Segmenting MR Images by Level-Set Algorithms for Perspective Colorectal Cancer Diagnosis

  • Mumtaz Hussain Soomro
  • Gaetano Giunta
  • Andrea Laghi
  • Damiano Caruso
  • Maria Ciolina
  • Cristiano De Marchis
  • Silvia Conforto
  • Maurizio Schmid
Conference paper
Part of the Lecture Notes in Computational Vision and Biomechanics book series (LNCVB, volume 27)

Abstract

Segmentation is an essential and crucial step in interpreting medical images for possible treatment. Medical image segmentation is very chaotic procedure as medical image may have different structures of same organ in different image modalities and may also have different features in different image slices of same modality. In this work, we present a comparison of segmentation algorithms based on level set methods, viz. Caselles, Chan & Vese, Li, Lankton, Bernard, and Shi algorithms. We assessed these algorithms with our T2-weighted colorectal MR images using Dice coefficient that measures the similarity between the reference sketched by specialist and the segmentation result produced by each algorithm. In addition, computational time taken by each algorithm to perform the segmentation is also computed. Our results on average Dice coefficient and average time computation demonstrate that Bernard has the lowest average Dice coefficient and the highest computational complexity followed by Li which has second lowest Dice coefficient and highest computational complexity. Lankton has achieved satisfactory results on average Dice coefficient and computational complexity followed by Chan & Vese and Shi. Whereas, Caselles algorithm outperforms than all with respect to average Dice coefficient and computational time.

Keywords

Magnetic Resonance Imaging (MRI) T2-weighted colorectal MRI Medical image segmentation Level set segmentation algorithm 

References

  1. 1.
    Ashiya: Notes on the structure and functions of large intestine of human body, February 2013. http://www.preservearticles.com/201105216897/notes-on-the-structure-and-functions-of-large-intestine-of-human-body.html
  2. 2.
    Soomro, M.H., Giunta, G., Laghi, A., Caruso, D., Ciolina, M., De Marchis, C., Conforto, S., Schmid, M.: Haralick’s texture analysis applied to colorectal T2-weighted MRI: a preliminary study of significance for cancer evolution. In: Proceedings of 13th IASTED (BioMed 2017), pp. 16–19 (2017)Google Scholar
  3. 3.
    Scholefield, J., et al. (eds.): Challenges in Colorectal Cancer, 2nd edn. Wiley-Blackwell, Oxford (2006)Google Scholar
  4. 4.
    Colon Cancer Alliance: Colon Cancer Risk Factors, December 2012. http://www.ccalliance.org/colorectal_cancer/riskfactors.html
  5. 5.
    Kaur, H., Choi, H., Nancy, Y.Y., Rauch, G.M., Jensen, C.T., Hou, P., Chang, G.J., Skibber, J.M., Ernst, R.D.: MR imaging for preoperative evaluation of primary rectal cancer: practical considerations. J. RadioGr. 32(2), 389–409 (2012)CrossRefGoogle Scholar
  6. 6.
    Tapan, U., Özbayrak, M., Tatlı, S.: MRI in local staging of rectal cancer: an update. J. Diagn. Interv. Radiol. 20(5), 390–398 (2014)CrossRefGoogle Scholar
  7. 7.
    Atkin, W., Dadswell, E., Wooldrage, K.: Computed tomographic colonography versus colonoscopy for investigation of patients with symptoms suggestive of colorectal cancer (SIGGAR): a multicentre randomised trial. Lancet 381, 1194 (2013)CrossRefGoogle Scholar
  8. 8.
    Furukawa, H., Ikuma, H., Seki, A.: Positron emission tomography scanning is not superior to whole body multidetector helical computed tomography in the preoperative staging of colorectal cancer. Gut 55, 1007 (2006)CrossRefGoogle Scholar
  9. 9.
    Caselles, V., Kimmel, R., Sapiro, G.: Geodesic active contours. Int. J. Comput. Vision 22, 61–79 (1997)CrossRefMATHGoogle Scholar
  10. 10.
    Chan, T., Vese, L.: Active contours without edges. IEEE Trans. Image Process. 10, 266–277 (2001)CrossRefMATHGoogle Scholar
  11. 11.
    Li, C., Kao, C.Y., Gore, J.C., Ding, Z.: Minimization of region-scalable fitting energy for image segmentation. IEEE Trans. Image Process. 17, 1940–1949 (2008)CrossRefMATHMathSciNetGoogle Scholar
  12. 12.
    Lankton, S., Tannenbaum, A.: Localizing region based active contours. IEEE Trans. Image Process. 17, 2029–2039 (2008)CrossRefMATHMathSciNetGoogle Scholar
  13. 13.
    Bernard, O., Friboulet, D., Thévenaz, P., Unser, M.: Variational B-Spline level-set: a linear filtering approach for fast deformable model evolution. IEEE Trans. Image Process. 18, 1179–1191 (2009)CrossRefMATHMathSciNetGoogle Scholar
  14. 14.
    Shi, Y., Karl, W.C.: A real-time algorithm for the approximation of level-set based curve evolution. IEEE Trans. Image Process. 17, 645–656 (2008)CrossRefMathSciNetGoogle Scholar
  15. 15.
    Dietenbeck, T., Alessandrini, M., Friboulet, D., Bernard, O.: CREASEG: a free software for the evaluation of image segmentation algorithms based on level-set. In: International Conference on Image Processing (2010)Google Scholar
  16. 16.
    Yezzi, J.A., Tsai, A., Willsky, A.: A fully global approach to image segmentation via coupled curve evolution equations. J. Vis. Commun. Image Represent. 13(1), 195–216 (2002)CrossRefGoogle Scholar
  17. 17.
    Belaroussi, B., Milles, J., Carme, S., Zhu, Y.M., Benoit, C.H.: Intensity non-uniformity correction in MRI: existing methods and their validation. Med. Image Anal. 10, 234–246 (2006)CrossRefGoogle Scholar
  18. 18.
    McAuliffe, M.J., Lalonde, F.M., McGarry, D., Gandler, W., Csaky, K., Trus, B.L.: Medical image processing, analysis and visualization in clinical research. In: Computer-Based Medical Systems (2001)Google Scholar

Copyright information

© Springer International Publishing AG 2018

Authors and Affiliations

  • Mumtaz Hussain Soomro
    • 1
  • Gaetano Giunta
    • 1
  • Andrea Laghi
    • 2
  • Damiano Caruso
    • 2
  • Maria Ciolina
    • 2
  • Cristiano De Marchis
    • 1
  • Silvia Conforto
    • 1
  • Maurizio Schmid
    • 1
  1. 1.Department of EngineeringUniversity of Roma TreRomeItaly
  2. 2.Department of Radiological, Oncological and Pathological SciencesUniversity of Rome La SapienzaRomeItaly

Personalised recommendations