Advertisement

The Automatic Two – Step Vessel Lumen Segmentation Algorithm for Carotid Bifurcation Analysis during Perfusion Examination

  • Marek R. Ogiela
  • Tomasz Hachaj
Part of the Smart Innovation, Systems and Technologies book series (SIST, volume 16)

Abstract

The novel path detection algorithm and the region growing based lumen detection algorithm is the main contribution of this article. The proposed lumen segmentation method is consisted of two sub-algorithms. After preprocessing step the first algorithm detects the possible path between start and end point. In the second step it performs the thinning of previously obtained path. The second algorithm is a region – growing procedure with proper homogeneity criteria. The role of this procedure is to segment the whole lumen of considered vessel. The region growing is computed in axial slices and the seed point for growing method in each slice is a voxel taken from path computed in previous step. The proposed method was tested on six carotid arteries structures obtained from CTA examination. Our researches has shown that with our method it is possible to keep the TPR (true positive rate) in 5 from 6 considered cases on the level higher than 80% with FPR (false positive rate) below 1%.

Keywords

Lumen segmentation carotid bifurcation computed tomography angiography brain perfusion maps computer - aided diagnosis 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Fawcett, T., Graphs, R.O.C.: Notes and Practical Considerations for Researchers, vol. 31, pp. 1–38, HPL-2003-4. Citeseer (2003-2004)Google Scholar
  2. 2.
    Lu, Y., Jiang, T., Zanga, Y.: Region growing method for the analysis of functional MRI data. NeuroImage 20, 455–465 (2003)CrossRefGoogle Scholar
  3. 3.
    Krissian, K., Garcia, S.A.: A Minimal Cost Path and Level Set Evolution Approach for Carotid Bifurcation Segmentation. In: Proc. of MICCAI 2009 Workshop: Carotid Lumen Segmentation and Stenosis Grading Challenge (2009)Google Scholar
  4. 4.
    Freiman, M., Frank, J., Weizman, L., Nammer, E., Shilon, O., Joskowicz, L., Sosna, J.: Nearly automatic vessels segmentation using graph-based energy minimization. In: Proc. 3rd 3D Segmentation in the Clinic: Carotid Lumen segmentation challenge workshop, 12th Int. Conf. on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2009, London, UK (2009)Google Scholar
  5. 5.
    Hameeteman, R., Zuluaga, M., Joskowicz, L., Freiman, M., Van Walsum, T.: Carotid lumen segmentation and stenosis grading challenge, 4.2, 5.1 (May 2009), http://cls2009.bigr.nl/download/evaluationframework2009.pdf
  6. 6.
    Steinman, D.A., Poepping, T.L., Tambasco, M., Rankin, R.N., Holdsworth, D.W.: Flow Patterns at the Stenosed Carotid Bifurcation: Effect of Concentric versus Eccentric Stenosis. Annals of Biomedical Engineering 28(4), 415–423, doi:10.1114/1.279Google Scholar
  7. 7.
    Frangi, A.F., Niessen, W.J., Vincken, K.L., Viergever, M.A.: Multiscale Vessel Enhancement Filtering. In: Wells, W.M., Colchester, A.C.F., Delp, S.L. (eds.) MICCAI 1998. LNCS, vol. 1496, pp. 130–137. Springer, Heidelberg (1998)Google Scholar
  8. 8.
    Cuisenaire, O., Virmani, S., Olszewski, M.E., Ardon, R.: Fully automated segmentation of carotid and vertebral arteries from contrast enhanced CTA. In: Proceedings of SPIE (2008), vol. 6914, pp. 69143R-69143R-8. Spie (2008)Google Scholar
  9. 9.
    Scharf, J., et al.: Improvement of Sensitivity and Interrater Reliability to Detect Acute Stroke by Dynamic Perfusion Computed Tomography and Computed Tomography Angiography. Journal of Computer Assisted Tomography 30(1), 105–110 (2006)MathSciNetCrossRefGoogle Scholar
  10. 10.
    Josephson, S.A., Bryant, S.O., Mak, H.K., Johnston, S.C., Dillon, W.P., Smith, W.S.: Evaluation of carotid stenosis using CT angiography in the initial evaluation of stroke and TIA. Neurology 63(3), 457–460 (2004)Google Scholar
  11. 11.
    Trzupek, M., Ogiela, M.R., Tadeusiewicz, R.: Intelligent image content semantic description for cardiac 3D visualisations. Engineering Applications of Artificial Intelligence 24, 1410–1418 (2011)CrossRefGoogle Scholar
  12. 12.
    Hachaj, T., Ogiela, M.R.: Automatic detection and lesion description in cerebral blood flow and cerebral blood volume perfusion maps. Journal of Signal Processing Systems for Signal, Image, and Video Technology 61(3), 317–328 (2010)CrossRefGoogle Scholar
  13. 13.
    Hachaj, T., Ogiela, M.R.: A system for detecting and describing pathological changes using dynamic perfusion computer tomography brain maps. Computers in Biology and Medicine 41, 402–410 (2011)CrossRefGoogle Scholar
  14. 14.
    Hachaj, T., Ogiela, M.R.: CAD system for automatic analysis of CT perfusion maps. Opto-Electronics Review 19(1), 95–103 (2011), doi:10.2478/s11772-010-0071-2CrossRefGoogle Scholar
  15. 15.
    Trzupek, M.: Semantic Modelling of Coronary Vessel Structures in Computer Aided Detection of Pathological Changes. In: Tjoa, A.M., Quirchmayr, G., You, I., Xu, L. (eds.) ARES 2011. LNCS, vol. 6908, pp. 220–227. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  16. 16.
    Hameeteman, K., et al.: Evaluation framework for carotid bifurcation lumen segmentation and stenosis grading. Medical Image Analysis 15(4), 477–488 (2011)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  1. 1.AGH University of Science and TechnologyKrakowPoland
  2. 2.Institute of Computer Science and Computer MethodsPedagogical University of KrakowKrakowPoland

Personalised recommendations