Spatially adaptive active contours: a semi-automatic tumor segmentation framework

  • Cristina FarmakiEmail author
  • Konstantinos Marias
  • Vangelis Sakkalis
  • Norbert Graf
Original Article



Tumor segmentation constitutes a crucial step in simulating cancer growth and response to therapy. Incorporation of imaging data individualizes the simulation and assists clinical correlation with the predicted outcome. We adapted snakes to improve tumor segmentation including difficult cases with inherently inhomogeneous structure and poorly defined margins.


Snakes are flexible curves, based on the parameter-controlled deformation of an initial user-defined contour toward the boundary of the desired object, through the minimization of a suitable energy function. Although parameter-adjustment can yield fairly good results in homogeneous regions, traditional snakes often fail to provide an accurate segmentation result when both rigid and very elastic behavior is needed simultaneously to delineate the true outline of the tumor. We developed and tested a spatially adaptive active contour technique by introducing local snake bending, to improve traditional snakes performance for segmenting tumors. The key point of our method is the use of adaptable snake parameters, instead of constant ones, to adjust the bending of the curve according to the local edge characteristics. Our algorithm discriminates image regions according to underlying image features, such as gradient magnitude and corner strength. More specifically, it assigns each region a different “localized” set of parameters, one corresponding to a very flexible snake, and the other corresponding to a very rigid one, according to the local image characteristics.


Qualitative results on more than 150 real MR images, as well as quantitative validation based on agreement with an expert clinician’s annotations of the true tumor boundaries, demonstrate our approach is highly efficient compared to traditional active contours and region growing. Due to the use of adaptable parameters in the snake evolution process, our approach outperforms the other two methods, and consistently follows an expert’s annotations. Statistical tests indicated significant difference between the results produced by our approach and two other algorithms traditional snakes and region growing, while multiple comparison showed that our method consistently outperformed those algorithms, with an average overlap of 89%, over the entire data set, while traditional snakes were at 82.5% and region growing at 59.2%. Furthermore, we performed several tests that demonstrate our method’s stability to different initial contours, as well as, to lower resolution images.


Our adaptive snake algorithm can spatially adapt to diverse image characteristics, producing outlines that mimic the true tumor boundaries. Results in MR datasets are very close to an expert clinician’s intuition about the tumor boundaries.


Active contours Semi-automatic segmentation Spatially adaptive contours Tumor segmentation 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Casciari J, Sotirchos S, Sutherland R (1992) Variations in tumor growth rates and metabolism with oxygen concentration, glucose concentration, and extracellular pH. J Cell Physiol 151: 386–394CrossRefPubMedGoogle Scholar
  2. 2.
    Santini M, Rainaldi G (1999) Three-dimensional spheroid model in tumor biology. Pathobiology 67: 148–157CrossRefPubMedGoogle Scholar
  3. 3.
    Wiarda D, Travis C (1997) Determinability of model parameters in a two-stage deterministic cancer model. Math Biosci 146: 1–13. doi: 10.1016/S0025-5564(97)00025-4 CrossRefPubMedGoogle Scholar
  4. 4.
    Stamatakos G, Antipas V, Uzunoglu U (2006) A spatiotemporal, patient individualized simulation model of solid tumor response to chemotherapy in vivo: the paradigm of glioblastoma multi- forme treated by temozolomide. IEEE Trans Biomed Eng 53: 1467–1477CrossRefPubMedGoogle Scholar
  5. 5.
    Adams R, Bischof L (1994) Seeded region growing. IEEE Trans Pattern Anal Mach Intell 16: 641–647CrossRefGoogle Scholar
  6. 6.
    Beucher S (1991) The watershed transformation applied to image segmentation. In: Proceedings of scanning microscopy international, pp 299–314Google Scholar
  7. 7.
    Boykov Y, Jolly M (2001) Interactive graph cuts for optimal boundary and region segmentation of objects in ND images. In: International conference on computer vision, pp 105–112Google Scholar
  8. 8.
    Barrett W, Mortensen E (1997) Interactive live-wire boundary extraction. Med Image Anal 1: 331–341CrossRefPubMedGoogle Scholar
  9. 9.
    Kass M, Witkin A, Terzopoulos D (1998) Snakes: active contour models. Int J Comput Vis 1: 321–331CrossRefGoogle Scholar
  10. 10.
    Xu C, Prince J (1997) Gradient vector flow: a new external force for snakes. In: Proceedings of 1997 IEEE computer society conference on computer vision and pattern recognition, pp 66–71Google Scholar
  11. 11.
    Osher S, Sethian J (1988) Fronts propagating with curvature dependent speed: algorithms based on Hamilton-Jacobi formulations. J Comput Phys 79: 12–49CrossRefGoogle Scholar
  12. 12.
    Caselles V, Kimmel R, Sapiro G (1997) Geodesic active contours. Int J Comput Vis 22: 61–79CrossRefGoogle Scholar
  13. 13.
    Kim D, Park J (2004) Computer aided detection of kidney tumor on abdominal computed tomography scans. Acta Radiol 45: 791–795CrossRefPubMedGoogle Scholar
  14. 14.
    Mancas M, Gosselin B (2003) Fuzzy tumor segmentation based on iterative watersheds. In: Proceedings of 14th ProRISC workshop circuits systems and signal process. UnpublishedGoogle Scholar
  15. 15.
    Boykov Y, Jolly M (2000) Interactive organ segmentation using graph cuts. In: Medical image computing and computer-assisted intervention, pp 276–286Google Scholar
  16. 16.
    Boykov Y, Funka-Lea G (2006) Graph cuts and efficient nd image segmentation. Int J Comput Vis 70: 109–131CrossRefGoogle Scholar
  17. 17.
    Esneault S, Hraiech N, Delabrousse E, Dillenseger J (2007) Graph cut liver segmentation for interstitial ultrasound therapy. Conf Proc IEEE Eng Med Biol Soc 1: 5247–5250Google Scholar
  18. 18.
    Cohen L, Cohen I, Ceremade P (1993) Finite-element methods for active contour models and balloons for 2-D and 3-D images. IEEE Trans Pattern Anal Mach Intell 15: 1131–1147CrossRefGoogle Scholar
  19. 19.
    Nogueira S, Ruichek Y (2007) A new B-spline based active contour approach. In: IAPR conference on machine vision applications, pp 268–271Google Scholar
  20. 20.
    Lu R, Marziliano P, Thng C (2005) Liver tumor volume estimation bye semi-automatic segmentation method. In: Proceedings of 2005 IEEE engineering in medicine and biology 27th Annual Conference, pp 3296–3299Google Scholar
  21. 21.
    Cvancarova M, Albregtsen F, Brabrand K, Samset E (2005) Segmentation of ultrasound images of liver tumors applying snake algorithms and GVF. In: International congress of computer assisted radiology and surgeryGoogle Scholar
  22. 22.
    Gu L, Xu J, Peters T (2006) Novel multistage three-dimensional medical image segmentation: methodology and validation. IEEE Trans Inf Technol Biomed 10: 740–748CrossRefPubMedGoogle Scholar
  23. 23.
    Linguraru M et al (2009) Renal tumor quantification and classification in contrast-enhanced abdominal CT. Pattern Recognit 42: 1149–1161CrossRefPubMedGoogle Scholar
  24. 24.
    Aleman-Flores M, Álvarez L, Caselles V (2007) Texture-oriented anisotropic filtering and geodesic active contours in breast tumor ultrasound segmentation. J Math Imaging Vis 28: 81–97CrossRefGoogle Scholar
  25. 25.
    Kanakatte A, Gubbi J, Srinivasan B, Mani N, Kron T, Binns D, Palaniswami M (2008) Pulmonary tumor volume delineation in PET images using deformable models. Conf Proc IEEE Eng Med Biol Soc, pp 3118–3121Google Scholar
  26. 26.
    Farmaki C, Marias K, Sakkalis V, Graf N (2009) A spatially adaptive active contour method for improving semi-automatic medical image annotation. In: Proc World congress on medical physics and biomedical engineering, pp 1878–1881Google Scholar
  27. 27.
    Logan J (1997) Applied mathematics, chap 3, 2nd edn. Wiley, New yorkGoogle Scholar
  28. 28.
    Perona P, Malik J (1990) Scale-space and edge detection using anisotropic diffusion. IEEE Trans Pattern Anal Mach Intell 12: 629–639CrossRefGoogle Scholar
  29. 29.
    Tsai D-M, Chao S-M (2005) An anisotropic diffusion-based defect detection for sputtered surfaces with inhomogeneous textures. Image Vis Comput 23: 325–338CrossRefGoogle Scholar
  30. 30.
    Gonzalez RC, Woods RE (2002) Digital image processing. Prentice Hall, UK, pp, pp 134–137Google Scholar
  31. 31.
    Harris C, Stephens M (1988) A combined corner and edge detector. In: Alvey vision conference, pp 147–152Google Scholar
  32. 32.
    Chang F, Chen C, Lu C (2004) A linear-time component-labeling algorithm using contour tracing technique. Comput Vis Image Underst 93: 206–220CrossRefGoogle Scholar
  33. 33.
    Zou K et al (2004) Statistical validation of image segmentation quality based on a spatial overlap index: scientific reports. Acad Radiol 11: 178–189CrossRefPubMedGoogle Scholar
  34. 34.
    Daniel WW (1978) Applied nonparametric statistics. Houghton Mifflin, BostonGoogle Scholar

Copyright information

© CARS 2010

Authors and Affiliations

  • Cristina Farmaki
    • 1
    Email author
  • Konstantinos Marias
    • 1
  • Vangelis Sakkalis
    • 1
  • Norbert Graf
    • 2
  1. 1.Institute of Computer ScienceFoundation for Research and Technology, HellasHeraklion, CreteGreece
  2. 2.Department of Paediatric Oncology and HaematologyUniversity of the SaarlandHomburgGermany

Personalised recommendations