Classification of Cross-sections for Vascular Skeleton Extraction Using Convolutional Neural Networks

  • Kristína LidayováEmail author
  • Anindya Gupta
  • Hans Frimmel
  • Ida-Maria Sintorn
  • Ewert Bengtsson
  • Örjan Smedby
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 723)


Recent advances in Computed Tomography Angiography provide high-resolution 3D images of the vessels. However, there is an inevitable requisite for automated and fast methods to process the increased amount of generated data. In this work, we propose a fast method for vascular skeleton extraction which can be combined with a segmentation algorithm to accelerate the vessel delineation. The algorithm detects central voxels - nodes - of potential vessel regions in the orthogonal CT slices and uses a convolutional neural network (CNN) to identify the true vessel nodes. The nodes are gradually linked together to generate an approximate vascular skeleton. The CNN classifier yields a precision of 0.81 and recall of 0.83 for the medium size vessels and produces a qualitatively evaluated enhanced representation of vascular skeletons.


Vascular skeleton CT angiography Convolutional neural networks Classification 



Lidayová, Frimmel, Bengtsson, and Smedby have been supported by the Swedish Research Council (VR), grant no. 621-2014-6153. Gupta has been supported by Skype IT Academy Stipend Program, EU institutional grant IUT19-11 of Estonian Research Council.


  1. 1.
    Lidayová, K., Frimmel, H., Wang, C., Bengtsson, E., Smedby, Ö.: Fast vascular skeleton extraction algorithm. Pattern Recogn. Lett. 76, 67–75 (2016)CrossRefGoogle Scholar
  2. 2.
    Kirbas, C., Quek, F.: A review of vessel extraction techniques and algorithms. ACM Comput. Surv. (CSUR) 36(2), 81–121 (2004)CrossRefGoogle Scholar
  3. 3.
    Lesage, D., Angelini, E.D., Bloch, I., Funka-Lea, G.: A review of 3D vessel lumen segmentation techniques: models, features and extraction schemes. Med. Image Anal. 13(6), 819–845 (2009)CrossRefGoogle Scholar
  4. 4.
    Charbonnier, J.P., van Rikxoort, E.M., Setio, A.A., Schaefer-Prokop, C.M., van Ginneken, B., Ciompi, F.: Improving airway segmentation in computed tomography using leak detection with convolutional networks. Med. Image Anal. 36, 52–60 (2017)CrossRefGoogle Scholar
  5. 5.
    Merkow, J., Marsden, A., Kriegman, D., Tu, Z.: Dense volume-to-volume vascular boundary detection. In: Ourselin, S., Joskowicz, L., Sabuncu, M.R., Unal, G., Wells, W. (eds.) MICCAI 2016. LNCS, vol. 9902, pp. 371–379. Springer, Cham (2016). doi: 10.1007/978-3-319-46726-9_43 CrossRefGoogle Scholar
  6. 6.
    Gülsün, M.A., Funka-Lea, G., Sharma, P., Rapaka, S., Zheng, Y.: Coronary centerline extraction via optimal flow paths and CNN path pruning. In: Ourselin, S., Joskowicz, L., Sabuncu, M.R., Unal, G., Wells, W. (eds.) MICCAI 2016. LNCS, vol. 9902, pp. 317–325. Springer, Cham (2016). doi: 10.1007/978-3-319-46726-9_37 CrossRefGoogle Scholar
  7. 7.
    Yushkevich, P.A., Piven, J., Hazlett, H.C., Smith, R.G., Ho, S., Gee, J.C., Gerig, G.: User-guided 3D active contour segmentation of anatomical structures: significantly improved efficiency and reliability. Neuroimage 31(3), 1116–1128 (2006)CrossRefGoogle Scholar
  8. 8.
    Tieleman, T., Hinton, G.: Lecture 6.5-RmsProp: divide the gradient by a running average of its recent magnitude. In: COURSERA: Neural Networks for ML (2012)Google Scholar
  9. 9.
    Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feed-forward neural networks. In: AISTATS, vol. 9, pp. 249–256 (2010)Google Scholar
  10. 10.
    Srivastava, N., Hinton, G.E., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929–1958 (2014)MathSciNetzbMATHGoogle Scholar
  11. 11.
    Chollet, F.: Keras (2015).
  12. 12.
    Springenberg, J.T., Dosovitskiy, A., Brox, T., Riedmiller, M.: Striving for simplicity: the all convolutional net. In: Proceedings of 3rd International Conference on Learning Representations (ICLR) (2015)Google Scholar
  13. 13.
    Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift (2015). arXiv preprint arXiv:1502.03167
  14. 14.
    Nair, V., Hinton, G.E.: Rectified linear units improve restricted Boltzmann machines. In: 27th International Conference on Machine Learning, pp. 807–814 (2010)Google Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Kristína Lidayová
    • 1
    Email author
  • Anindya Gupta
    • 2
  • Hans Frimmel
    • 3
  • Ida-Maria Sintorn
    • 1
  • Ewert Bengtsson
    • 1
  • Örjan Smedby
    • 4
  1. 1.Department of IT, Centre for Image AnalysisUppsala UniversityUppsalaSweden
  2. 2.T. J. Seebeck Department of ElectronicsTallinn University of TechnologyTallinnEstonia
  3. 3.Division of Scientific Computing, Department of ITUppsala UniversityUppsalaSweden
  4. 4.School of Technology and HealthKTH Royal Institute of TechnologyStockholmSweden

Personalised recommendations