Neural Network Boundary Detection for 3D Vessel Segmentation

  • Robert Ieuan Palmer
  • Xianghua XieEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10016)


Conventionally, hand-crafted features are used to train machine learning algorithms, however choosing useful features is not a trivial task as they are very much data-dependent. Given raw image intensities as inputs, supervised neural networks (NNs) essentially learn useful features by adjusting the weights of its nodes using the back-propagation algorithm. In this paper we investigate the performance of NN architectures for the purpose of boundary detection, before integrating a chosen architecture in a data-driven deformable modelling framework for full segmentation. Boundary detection performed well, with boundary sensitivity of >88 % and specificity of >85 % for highly obscured and diffused lymphatic vessel walls. In addition, the vast majority of all boundary-classified pixels were in the immediate vicinity of the ground truth boundary. When integrated into a 3D deformable modelling framework it produced an area overlap with the ground truth of >98 %, and both point-to-mesh and Hausdorff distance errors were less than other approaches. To this end it has been shown that NNs are suitable for boundary detection in deformable modelling, where object boundaries are obscured, diffused and low in contrast.


  1. 1.
    Chiverton, J., Xie, X., Mirmehdi, M.: Automatic bootstrapping and tracking of object contours. IEEE T-IP 21(3), 1231–1245 (2012)MathSciNetCrossRefGoogle Scholar
  2. 2.
    Espona, L., Carreira, M., Penedo, M., Ortega, M.: Retinal vessel tree segmentation using a deformable contour model. In: ICPR, pp. 2128–2131 (2008)Google Scholar
  3. 3.
    Essa, E., Xie, X., Jones, J.-L.: Minimum s-excess graph for segmenting and tracking multiple borders with HMM. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9350, pp. 28–35. Springer, Heidelberg (2015). doi: 10.1007/978-3-319-24571-3_4 CrossRefGoogle Scholar
  4. 4.
    Hu, Y., Rogers, W., Coast, D., Kramer, C., Reichek, N.: Vessel boundary extraction based on a global and local deformable physical model with variable stiffness. MRI 16, 943–951 (1998)CrossRefGoogle Scholar
  5. 5.
    Jones, J.-L., Essa, E., Xie, X., Smith, D.: Interactive segmentation of media-adventitia border in IVUS. In: Wilson, R., Hancock, E., Bors, A., Smith, W. (eds.) CAIP 2013. LNCS, vol. 8048, pp. 466–474. Springer, Heidelberg (2013). doi: 10.1007/978-3-642-40246-3_58 CrossRefGoogle Scholar
  6. 6.
    Jones, J., Xie, X., Essa, E.: Combining region-based and imprecise boundary-based cues for interactive medical image segmentation. J. Numer. Methods Biomed. Eng. 30(12), 1649–1666 (2014)CrossRefGoogle Scholar
  7. 7.
    Kirbas, C., Quek, F.: A review of vessel extraction techniques and algorithms. ACM Comput. Surv. (CSUR) 36(2), 81–121 (2004)CrossRefGoogle Scholar
  8. 8.
    Lee, S., Wolberg, G., Shin, S.Y.: Scattered data interpolation with multilevel b-splines. Trans. Vis. Comput. Graph. 3, 228–244 (1997)CrossRefGoogle Scholar
  9. 9.
    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
  10. 10.
    Lu, D., Yu, X., Jin, X., Li, B., Chen, Q., Zhu, J.: Neural network based edge detection for automated medical diagnosis. In: IEEE ICIA, pp. 343–348 (2011)Google Scholar
  11. 11.
    Ma, J., Lu, L., Zhan, Y., Zhou, X., Salganicoff, M., Krishnan, A.: Hierarchical segmentation and identification of thoracic vertebra using learning-based edge detection and coarse-to-fine deformable model. In: Jiang, T., Navab, N., Pluim, J.P.W., Viergever, M.A. (eds.) MICCAI 2010. LNCS, vol. 6361, pp. 19–27. Springer, Heidelberg (2010). doi: 10.1007/978-3-642-15705-9_3 CrossRefGoogle Scholar
  12. 12.
    McInerney, T., Terzopoulos, D.: Deformable models in medical image analysis: a survey. MIA 1(2), 91–108 (1996)Google Scholar
  13. 13.
    Mesejo, P., Ibáñez, O., Cordón, O., Cagnoni, S.: A survey on image segmentation using metaheuristic-based deformable models: state of the art and critical analysis. Appl. Soft Comput. 44, 1–29 (2016)CrossRefGoogle Scholar
  14. 14.
    Paiement, A., Mirmehdi, M., Xie, X., Hamilton, M.: Integrated segmentation and interpolation of sparse data. IEEE T-IP 23(11), 3902–3914 (2014)MathSciNetGoogle Scholar
  15. 15.
    Palmer, R., Xie, X., Tam, G.: Automatic aortic root segmentation with shape constraints and mesh regularisation. In: BMVC (2015)Google Scholar
  16. 16.
    Senthilkumaran, N., Rajesh, R.: Edge detection techniques for image segmentation-a survey of soft computing approaches. IJRTE 1(2), 250–254 (2009)Google Scholar
  17. 17.
    Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: Proceedings of the Conference on Computer Vision and Pattern Recognition, pp. 511–518 (2001)Google Scholar
  18. 18.
    Xie, X., Mirmehdi, M.: Magnetostatic field for the active contour model: a study in convergence. In: BMVC, pp. 127–136 (2006)Google Scholar
  19. 19.
    Xie, X., Mirmehdi, M.: Implicit active model using radial basis function interpolated level sets. In: BMVC, pp. 1–10 (2007)Google Scholar
  20. 20.
    Yeo, S., Xie, X., Sazonov, I., Nithiarasu, P.: Level set segmentation with robust image gradient energy and statistical shape prior. In: IEEE ICIP (2011)Google Scholar
  21. 21.
    Yim, P., Cebral, R., Mullick, R., Choyle, P.: Vessel surface reconstruction with a tubular deformable model. IEEE T-MI 20, 1411–1421 (2001)Google Scholar

Copyright information

© Springer International Publishing AG 2016

Authors and Affiliations

  1. 1.Department of Computer ScienceSwansea UniversitySwanseaUK

Personalised recommendations