field segmentation (FFS), Poisson Inverse Gradient Vector Flow (PIG), and quasi-automated initialization (QAI). The numerical tests demonstrated that CoD and FFS failed on the selected test images, whereas the average accuracy of PIG and QAI was 73 and 87%, respectively, versus 97% achieved by the proposed method. Finally, TS has shown a comparable accuracy of about 93%; however, the method is about ten times slower than the proposed exploding seeds. A video demonstration of the algorithm is at http://onlinemedicalimages.com/index.php/en/presentations.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
¥17,985 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price includes VAT (Japan)

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4

References

  1. Kass M, Witkin A, Terzopoulos D (1988) Snakes: active contour models. Int J Comput Vis 1(4):321–331

    Article  MATH  Google Scholar 

  2. Xu C, Prince JL (1998) Snakes, shapes, and gradient vector flow. IEEE Trans Image Process 7(3):359–369

    Article  MathSciNet  MATH  Google Scholar 

  3. Xu C, Prince JL (1998) Generalized gradient vector flow external forces for active contours. Signal Process 71(2):131–139

    Article  MATH  Google Scholar 

  4. Tang J (2009) A multi-direction GVF snake for the segmentation of skin cancer images. Pattern Recognit 42(6):1172–1179

    Article  Google Scholar 

  5. Wei M, Zhou Y, Wan M (2004) A fast snake model based on non-linear diffusion for medical image segmentation. Comput Med Imaging Graph 28(3):109–117

    Article  Google Scholar 

  6. Jifeng N, Chengke W, Shigang L, Shuqin Y (2007) NGVF: an improved external force field for active contour model. Pattern Recognit Lett 28(1):58–63

    Article  Google Scholar 

  7. Guillot L, Guyader CL (2009) Extrapolation of vector fields using the infinity Laplacian and with applications to image segmentation. Scale Space Var Methods Comput Vis 87–99

  8. Wang Y, Jia Y, Liu L (2008) Harmonic gradient vector flow external force for snake model. Electron Lett 44(2):105–106

    Article  Google Scholar 

  9. Li B, Acton ST (2007) Active contour external force using vector field convolution for image segmentation. IEEE Trans Image Process 16(8):2096–2106

    Article  MathSciNet  Google Scholar 

  10. Cheng J, Foo SW (2006) Dynamic directional gradient vector flow for snakes. IEEE Trans Image Process 15(6):1563–1571

    Article  Google Scholar 

  11. Wu Y, Wang Y, Jia Y (2013) Adaptive diffusion flow active contours for image segmentation. Comput Vis Image Underst 117(10):1421–1435

    Article  Google Scholar 

  12. Rodtook A, Makhanov SS (2013) Multi-feature gradient vector flow snakes for adaptive segmentation of the ultrasound images of breast cancer. J Vis Commun Image Represent 24(8):1414–1430

    Article  Google Scholar 

  13. Rochery M, Jermyn IH, Zerubia J (2006) Higher order active contours. Int J Comput Vis 69:27–42

    Article  Google Scholar 

  14. Li C, Liu J, Foxa MD (2005) Segmentation of external force field for automatic initialization and splitting of snakes. Pattern Recognit 38(11):1947–1960

    Article  Google Scholar 

  15. Wang Y, Liang J, Jia Y (2007) On the critical point of gradient vector flow snake. ACCV2007. LNCS 4844:754–763

    Google Scholar 

  16. Xingfei G, Jie T (2002) An automatic active contour model for multiple objects. Proc Int Conf Pattern Recognit 2:881–884

    Google Scholar 

  17. He Y, Luo Y, Hu D (2006) Semi-automatic initialization of gradient vector flow snakes. J Electron Imaging 15(4):1–8

    Article  Google Scholar 

  18. Shu CF, Jain RC (1994) Vector field analysis for oriented patterns. IEEE Trans Pattern Anal Mach Intell 16(9):946–950

    Article  Google Scholar 

  19. Cohen I, Herlin I (1995) A motion computation and interpretation framework for oceanographic satellite images. In: Proc. internat. symposium comput. vis., Nov 1995, pp 13–18

  20. Li J, Yau WY, Wang H (2008) Combining singular points and orientation image information for fingerprint classification. Pattern Recognit 41(1):353–366

    Article  MATH  Google Scholar 

  21. Li J, Yau WY, Wang H (2006) Constrained nonlinear models of fingerprint orientations with prediction. Pattern Recognit 39(1):102–114

    Article  Google Scholar 

  22. Tian X, Samarasinghe S, Murphy G (1999) An integrated algorithm for detecting position and size of knots on logs using texture analysis. In: Proc. conf. image and visions computing, pp 121–132

  23. Yau WY, Li J, Wang H (2004) Nonlinear phase portrait modeling of fingerprint orientation. In: Internat. conf. control, automation, robotics and vision (ICARCV2004) 8th, Dec 2004, pp 1262–1267

  24. Ray N, Acton ST (2003) Merging parametric active contours within homogeneous image regions for MRI-based lung segmentation. IEEE TMI 22(2):189–199

    Google Scholar 

  25. Saha BN, Ray N, Zhang H (2009) Snake validation: a PCA-based outlier detection method. IEEE Signal Process Lett 16(6):549–552

    Article  Google Scholar 

  26. Tauber C, Batatia H, Ayache A (2010) Quasi-automatic initialization for parametric active contours. Pattern Recognit Lett 31(1):83–90

    Article  Google Scholar 

  27. Tauber C, Batatia H, Ayache A (2005) A general quasi-automatic initialization for snakes: application to ultrasound images. In: IEEE internat. conf. image processing, vol 2, pp 806–809

  28. Li B, Acton ST (2008) Automatic active model initialization via Poisson inverse gradient. IEEE Trans Image Process 17(8):1406–1420

    Article  MathSciNet  Google Scholar 

  29. Hsu CY, Liu CY, Chen CM (2008) Automatic segmentation of liver PET images. Comput Med Imaging Graph 32(7):601–610

    Article  Google Scholar 

  30. Hsua CY, Wang HF, Wang HC, Tseng KK (2012) Automatic extraction of face contours in images and videos. Future Gener Comput Syst 28(1):322–335

    Article  Google Scholar 

  31. Veronesea E, Stramarec R, Campiona A, Raffeinerb B, Beltramec V, Scagliori E, Coranc A, Ciprianb L, Fioccob U, Grisana E (2013) Improved detection of synovial boundaries in ultrasound examination by using a cascade of active-contours. Med Eng Phys 35(2):188–194

    Article  Google Scholar 

  32. Doshi DJ, March DE, Crisi GM, Coughlin BF (2007) Complex cystic breast masses: diagnostic approach and imaging-pathologic correlation. Radiographics 27:53–64

    Article  Google Scholar 

  33. Jung IS, Thapa D, Wang GN (2005) Automatic segmentation and diagnosis of breast lesions using morphology method based on ultrasound. In: Internat. conf. on fuzzy systems and knowledge discovery (FSKD), August 2005, LNAI 3614, pp 1079–1088

  34. Madabhushi A, Metaxas DN (2003) Combining low-, high-level and empirical domain knowledge for automated segmentation of ultrasonic breast lesions. IEEE Trans Med Imaging 22(2):155–169

    Article  Google Scholar 

  35. Selvan S, Shenbagadevi S (2015) Automatic seed point selection in ultrasound echography images of breast using texture features. Biocybern Biomed Eng 35(3):157–168

    Article  Google Scholar 

  36. Fergani K, Lui D, Scharfenberger C, Wong A, Clausi DA (2014) Hybrid structural and texture distinctiveness vector field convolution for region segmentation. Comput Vis Image Underst 125:85–96

    Article  Google Scholar 

  37. Liu S, Peng Y (2012) A local region-based Chan-Vese model for image segmentation. Pattern Recognit 45(7):2769–2779

    Article  MATH  Google Scholar 

  38. Akgul YS, Kambhamettu C, Stone M (1998) Extraction and tracking of the tongue surface from ultrasound image sequences. In: Proc. internat. ieee comput. society conf. comput. vis. and pattern recognit., pp 298–303

  39. Kirimasthong K, Rodtook A, Chaumrattanakul U, Makhanov SS (2016) Phase portrait analysis for automatic initialization of multiple snakes for segmentation of the ultrasound images of breast cancer. Pattern Anal Appl. doi:10.1007/s10044-016-0556-9

    Google Scholar 

  40. Jalba AC, Wilkinson MHF, Roerdink JBTM (2004) Automatic image segmentation using a deformable model based on charged particles. Lecture Notes in Computer Science, vol 3211, pp 1–8

  41. Jordan D, Smith P (2007) Nonlinear ordinary differential equations: an introduction for scientists and engineers, 4th edn. Oxford University Press, Oxford

    MATH  Google Scholar 

  42. Rangayyan R, Ayres F (2006) Gabor filters and phase portraits for the detection of architectural distortion in mammograms. Med Biol Eng Comput 44:883–894

    Article  Google Scholar 

  43. Chucherd S, Rodtook A, Makhanov SS (2010) Phase portrait analysis for multiresolution generalized gradient vector flow. IEICE Trans Inf Syst E93-D 2822–2835

  44. Dubuisson M-P, Jain AK (1994) A modified Hausdorff distance for object matching proceedings. In: International conference on pattern recognition, Israel, 1994, pp 566–568

Download references

Acknowledgements

We wish to thank the anonymous referees of the paper for valuable remarks.

This research is sponsored by the Thailand Research Fund, Grant BRG5780012, and the Center of Excellence in Biomedical Engineering, Thammasat University.

Author information

Authors and Affiliations

  1. School of Information and Computer Technology, Sirindhorn International Institute of Technology, Thammasat University, Pathum Thani, Thailand

    Khwunta Kirimasthong & Stanislav S. Makhanov

  2. Department of Computer Science, Ramkhamhaeng University, Bangkok, Thailand

    Annupan Rodtook

  3. Department of Radiology, Thammasat University, Pathum Thani, Thailand

    Wanrudee Lohitvisate

Authors
  1. Khwunta Kirimasthong
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Annupan Rodtook
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Wanrudee Lohitvisate
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Stanislav S. Makhanov
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Stanislav S. Makhanov.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Kirimasthong, K., Rodtook, A., Lohitvisate, W. et al. Automatic initialization of active contours in ultrasound images of breast cancer. Pattern Anal Applic 21, 491–500 (2018). https://doi.org/10.1007/s10044-017-0627-6

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10044-017-0627-6

Keywords