Advertisement

Towards Grey Scale-Based Tensor Voting for Blood Vessel Analysis

  • Daniel Jörgens
  • Rodrigo Moreno
Conference paper
Part of the Mathematics and Visualization book series (MATHVISUAL)

Abstract

Tensor Voting is a technique that uses perceptual rules to group points in a set of input data. Its main advantage lies in its ability to robustly extract geometrical shapes like curves and surfaces from point clouds even in noisy scenarios. Following the original formulation this is achieved by exploiting the relative positioning of those points with respect to each other. Having this in mind, it is not a straight forward task to apply original tensor voting to greyscale images. Due to the underlying voxel grid, digital images have all data measurements at regularly sampled positions. For that reason, the pure spatial position of data points relative to each other does not provide useful information unless one considers the measured intensity value in addition to that.

To account for that, previous approaches of employing tensor voting to scalar images have followed mainly two ideas. One is to define a subset of voxels that are likely to resemble a desired structure like curves or surfaces in the original image in a preprocessing step and to use only those points for initialisation in tensor voting. In other methods, the encoding step is modified e.g. by using estimations of local orientations for initialisation.

In contrast to these approaches, another idea is to embed all information given as input, that is position in combination with intensity value, into a 4D space and perform classic tensor voting on that. In doing so, it is neither necessary to rely on a preprocessing step for estimating local orientation features nor is it needed to employ assumptions within the encoding step as all data points are initialised with unit ball tensors. Alternatively, the intensity dimension could be partially included by considering it in the weighting function of tensor voting while still employing 3D tensors for the voting. Considering the advantage of a shorter computation time for the latter approach, it is of interest to investigate the differences between these two approaches.

Although different methods have employed an ND implementation of tensor voting before, the actual interpretation of its output, that is the estimation of a local hyper surface at each point, depends on the actual application at hand. As we are especially interested in the analysis of blood vessels in CT angiography data, we study the feasibility of detecting tubular structures and the estimation of their orientation totally within the proposed framework and also compare the two mentioned approaches with a special focus on these aspects.

In this chapter we first provide the formulation of both approaches followed by the application-specific interpretations of the shape of 4D output tensors. Based on that, we compare the information inferred by both methods from both synthetic and medical image data focusing on the application of blood vessel analysis.

Notes

Acknowledgements

We thank Hortense Kirisli, Theo van Walsum and Wiro Niessen for providing the CTA data used in the experiments. This research has been supported by the Swedish Research Council (VR), grants no. 2014-6153 and 2012-3512, and the Swedish Heart-Lung Foundation (HLF), grant no. 2011-0376.

References

  1. 1.
    Aylward, S., Bullitt, E., Pizer, S., Eberly, D.: Intensity ridge and widths for tubular object segmentation and description. In: Proceedings of the Workshop on Mathematical Methods in Biomedical Image Analysis, pp. 131–138. IEEE, Piscataway (1996)Google Scholar
  2. 2.
    Cetin, S., Unal, G.: A higher-order tensor vessel tractography for segmentation of vascular structures. IEEE Trans. Med. Imaging 34(10), 2172–2185 (2015)CrossRefGoogle Scholar
  3. 3.
    Cetin, S., Demir, A., Yezzi, A., Degertekin, M., Unal, G.: Vessel tractography using an intensity based tensor model with branch detection. IEEE Trans. Med. Imaging 32(2), 348–363 (2013)CrossRefGoogle Scholar
  4. 4.
    Cheng, G., Zhu, F., Xiang, S., Pan, C.: Accurate urban road centerline extraction from VHR imagery via multiscale segmentation and tensor voting. Neurocomputing 205, 407–420 (2016)CrossRefGoogle Scholar
  5. 5.
    Dumortier, Y., Herlin, I., Ducrot, A.: 4-d tensor voting motion segmentation for obstacle detection in autonomous guided vehicle. In: 2008 IEEE Intelligent Vehicles Symposium, pp. 379–384. IEEE, Piscataway (2008)Google Scholar
  6. 6.
    Frangi, A.F., Niessen, W.J., Vincken, K.L., Viergever, M.A.: Multiscale vessel enhancement filtering. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 130–137. Springer, Berlin (1998)Google Scholar
  7. 7.
    Franken, E., van Almsick, M., Rongen, P., Florack, L., ter Haar Romeny, B.: An efficient method for tensor voting using steerable filters. In: Computer Vision–ECCV, ECCV’06, pp. 228–240. Springer, Berlin (2006)Google Scholar
  8. 8.
    Fridman, Y., Pizer, S.M., Aylward, S., Bullitt, E.: Segmenting 3D branching tubular structures using cores. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 570–577. Springer, Berlin (2003)Google Scholar
  9. 9.
    Guest, I.W.: Tensor voting on sparse motion vector estimation. In: Proceedings of the Fifteenth Annual Symposium of the Pattern Recognition Association of South Africa (PRASA), pp. 7–11 (2004)Google Scholar
  10. 10.
    Jia, J., Tang, C.K.: Image repairing: Robust image synthesis by adaptive nd tensor voting. In: 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Proceedings, vol. 1, pp. 643–650. IEEE, Piscataway (2003)Google Scholar
  11. 11.
    Kim, H.S., Choi, H.K., Lee, K.H.: Feature detection of triangular meshes based on tensor voting theory. Comput. Aided Des. 41(1), 47–58 (2009)CrossRefGoogle Scholar
  12. 12.
    Kirişli, H., Schaap, M., Metz, C., Dharampal, A., Meijboom, W.B., Papadopoulou, S., Dedic, A., Nieman, K., De Graaf, M., Meijs, M., et al.: Standardized evaluation framework for evaluating coronary artery stenosis detection, stenosis quantification and lumen segmentation algorithms in computed tomography angiography. Med. Image Anal. 17(8), 859–876 (2013)CrossRefGoogle Scholar
  13. 13.
    Kustra, J., Jalba, A., Telea, A.: Robust segmentation of multiple intersecting manifolds from unoriented noisy point clouds. In: Computer Graphics Forum, vol. 33, pp. 73–87. Wiley Online Library (2014)Google Scholar
  14. 14.
    Leng, Z., Korenberg, J., Roysam, B., Tasdizen, T.: A rapid 2-D centerline extraction method based on tensor voting. In: 2011 IEEE International Symposium on Biomedical Imaging: From Nano to Macro, pp. 1000–1003 (2011)Google Scholar
  15. 15.
    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
  16. 16.
    Liu, M.: Efficient segmentation and plane modeling of point-cloud for structured environment by normal clustering and tensor voting. In: 2014 IEEE International Conference on Robotics and Biomimetics (ROBIO), pp. 1805–1810 (2014)Google Scholar
  17. 17.
    Lombardi, G., Casiraghi, E., Campadelli, P.: Curvature estimation and curve inference with tensor voting: a new approach. In: Advanced Concepts for Intelligent Vision Systems, pp. 613–624. Springer, Berlin (2008)Google Scholar
  18. 18.
    Lombardi, G., Rozza, A., Casiraghi, E., Campadelli, P.: A novel approach for geometric clustering based on tensor voting framework. In: Proceedings of the 21st Italian Workshop on Neural Nets WIRN11, pp. 129–138 (2011)Google Scholar
  19. 19.
    Loss, L., Bebis, G., Parvin, B.: Iterative tensor voting for perceptual grouping of ill-defined curvilinear structures. IEEE Trans. Med. Imaging 30(8), 1503–1513 (2011)CrossRefGoogle Scholar
  20. 20.
    Loss, L.A., Bebis, G., Chang, H., Auer, M., Sarkar, P., Parvin, B.: Automatic segmentation and quantification of filamentous structures in electron tomography. In: Proceedings of the ACM Conference on Bioinformatics, Computational Biology and Biomedicine, pp. 170–177. ACM, New York (2012)Google Scholar
  21. 21.
    Medioni, G., Tang, C.K., Lee, M.S.: Tensor voting: theory and applications. In: Proceedings of RFIA, Paris, France, vol. 3 (2000)Google Scholar
  22. 22.
    Miao, Z., Wang, B., Shi, W., Wu, H.: A method for accurate road centerline extraction from a classified image. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 7(12), 4762–4771 (2014)CrossRefGoogle Scholar
  23. 23.
    Mordohai, P., Medioni, G.: Dimensionality estimation, manifold learning and function approximation using tensor voting. J. Mach. Learn. Res. 11, 411–450 (2010)MathSciNetMATHGoogle Scholar
  24. 24.
    Moreno, R., Garcia, M., Puig, D.: Robust color image segmentation through tensor voting. In: 20th International Conference on Pattern Recognition (ICPR), pp. 3372–3375 (2010)Google Scholar
  25. 25.
    Moreno, R., Garcia, M., Puig, D., Pizarro, L., Burgeth, B., Weickert, J.: On improving the efficiency of tensor voting. IEEE Trans. Pattern Anal. Mach. Intell. 33(11), 2215–2228 (2011)CrossRefGoogle Scholar
  26. 26.
    Moreno, R., Pizarro, L., Burgeth, B., Weickert, J., Garcia, M.A., Puig, D.: Adaptation of tensor voting to image structure estimation. In: New Developments in the Visualization and Processing of Tensor Fields, pp. 29–50. Springer, Berlin (2012)Google Scholar
  27. 27.
    Mottini, A., Descombes, X., Besse, F.: Axon extraction from fluorescent confocal microscopy images. In: 9th IEEE International Symposium on Biomedical Imaging, pp. 764–767 (2012)Google Scholar
  28. 28.
    Nicolescu, M., Medioni, G.: A voting-based computational framework for visual motion analysis and interpretation. IEEE Trans. Pattern Anal. Mach. Intell. 27(5), 739–752 (2005)CrossRefGoogle Scholar
  29. 29.
    Park, M.K., Lee, S.J., Lee, K.H.: Multi-scale tensor voting for feature extraction from unstructured point clouds. Graph. Model. 74(4), 197–208 (2012)CrossRefGoogle Scholar
  30. 30.
    Risser, L., Plouraboué, F., Descombes, X.: Gap filling of 3-D microvascular networks by tensor voting. IEEE Trans. Med. Imaging 27(5), 674–687 (2008)CrossRefGoogle Scholar
  31. 31.
    Schultz, T.: Towards resolving fiber crossings with higher order tensor inpainting. In: New Developments in the Visualization and Processing of Tensor Fields, pp. 253–265. Springer, Berlin (2012)Google Scholar
  32. 32.
    Strokina, N., Kurakina, T., Eerola, T., Lensu, L., Kälviäinen, H.: Detection of curvilinear structures by tensor voting applied to fiber characterization. In: Scandinavian Conference on Image Analysis, pp. 22–33. Springer, Berlin (2013)Google Scholar
  33. 33.
    Tao, L., Murino, V., Medioni, G.: A tensor voting approach for the hierarchical segmentation of 3-D acoustic images. In: First International Symposium on 3D Data Processing Visualization and Transmission, pp. 126–135. IEEE, Piscataway (2002)Google Scholar
  34. 34.
    Tomasi, C., Manduchi, R.: Bilateral filtering for gray and color images. In: 6th International Conference on Computer Vision, pp. 839–846. IEEE, Piscataway (1998)Google Scholar
  35. 35.
    Tong, W.S., Tang, C.K.: Robust estimation of adaptive tensors of curvature by tensor voting. IEEE Trans. Pattern Anal. Mach. Intell. 27(3), 434–449 (2005)CrossRefGoogle Scholar
  36. 36.
    Wang, J., Lu, H., Liu, Q.: Feature space analysis using low-order tensor voting. In: 2004 International Conference on Image Processing, vol. 4, pp. 2681–2684 (2004)Google Scholar
  37. 37.
    Yigitsoy, M., Navab, N.: Structure propagation for image registration. IEEE Trans. Med. Imaging 32(9), 1657–1670 (2013)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  1. 1.School of Technology and HealthKTH Royal Institute of TechnologyHuddingeSweden

Personalised recommendations