Automatic Kidney Cysts Segmentation in Digital Ultrasound Images

  • Prema T. Akkasaligar
  • Sunanda Biradar


Computer-aided systems are extensively used in the recent medical field for diagnostics. Medical imaging, particularly ultrasonography is the most commonly used primary diagnostic tool by the medical experts. The segmentation and analysis of region of interest in ultrasound images is a difficult task due to the shape variant objects, orientation, and poor quality. Existing segmentation algorithms need an initial seed point as user input. In this chapter, a novel approach for automatic kidney cysts segmentation in digital ultrasound images is proposed. Initially, contourlet transform is used for preprocessing of kidney ultrasound images and contrast enhancement is performed by using histogram equalization. Initial contour for segmentation closer to the actual cysts boundaries is obtained automatically using morphological operations. Complete automation of active contour method and level set segmentation method is mainly addressed in the work proposed. Further, the diagnostic parameters essentially needed by medical experts, namely, the number of cysts and the size of each cyst, are calculated. The developed method is evaluated using performance parameters such as Jaccard coefficient, Dice, sensitivity, specificity, and accuracy. The efficacy of the developed approach is proved by the results of the experiment.


Ultrasound image Image segmentation Morphological operation Level set Active contours 



The authors are thankful to Dr. Bhushita B. Lakhkar, Radiologist, BLDEDU’s Shri. B. M. Patil Medical College Hospital and Research Centre, Vijayapur for providing USG image set of kidney. Authors are also thankful to Dr. Vinay Kundaragi, Nephrologist, BLDEDU’s Shri. B. M. Patil Medical College Hospital and Research Centre, Vijayapur for rendering manual segmentation of images. This work is financially supported by Vision Group of Science and Technology (VGST), Government of Karnataka under RGS/F scheme.


  1. 1.
    Hagen-Ansert S. Urinary system. Diagnostic ultrasonography-diagnostic ultrasound. St. Louis: Mosby; 1995.Google Scholar
  2. 2.
    Pollack HM, McClennan BL. Clinical urography. 2nd ed. Reading: W.B. Saunders; 2000. p. 1817–23.Google Scholar
  3. 3.
    Maulik U. Medical image segmentation using genetic algorithms. IEEE Trans Inform Tecnol Biomed. 2009;13(2):166–73.CrossRefGoogle Scholar
  4. 4.
    Xie J, Jiang Y, Tsui H. Segmentation of kidney from ultrasound images based on texture and shape. Prioris IEEE Trans Med Imag. 2005;24(1):45–57.CrossRefGoogle Scholar
  5. 5.
    Raja KB, Madheswaran M, Thyagarajah K. Quantitative and qualitative evaluation of US kidney images for disorder classification using multi-scale differential features. ICGST-BIME J. 2000;7:1):1–8.Google Scholar
  6. 6.
    Mendoza CS, Kang X, Safdar N, Myers E, Peters CA, Linguraru MG. Kidney segmentation in ultrasound via genetic initialization and active shape models with rotation correction. Proc IEEE Symp Biomed Imag (ISBI’13) 2013; 69–72.Google Scholar
  7. 7.
    Raja KB, Madheswaran M, Thyagarajah K. A general segmentation scheme for contouring kidney region in ultrasound kidney images using improved higher order spline interpolation. Int J Biological and Life Sci. 2007;2(2):81–8.Google Scholar
  8. 8.
    Akkasaligar Prema T, Biradar S. Classification of medical ultrasound images of kidney. Int J Comput Appl 2014. (ISSN:0975–8887). Special Issue on ICICT. 2014:32–6.Google Scholar
  9. 9.
    Noble JA, Boukerroui D. Ultrasound image segmentation: a survey. IEEE Trans Med Imag. 2006;25(8):987–1010.CrossRefGoogle Scholar
  10. 10.
    Meiburger KM, Acharya UR, Molinari F. Automated localization and segmentation techniques for B-mode ultrasound images: a review. Comput Biol Med. 2018;92:210–35.CrossRefGoogle Scholar
  11. 11.
    Huang J, Yang H, Chen Y, Tang L. Ultrasound kidney segmentation with a global prior shape. J Vis Commun Image Rep. 2013;24:937–43.CrossRefGoogle Scholar
  12. 12.
    Spiegel M, Dieter AH, Volker D, Jakob W, Joachi H. Segmentation of kidney using a new active shape model generation technique based on non-rigid image registration. J Comput Med Imag Graph. 2009;33:29–39.CrossRefGoogle Scholar
  13. 13.
    Hafizah WM, Supriyanto E. Automatic generation of region of interest for kidney ultrasound images using texture analysis. Int J Biol Biomed Eng. 2012;6(1):1289–305.Google Scholar
  14. 14.
    Jeyakumar V, Hasmi MK. Quantitative analysis of segmentation methods on ultrasound kidney image. Int J Adv Res Comput Commun Eng. 2013;2(5):2319–5940.Google Scholar
  15. 15.
    Burckhardt C. Speckle in ultrasound B- mode scans. IEEE Trans Sonics Ultrason. 1978;25:1–6.CrossRefGoogle Scholar
  16. 16.
    Hiremath PS, Akkasaligar Prema T, Badiger S. Speckle reducing Contourlet transform for medical ultrasound images. World Acad Sci Eng Technol Special J Issue. 2011;80:1217–24.Google Scholar
  17. 17.
    Agarwal T, et al. Modified histogram based contrast Enhancementusing Homomorphic filtering for medical images. Paper presented at International Advance Computing Conference (IACC) 2014 Gurgaon, New Delhi, India,21st-22nd Feb 2014, p 964–968.Google Scholar
  18. 18.
    Sonka Milan VH, Roger B. Image processing, analysis and machine vision, 3rd ed. Cengage Learning, Boston. 2013:630–5.Google Scholar
  19. 19.
    Cohen LD, Cohen I. A finite element method applied to new active contour models and 3D reconstruction from cross sections. Paper presented at the 3rd international conference on computer vision, Osaka, Japan, 1990; p 587–591.Google Scholar
  20. 20.
    Chan T, Vese L. Active contours without edges. IEEE Trans Image Proc. 2001;10(2):266–77.ADSCrossRefGoogle Scholar
  21. 21.
    Sussman M, Smereka P, Osher S. A level set approach for computing solutions to incompressible two-phase flow. J Comput Phys. 1994;114(1):146–59.ADSCrossRefGoogle Scholar
  22. 22.
    Osher S, Fedkiw R. Level set methods and dynamic implicit surfaces. New York: Springer; 2002.zbMATHGoogle Scholar
  23. 23.
    Udupa JK, LeBlanc VR. Methodology for evaluating image segmentation algorithms SPIE medical imaging; 2002.Google Scholar
  24. 24.
    Li C, Xu C, Gui C, Fox MD. Level set evolution without re-initialization: A new variational formulation. IEEE Trans Image Process. 2010;19(12):3243–54.ADSMathSciNetCrossRefGoogle Scholar
  25. 25.
    Cerrolaza J, et al. Quantification of kidneys from 3D ultrasound in pediatric hydronephrosis. IEEE International Symp. 2015:157–60.Google Scholar
  26. 26.
    Akkasaligar Prema T, Biradar S. Analysis of polycystic kidney disease in medical ultrasound images. Int J Med Eng Inform. 2018;10(1):49–64.CrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  • Prema T. Akkasaligar
    • 1
  • Sunanda Biradar
    • 1
  1. 1.Department of Computer Science and EngineeringBLDEA’s V. P. Dr. P.G. Halakatti College of Engineering and TechnologyVijayapurIndia

Personalised recommendations