A tree-topology preserving pairing for 3D/2D registration

  • Thomas Benseghir
  • Grégoire Malandain
  • Régis Vaillant
Original Article



Fusing preoperative and intra-operative information into a single space aims at taking advantage of two complementary modalities and necessitates a step of registration that must provide good alignment and relevant correspondences. This paper addresses both purposes in the case of 3D/2D vessel tree matching.


We propose a registration algorithm endorsing this vascular tree nature by providing a pairing procedure that preserves the tree topology and by integrating this pairing into an iterative algorithm maintaining pairing coherence. In addition, we define two complementary error measures quantifying the resulting alignment error and pairing error, and both are based on manual ground-truth that is independent of the type of transformation to retrieve.


Experiments were conducted on a database of 63 clinical cases, evaluating robustness and accuracy of our approach with respect to the iterative closest point algorithm.


The proposed method exhibits good results in terms of both pairing and alignment as well as low sensitivity to rotations to be compensated (up to 30\(^{\circ }\)).


Registration Tree Coronary arteries  X-ray  Navigation Iterative closest curve 


Conflict of interest

Thomas Benseghir, Grégoire Malandain and Régis Vaillant declare that they have no conflict of interest.


  1. 1.
    Baka N, Metz CT, Schultz CJ, van Geuns RJ, Niessen WJ, van Walsum T (2014) Oriented gaussian mixture models for nonrigid 2d/3d coronary artery registration. IEEE Trans Med Imaging 33(5):1023–1034CrossRefPubMedGoogle Scholar
  2. 2.
    Benseghir T, Malandain G, Vaillant R (2013) Iterative closest curve: a framework for curvilinear structure registration application to 2d/3d coronary arteries registration. In: Medical image computing and computer-assisted intervention—MICCAI 2013, vol 8149, pp 179–186Google Scholar
  3. 3.
    Besl P, McKay N (1992) A method for registration of 3-d shapes. IEEE Trans Pattern Anal Mach Intell 14(2):239–256CrossRefGoogle Scholar
  4. 4.
    Duong L, Liao R, Sundar H, Tailhades B, Meyer A, Xu C (2009) Curve-based 2d–3d registration of coronary vessels for image guided procedure. In: SPIE, vol 7261Google Scholar
  5. 5.
    Eiter T, Mannila H (1994) Computing discrete fréchet distance. Tech. rep, Christian Doppler Laboratory for Expert Systems, TU Vienna, AustriaGoogle Scholar
  6. 6.
    Granger S, Pennec X (2002) Multi-scale em-icp: a fast and robust approach for surface registration. In: European conference on computer vision, vol 2353, pp 418–432Google Scholar
  7. 7.
    Groher M, Bender F, Hoffmann RT, Navab N (2007) Segmentation-driven 2d–3d registration for abdominal catheter interventions. In: Medical image computing and computer-assisted intervention—MICCAI 2007, vol 4792, pp 527–535Google Scholar
  8. 8.
    Groher M, Zikic D, Navab N (2009) Deformable 2d–3d registration of vascular structures in a one view scenario. IEEE Trans Med Imaging 28(6):847–860CrossRefPubMedGoogle Scholar
  9. 9.
    Jian B, Vemuri B (2011) Robust point set registration using Gaussian mixture models. IEEE Trans Pattern Anal Mach Intell 33(8):1633–1645CrossRefGoogle Scholar
  10. 10.
    Krissian K, Malandain G, Ayache N, Vaillant R, Trousset Y (2000) Model-based detection of tubular structures in 3D images. Comput Vision Image Underst 80(2):130–171CrossRefGoogle Scholar
  11. 11.
    Lacroix R, Florent R, Auvray V (2012) Model-based segmentation of the left main coronary bifurcation from 2d angiograms. In: IEEE international symposium on biomedical imaging (ISBI), pp 780–783Google Scholar
  12. 12.
    Lee JH, Won CH (2011) Topology preserving relaxation labeling for nonrigid point matching. IEEE Trans Pattern Anal Mach Intell 33(2):427–432CrossRefPubMedGoogle Scholar
  13. 13.
    Liu A, Bullitt E (1998) 3d/2d registration via skeletal near projective invariance in tubular objects. In: Medical image computing and computer-assisted interventation—MICCAI 98, pp 780–787Google Scholar
  14. 14.
    Maintz J, Viergever M (1998) A survey of medical image registration. Med Image Anal 2(1):1–36CrossRefPubMedGoogle Scholar
  15. 15.
    Markelj P, Tomaževič D, Likar B, Pernuš F (2012) A review of 3d/2d registration methods for image-guided interventions. Med Image Anal 16(3):642–661CrossRefPubMedGoogle Scholar
  16. 16.
    Metz CT, Schaap M, Klein S, Baka N, Neefjes LA, Schultz CJ, Niessen WJ, Walsum TV (2013) Registration of 3d+t coronary cta and monoplane 2d+t X-ray angiography. IEEE Trans Med Imaging 32(5):919–931CrossRefPubMedGoogle Scholar
  17. 17.
    Myronenko A, Song X (2010) Point set registration: coherent point drift. IEEE Trans Pattern Anal Mach Intell 32(12):2262–2275CrossRefPubMedGoogle Scholar
  18. 18.
    Rivest-Henault D, Sundar H, Cheriet M (2012) Nonrigid 2d/3d registration of coronary artery models with live fluoroscopy for guidance of cardiac interventions. IEEE Trans Med Imaging 31(8):1557–1572CrossRefPubMedGoogle Scholar
  19. 19.
    Rusinkiewicz S, Levoy M (2001) Efficient variants of the icp algorithm. In: IEEE third international conference on 3-D digital imaging and modeling, pp 145–152Google Scholar
  20. 20.
    Serradell E, Pinheiro M, Sznitman R, Kybic J, Moreno-Noguer F, Fua P (2015) Non-rigid graph registration using active testing search. IEEE Trans Pattern Anal Mach Intell 37(3):625–638CrossRefGoogle Scholar
  21. 21.
    Serradell E, Romero A, Leta R, Gatta C, Moreno-Noguer F (2011) Simultaneous correspondence and non-rigid 3d reconstruction of the coronary tree from single X-ray images. In: International conference on computer vision 2011, pp 850–857Google Scholar
  22. 22.
    Smeets D, Bruyninckx P (2010) Robust matching of 3d lung vessel trees. In: MICCAI workshop on pulmonary image analysis vol 2, pp 61–70Google Scholar

Copyright information

© CARS 2015

Authors and Affiliations

  • Thomas Benseghir
    • 1
    • 2
  • Grégoire Malandain
    • 2
  • Régis Vaillant
    • 1
  1. 1.GE-HealthcareBucFrance
  2. 2.INRIASophia AntipolisFrance

Personalised recommendations