Recursive tracking of vascular tree axes in 3D medical images

  • Juan F. Carrillo
  • Marcela Hernández Hoyos
  • Eduardo E. Dávila
  • Maciej Orkisz
Original article

Abstract

Object This article describes a method for automated extraction of branching structures in three dimensional (3D) medical images.

Materials and methods The algorithm recursively tracks branches and detects bifurcations by analyzing the binary connected components on the surface of a sphere that moves along the vessels. Local segmentation within the sphere is performed using a clustering algorithm based on both geometric and intensity information. It minimizes a combination of the intra-class intensity variances and of the inertia moment of the “vessel” class, which emphasizes the cylindrical structures. The algorithm was applied to 16 MRA and 12 CTA 3D images of different anatomic regions. Its capability of extracting all the branches and avoiding spurious detections was evaluated by comparing the number of extracted branches with the number of branches found by visual inspection of the datasets. Its reproducibility and sensitivity to parameter variation were also assessed.

Results With a fixed parameter setting, 68 out of 286 perceptible branches were missed or partly extracted and 11 spurious branches were obtained. Increasing the weight of the geometric criterion helped in tracking the principal branches in noisy data but increased the number of missed branches. Processing time was within 5 min per dataset.

Conclusion From one initial point, the algorithm extracts a vascular tree where the differences of size and of intensity between the branches are not large. Missed sub-trees can be recovered using additional starting points.

Keywords

Vascular diseases Magnetic resonance angiography Computed tomography angiography Three-dimensional image Computer assisted image processing 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Suri JS, Liu K, Reden L, Laxminarayan S (2002). A review on MR vascular image processing: skeleton versus nonskeleton approaches: part II. IEEE Trans Inf Technol Biomed 6:338–350PubMedCrossRefGoogle Scholar
  2. 2.
    Tizon X (2004) Algorithms for the analysis of 3D magnetic resonance angiography images (Acta Universitatis Agriculturæ Sueciæ, Uppsala, ISBN 91-576-670-4Google Scholar
  3. 3.
    Wink O (2004) Vessel axis determination (Print Partner Ipskamp, Amsterdam, ISBN 90-393-3698-9Google Scholar
  4. 4.
    Kirbas C, Quek FKH (2004). A review of vessel extraction techniques and algorithms. ACM Comput Surv 36:81–121CrossRefGoogle Scholar
  5. 5.
    Hernández Hoyos M, Orkisz M, Douek PC, Magnin IE (2005). Assessment of carotid artery stenoses in 3D contrast-enhanced magnetic resonance angiography, based on improved generation of the centerline. Mach Graph Vis 22:349–378Google Scholar
  6. 6.
    Bullitt E, Aylward S, Smith K, Mukherji S, Jiroutek M, Muller K (2001). Symbolic description of intracerebral vessels segmented from magnetic resonance angiograms and evaluation by comparison with X-ray angiograms. Med Image Anal 5:157–169PubMedCrossRefGoogle Scholar
  7. 7.
    Aylward S, Bullitt E (2002). Initialization, noise, singularities and scale in height ridge traversal for tubular object centerline extraction. IEEE Trans Med Imaging 21(2):61–75PubMedCrossRefGoogle Scholar
  8. 8.
    Toumoulin C, Boldak C, Dillenseger JL, Coatrieux JL, Rolland Y (2001). Fast detection and characterization of vessels in very large data sets using geometrical moments. IEEE Trans Biomed Eng 48:604–606PubMedCrossRefGoogle Scholar
  9. 9.
    Shim H, Yun ID, Lee KM, Lee SU (2005) Partition-based extraction of cerebral arteries from CT angiography with emphasis on adaptive tracking. In: Information processing med imaging, Glenwood Springs. LNCS, vol 3565. Springer, Heidelberg, pp 357–368Google Scholar
  10. 10.
    Yim PJ, Choyke PL, Summers RM (2000). Gray-scale skeletonization of small vessels in magnetic resonance angiography. IEEE Trans Med Imaging 19:568–576PubMedCrossRefGoogle Scholar
  11. 11.
    Descoteaux M, Collins L, Siddiqi K (2004) Geometric flows for segmenting vasculature in MRI: theory and validation. In: MICCAI—med image computing and computer-assisted intervention, Saint-Malo, France, Springer Verlag LNCS 3216:500–507Google Scholar
  12. 12.
    Manniesing R, Niessen W (2004) Local speed functions in level set based vessel segmentation. In: MICCAI—med image computing and computer-assisted intervention, Saint-Malo. LNCS, vol 3216. Springer, Heidelberg, pp 475–482Google Scholar
  13. 13.
    Lorenz C, Renisch S, Schlathölter T, Bülow T (2003). Simultaneous segmentation and tree reconstruction of the coronary arteries in MSCT images. In: Med imaging, San Diego. Proc SPIE 5031:167–177Google Scholar
  14. 14.
    Shikata H, Hoffman EA, Sonka M (2004) Automated segmentation of pulmonary vascular tree from 3D CT images. In: med imaging, San Diego. Proc SPIE 5369:107–116, doi: 10.1117/12.537032Google Scholar
  15. 15.
    Agam G, Armato SG, Wu C (2005). Vessel tree reconstruction in thoracic CT scans with application to nodule detection. IEEE Trans Med Imaging 24:486–499PubMedCrossRefGoogle Scholar
  16. 16.
    Flasque N, Desvignes M, Constans JM, Revenu M (2001). Acquisition, segmentation and tracking of the cerebral vascular tree on 3D magnetic resonance angiography images. Med Image Anal 5:173–183PubMedCrossRefGoogle Scholar
  17. 17.
    Antiga L, Ene-Iordache B, Remuzzi G, Remuzzi A (2001). Automatic generation of glomerular capillary topological organization. Microvascular Research 62:346–354PubMedCrossRefGoogle Scholar
  18. 18.
    Carrillo JF, Orkisz M, Hernández Hoyos M (2005) Extraction of 3D vascular tree skeletons based on the analysis of connected components evolution. In: CAIP’2005—11th Int IAPR Conference computer analysis of images and patterns, Versailles. LNCS, vol 3691. Springer, Heidelberg, pp 604–611Google Scholar
  19. 19.
    MacQueen J (1967) Some methods for classification and analysis of multivariate observations. In: 5th Berkeley Symposium Math Stat and Prob, Berkeley, University of California Press 1:281–297Google Scholar
  20. 20.
    Otsu N (1979). A threshold selection method from gray-level histograms. IEEE Trans Syst Man Cyber. (SMC) 9(1):63–66Google Scholar
  21. 21.
    Mukundan R, Ramakrishnan KR (1998). Moment functions in image analysis, theory and applications. World Scientific Publishing Co. Pte. Ltd., Singapore, 150 pGoogle Scholar
  22. 22.
    Saito T and Toriwaki JI (1994). New algorithms for Euclidean distance transformations of an n-dimensional digitised picture with applications. Pattern Recogn 27:1551–1565CrossRefGoogle Scholar
  23. 23.
    Wink O, Niessen WJ, Frangi AF, Verdonck B, Viergever MA (2002). 3D MRA coronary axis determination using a minimum cost path approach. Magn Res Med 47:1169–1175CrossRefGoogle Scholar

Copyright information

© CARS 2007

Authors and Affiliations

  • Juan F. Carrillo
    • 1
    • 2
  • Marcela Hernández Hoyos
    • 1
  • Eduardo E. Dávila
    • 2
  • Maciej Orkisz
    • 2
  1. 1.Grupo de Ingeniería Biomédica, Grupo ImagíneUniversidad de los AndesBogotaColombia
  2. 2.CNRS (UMR 5515) and INSERM (U630) Research UnitCREATIS, Université Lyon 1, INSA LyonVilleurbanne CedexFrance

Personalised recommendations