Applied Intelligence

, Volume 27, Issue 3, pp 193–203 | Cite as

A genetically optimized level set approach to segmentation of thyroid ultrasound images

  • Dimitris K. IakovidisEmail author
  • Michalis A. Savelonas
  • Stavros A. Karkanis
  • Dimitris E. Maroulis


This paper presents a novel framework for thyroid ultrasound image segmentation that aims to accurately delineate thyroid nodules. This framework, named GA-VBAC incorporates a level set approach named Variable Background Active Contour model (VBAC) that utilizes variable background regions, to reduce the effects of the intensity inhomogeneity in the thyroid ultrasound images. Moreover, a parameter tuning mechanism based on Genetic Algorithms (GA) has been considered to search for the optimal VBAC parameters automatically, without requiring technical skills. Experiments were conducted over a range of ultrasound images displaying thyroid nodules. The results show that the proposed GA-VBAC framework provides an efficient, effective and highly objective system for the delineation of thyroid nodules.


Level sets Active contour models Genetic algorithms Segmentation Thyroid Ultrasound 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    AACE clinical practice guidelines for the diagnosis and management of thyroid nodules (1996) Endocr Pract 2(1):78–84 Google Scholar
  2. 2.
    Jardim SVB, Figueiredo MAT (2003) Automatic contour estimation in fetal ultrasound images. In: Proceedings of the IEEE international conference on image processing, vol 2, pp 1065–1068 Google Scholar
  3. 3.
    New York Thyroid Center page.
  4. 4.
    Papini E, Guglielmi R, Bianchini A, Crescenzi A, Taccogna S, Nardi F, Panunzi C, Rinaldi R, Toscano V, Pacella CM (2002) Risk of malignancy in nonpalpable thyroid nodules: predictive value of ultrasound and color-Doppler features. J Clin Endocrinol Metabol 87(5):1941–1946 CrossRefGoogle Scholar
  5. 5.
    Zimmer Y, Tepper R, Akselrod S (1996) A two-dimensional extension of minimum cross entropy thresholding for the segmentation of ultrasound images. Ultrasound Medic Biol 22:1183–1190 CrossRefGoogle Scholar
  6. 6.
    Adams R, Bischof L (1994) Seeded region growing. IEEE Trans Pattern Anal Mach Intell 16(6):641–647 CrossRefGoogle Scholar
  7. 7.
    Pohle R, Toennies K (2001) Segmentation of medical images using adaptive region growing. Proc SPIE Med Im 4322:1337–1346 CrossRefGoogle Scholar
  8. 8.
    Hao X, Bruce C, Pislaru C, Greenleaf JF (2000) A novel region growing method for segmenting ultrasound images. In: Proceedings of the IEEE international ultrasonics symposium, vol 2, pp 1717–1720 Google Scholar
  9. 9.
    Kotropoulos C, Pittas I (2003) Segmentations of ultrasonic images using support vector machines. Pattern Recognit Lett 24:715–727 zbMATHCrossRefGoogle Scholar
  10. 10.
    Boukerroui D, Basset O, Guerin N, Baskurt A (1998) Multiresolution texture based adaptive clustering algorithm for breast lesion segmentation. Eur J Ultrasound 8:135–144 CrossRefGoogle Scholar
  11. 11.
    Fan L, Braden GA, Herrington DM (1996) Nonlinear wavelet filter for intracoronary ultrasound images. In: Proceedings of annual meeting on computers in cardiology, pp 41–44 Google Scholar
  12. 12.
    Thomas JG, Peters RA, Jeanty P (1991) Automatic segmentation of ultrasound images using morphological operators. IEEE Trans Med Im 10:180–186 CrossRefGoogle Scholar
  13. 13.
    Heckman T (1996) Searching for contours. Proc SPIE 2666:223–232 CrossRefGoogle Scholar
  14. 14.
    Solaiman B, Roux C, Rangayyan RM, Pipelier F, Hillion A (1996) Fuzzy edge evaluation in ultrasound endosonographic images. In: Proceedings of the Canadian conference on electrical and computer engineering, pp 335–338 Google Scholar
  15. 15.
    Chen CM, Lu HHS, Hsiao AT (2001) A dual-snake model of high penetrability for ultrasound image boundary extraction. Ultrasound Med Biol 27(12):1651–1665 CrossRefGoogle Scholar
  16. 16.
    Haenselmann T, Schremmer C, Effelsberg W (2001) Wavelet based semi-automatic segmentation of image objects. In: Proceedings of IEEE international conference on signal and image processing, pp 387–392 Google Scholar
  17. 17.
    Blake A, Isard M (1999) Active contours: the application of techniques from graphics, vision, control theory and statistics to visual tracking of shapes in motion. Springer, Berlin Google Scholar
  18. 18.
    Paragios N, Deriche R (2002) Geodesic active regions and level set methods for supervised texture segmentation. Int J Comput Vis 46(3):223–247 zbMATHCrossRefGoogle Scholar
  19. 19.
    McInerney T, Terzopoulos D (1996) Deformable models in medical images analysis: a survey. Med Im Anal 1(2):91–108 CrossRefGoogle Scholar
  20. 20.
    Lee JH, Lin CJ (2000) Automatic model selection for support vector machine. In: Visual information and information systems, pp 37–48 Google Scholar
  21. 21.
    Theodoridis S, Koutroumbas K (1998) Pattern recognition. Academic Press, New York zbMATHGoogle Scholar
  22. 22.
    Suri JS, Liu K, Laxminarayan SN, Zeng X, Reden L (2002) Shape recovery algorithms using level sets in 2-D/3-D medical imagery: a state-of-the-art review. IEEE Trans Inf Tech Biomed 6(1):8–28 CrossRefGoogle Scholar
  23. 23.
    Angelini E, Holmes J, Laine A (2003) Segmentation of RT3D ultrasound with implicit deformable models without gradients. In: Proceedings ISPA, vol 2, pp 711–716 Google Scholar
  24. 24.
    Honigmann D, Ruisz J, Pottmann H (2002) Fast model based segmentation of ultrasound data using an active image. In: Proceedings of IEEE international symposium on biomedical imaging, pp 225–228 Google Scholar
  25. 25.
    Lin N, Yu W, Duncan JS (2003) Combinative multi-scale level set framework for echocardiographic image segmentation. Med Im Anal 7:529–537 CrossRefGoogle Scholar
  26. 26.
    Chan TF, Vese LA (2001) Active contours without edges. IEEE Trans Im Proc 7:266–277 CrossRefGoogle Scholar
  27. 27.
    Savelonas MA, Maroulis DE, Iakovidis DK, Karkanis SA, Dimitropoulos N (2005) A variable background active contour model for thyroid nodule detection in ultrasound images. In: Proceedings of the IEEE international conference on image processing, vol 1, pp 17–20 Google Scholar
  28. 28.
    Kass M, Witkin A, Terzopoulos D (1998) Snakes: active contour models. Int J Comput Vis 8(2):321–331 Google Scholar
  29. 29.
    Jain AK, Zhong Y, Lakshmanan S (1991) Object matching using deformable models. IEEE Trans Patt Anal Mach Intell 18(3):267–278 CrossRefGoogle Scholar
  30. 30.
    Larsen OV, Radeva P, Marti E (1995) Guidelines for choosing optimal parameters of elasticity for snakes. In: Proceedings of the computer analysis of immages and patterns, pp 106–113 Google Scholar
  31. 31.
    Lai KF, Chin RT (1995) Deformable contours: modeling and extraction. IEEE Trans Patt Anal Mach Intell 17(11):1084–1090 CrossRefGoogle Scholar
  32. 32.
    Chen DH, Sun YN (2000) A self-learning segmentation framework—the Taguchi approach. Comput Med Im Graph 24(5):283–296 zbMATHCrossRefGoogle Scholar
  33. 33.
    Morrel JM, Solimini S (1988) Segmentation of images by variational methods: a constructive approach. Rev Mat Univ Complut Madrid 1:169–182 MathSciNetGoogle Scholar
  34. 34.
    Osher S, Sethian J (1988) Fronts propagating with curvature- dependent speed: algorithms based on the Hamilton–Jacobi formulations. J Comput Phys 79:12–49 zbMATHCrossRefMathSciNetGoogle Scholar
  35. 35.
    Goldberg DE (1989) Genetic algorithms in search, optimization and machine learning. Addison–Wesley, Reading zbMATHGoogle Scholar
  36. 36.
    Grefenstette JJ (1986) Optimization of control parameters for genetic algorithms. IEEE Trans Syst Man Cybern 16(1):122–128 CrossRefGoogle Scholar
  37. 37.
    Schmitt LM (2004) Theory of genetic algorithms II: models for genetic operators over the string-tensor representation of populations and convergence to global optima for arbitrary fitness function under scaling. Theor Comput Sci 310:181–231 zbMATHCrossRefGoogle Scholar
  38. 38.
    Min SH, Lee J, Han I (2006) Hybrid genetic algorithms and support vector machines for bankruptcy prediction. Expert Syst Appl 31(3):652–660 CrossRefGoogle Scholar
  39. 39.
    Zhao XM, Cheung YM, Huang DS (2005) A novel approach to extracting features from motif content and protein composition for protein sequence classification. Neural Netw 18:1019–1028 CrossRefGoogle Scholar
  40. 40.
    Plagianakos VP, Magoulas GD, Vrahatis MN (2001) Tumor detection in colonoscopic images using hybrid methods for on-line neural network training. In: Proceedings of international conference on neural networks and expert systems in medicine and healthcare, pp 59–64 Google Scholar
  41. 41.
    Pignalberi G, Cucchiara R, Cinque L, Levialdi S (2003) Tuning range segmentation by genetic algorithm. EURASIP J Appl Signal Process 8:780–790 CrossRefGoogle Scholar
  42. 42.
    Kaus MR, Warfield SK, Jolesz FA, Kikinis R (1999) Segmentation of meningiomas and low grade gliomas in MRI. In: Proceedings of the international conference on medical image computing and computer-assisted intervention, pp 1–10 Google Scholar
  43. 43.
    Syswerda G (1999) A study of reproduction in generational and steady state genetic algorithms. In: Rawlings GJE (ed) Foundations of genetic algorithms. Kaufmann, San Mateo, pp 94–101 Google Scholar
  44. 44.
    Goldberg DE, Korb B, Debb K (1989) Messy genetic algorithms: motivation, analysis and first results. Complex Syst 3(5):493–530 zbMATHGoogle Scholar
  45. 45.
    Eiben AE (2002) Multiparent Recombination in evolutionary computing, advances in evolutionary computing. In: Natural computing series. Springer, Berlin, pp 175–192 Google Scholar
  46. 46.
    van Kemenade KM, Eiben AE (1995) Multi-parent recombination to overcome premature convergence in genetic algorithms. In: Proceedings of the Dutch conference on artificial intelligence, pp 137–146 Google Scholar
  47. 47.
    Bäck T (1993) Optimal mutation rates in genetic search. In: Proceedings of the international conference on genetic algorithms, pp 2–8 Google Scholar
  48. 48.
    Rudolph G (1994) Convergence analysis of canonical genetic algorithms. IEEE Trans Neural Netw 5:96–101 CrossRefGoogle Scholar
  49. 49.
    Goldberg DE (1989) Sizing population for serial and parallel genetic algorithms. In: Proceedings of the international conference on genetic algorithms, pp 70–79 Google Scholar
  50. 50.
    Bäck T, Hammel U, Schwefel HP (1997) Evolutionary computation: Comments on the history and current state. IEEE Trans Evol Comput 1(1):3–17 CrossRefGoogle Scholar
  51. 51.
    Woltjer HH (1996) The intra- and interobserver variability of impedance cardiography in patients at rest during exercise. Physiol Meas 17:171–178 CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC 2007

Authors and Affiliations

  • Dimitris K. Iakovidis
    • 1
    Email author
  • Michalis A. Savelonas
    • 1
  • Stavros A. Karkanis
    • 2
  • Dimitris E. Maroulis
    • 1
  1. 1.Dept. of Informatics and TelecommunicationsUniversity of AthensAthensGreece
  2. 2.Dept. of Informatics and Computer TechnologyTechnological Educational Institute of LamiaLamiaGreece

Personalised recommendations