The Application of the Region Growing Method to the Determination of Arterial Changes

  • Ewelina Sobotnicka
  • Aleksander SobotnickiEmail author
  • Krzysztof Horoba
  • Piotr Porwik
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9876)


The paper discusses segmentation of medical images depicting aortic aneurysms and atherosclerotic changes in coronary vessels. The region growing method was deployed for segmentation. Before segmentation with the aforementioned method, the images were subjected to edging in order to acquire significant information, such as the size of the analyzed structure and pixel distribution. Edging paired with the region growing method ensures proper isolation of pixels with the same intensity, without the unwanted pixel overflow. In order to verify the method, results obtained by various authors were referred to, and a statistical analysis was performed to calculate the Dice coefficient.


Segmentation Region growing Aortic aneurysms Coronary vessels 


  1. 1.
    Al-Agamy, A., Osman, N., Fahmy, A.: Segmentation of ascending and descending aorta from magnetic resonance flow images. In: Biomedical Engineering Conference (CIBEC), pp. 41–44 (2010)Google Scholar
  2. 2.
    Avila-Montes, O., Kurkure, U., Nakazato, R., Berman, D., Dey, D.: Segmentation of the thoracic aorta in noncontrast cardiac CT images. IEEE J. Biomed. Health Inform. 17(5), 936–949 (2013)CrossRefGoogle Scholar
  3. 3.
    Ben Ayed, I., Wang, M., Miles, B., Garvin, G.J.: TRIC: trust region for invariant compactness and its application to abdominal aorta segmentation. In: Golland, P., Hata, N., Barillot, C., Hornegger, J., Howe, R. (eds.) MICCAI 2014, Part I. LNCS, vol. 8673, pp. 381–388. Springer, Heidelberg (2014)Google Scholar
  4. 4.
    Babin, D., Devos, D., Pizurica, A.: Robust segmentation methods with an application to aortic pulsewave velocity calculation. Comput. Med. Imaging Graph. 38, 179–189 (2014)CrossRefGoogle Scholar
  5. 5.
    Benmansour, F., Cohen, L.: A new interactive method for coronary arteries segmentation based on tubular anisotropy. In: International Symposium on Biomedical Imaging: From Nano to Macro. IEEE (2009)Google Scholar
  6. 6.
    Bruijne, M., Ginneken, B., Niessen, W., Loog, M., Viergever, M.: Model-based segmentation of abdominal aortic aneurysms in CTA images. In: SPIE, vol. 5032 (2003)Google Scholar
  7. 7.
    Chen, S., Wang, T., Lee, W.: Coronary arteries segmentation based on the 3D discrete wavelet transform and 3D neutrosophic transform. Biomed. Res. Int. 2015, 1–9 (2015). doi: 10.1155/2015/798303. Article ID 798303. PMID 25648181
  8. 8.
    Egger, J., Freisleben, B., Setser, R., Renapuraar, R.: Aorta segmentation for stent simulation. In: CI2BM09 – MICCAI (2011)Google Scholar
  9. 9.
    Goyal, P., Goyal, K., Gupta, V.: Calcification detection in coronary arteries using image processing. Int. J. Adv. Res. Comput. Sci. Softw. Eng. 3(8), 279–284 (2013). ISSN: 2277 128XGoogle Scholar
  10. 10.
    Goyal, P., Gupta, V., Goyal, K.: Segmentation of coronary arteries of heart. Int. J. Adv. Electr. Electron. Eng. 2(1), 93–98 (2013). ISSN: 2319-1112Google Scholar
  11. 11.
    Kovacs, T.,Cattin, P., Alkadhi, H.: Automatic segmentation of the vessel lumen from 3D CTA images of aortic dissection, Bildverarbeitung für die Medizin, pp. 161–165. Springer (2006)Google Scholar
  12. 12.
    Lara, D., Faria, A., Araújo, A., Menotti, D.: A novel hybrid method for the segmentation of thr coronary artery tree in 2D angiograms. Int. J. Comput. Sci. Inf. Technol. (IJCSIT) 5(3), 45–64 (2013). doi: 10.5121/ijcsit.2013.5304
  13. 13.
    Macía, I., Legarreta, J.H., Paloc, C., Graña, M., Maiora, J., García, G., de Blas, M.: Segmentation of abdominal aortic aneurysms in CT images using a radial model approach. In: Corchado, E., Yin, H. (eds.) IDEAL 2009. LNCS, vol. 5788, pp. 664–671. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  14. 14.
    Okusz, I., Ünay, D., Kadpasaoglu, K.: A hybrid method for coronary artery stenoses detection and quantification in CTA images. In: MICCAI Workshop 3d Cardiovascular Imaging: A MICCAI Segmentation (2012)Google Scholar
  15. 15.
    Ozkan, H.: Segmentation of ascending and descending Aorta in CTA images. Int. J. Med. Health, Biomed. Bioeng. Pharm. Eng. 6(5), 451–453 (2012)Google Scholar
  16. 16.
    Piekar, E., Momot, A.: Gradient and polynomial approximation methods for medical image segmentation. J. Med. Imaging Health Inf. 5, 1337–1349 (2015)CrossRefGoogle Scholar
  17. 17.
    Piekar, E., Szwarc, P., Sobotnicki, A., Momot, M.: Application of region growing method to brain tumor segmentation-preliminary results. J. Med. Inf. Technol. 22 (2013). ISSN 1642-6037Google Scholar
  18. 18.
    Roussona, M., Baib, Y., Xua, C., Sauera, F.: Probabilistic minimal path for automated esophagus segmentation. In: SPIE, vol. 6144 (2006)Google Scholar
  19. 19.
    Tek, H., Zheng, Y., Gulsun, M., Funka-Lea, G.: An automatic system for segmenting coronary arteries from CTA. In: MICCAI Workshop on Computing and Visualization for Intravascular Imaging (2011)Google Scholar
  20. 20.
    Zhao, F., Zhang, H., Wahle, A.: Automated 4D Segmentation of Aortic Magnetic Resonance Images. In: BMVC, pp. 247–256 (2006)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  • Ewelina Sobotnicka
    • 1
  • Aleksander Sobotnicki
    • 1
    Email author
  • Krzysztof Horoba
    • 1
  • Piotr Porwik
    • 2
  1. 1.Institute of Medical Technology and EquipmentZabrzePoland
  2. 2.Institute of Computer ScienceUniversity of SilesiaSosnowiecPoland

Personalised recommendations