Advertisement

Robust Supervoxel Matching Combining Mid-Level Spectral and Context-Rich Features

  • Florian Tilquin
  • Pierre-Henri Conze
  • Patrick Pessaux
  • Mathieu Lamard
  • Gwenolé Quellec
  • Vincent Noblet
  • Fabrice Heitz
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11075)

Abstract

This paper presents an innovative way to reach accurate semi-dense registration between images based on robust matching of structural entities. The proposed approach relies on a decomposition of images into visual primitives called supervoxels generated by aggregating adjacent voxels sharing similar characteristics. Two new categories of features are estimated at the supervoxel extent: mid-level spectral features relying on a spectral method applied on supervoxel graphs to capture the non-linear modes of intensity displacements, and mid-level context-rich features describing the broadened spatial context on the resulting spectral representations. Accurate supervoxel pairings are established by nearest neighbor search on these newly designed features. The effectiveness of the approach is demonstrated against state-of-the-art methods for semi-dense longitudinal registration of abdominal CT images, relying on liver label propagation and consistency assessment.

Keywords

Semi-dense image registration Supervoxel matching Mid-level representation Laplacian graph Spectral decomposition Context-rich features 

Notes

Acknowledgments

This work was partly funded by France Life Imaging (grant ANR-11-INBS-0006 from Investissements d’Avenir program). We acknowledge Visible Patient, www.visiblepatient.com, for 3D liver segmentation masks.

References

  1. 1.
    Schnabel, J.A., Heinrich, M.P., Papież, B.W., Brady, J.M.: Advances and challenges in deformable image registration: from image fusion to complex motion modelling. Med. Image Anal. 33, 145–148 (2016)CrossRefGoogle Scholar
  2. 2.
    Kanavati, F., Tong, T., Misawa, K., Fujiwara, M., Mori, K., Rueckert, D., Glocker, B.: Supervoxel classification forests for estimating pairwise image correspondences. Pattern Recogn. 63, 561–569 (2017)CrossRefGoogle Scholar
  3. 3.
    Conze, P.H., Tilquin, F., Noblet, V., Rousseau, F., Heitz, F., Pessaux, P.: Hierarchical multi-scale supervoxel matching using random forests for automatic semi-dense abdominal image registration. In: International Symposium on Biomedical Imaging (2017)Google Scholar
  4. 4.
    Giraud, R., Ta, V.T., Bugeau, A., Coupé, P., Papadakis, N.: Superpatchmatch: an algorithm for robust correspondences using superpixel patches. IEEE Trans. Image Process. 26(8), 4068–4078 (2017)MathSciNetCrossRefGoogle Scholar
  5. 5.
    Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P., Susstrunk, S.: SLIC superpixels compared to state-of-the-art superpixel methods. IEEE Trans. Pattern Anal. Mach. Intell. 34(11), 2274–2282 (2012)CrossRefGoogle Scholar
  6. 6.
    Fan, H., Xiang, J., Chen, Z.: Visual tracking by local superpixel matching with Markov random field. In: Pacific Rim Conference on Multimedia (2016)Google Scholar
  7. 7.
    Lombaert, H., Grady, L., Pennec, X., Ayache, N., Cheriet, F.: Spectral log-demons: diffeomorphic image registration with very large deformations. Int. J. Comput. Vis. 107(3), 254–271 (2014)CrossRefGoogle Scholar
  8. 8.
    Belkin, M., Niyogi, P.: Laplacian Eigenmaps and spectral techniques for embedding and clustering. In: Advances in Neural Information Processing Systems (2002)Google Scholar
  9. 9.
    Criminisi, A., Shotton, J., Robertson, D., Konukoglu, E.: Regression forests for efficient anatomy detection and localization in CT studies. In: MICCAI Workshop on Medical Computer Vision, pp. 106–117 (2010)CrossRefGoogle Scholar
  10. 10.
    Arnoldi, W.E.: The principle of minimized iterations in the solution of the matrix eigenvalue problem. Q. Appl. Math. 9(1), 17–29 (1951)MathSciNetCrossRefGoogle Scholar
  11. 11.
    Kuhn, H.W.: The Hungarian method for the assignment problem. Naval Res. Logist. 2, 83–97 (1955)MathSciNetCrossRefGoogle Scholar
  12. 12.
    Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Florian Tilquin
    • 1
  • Pierre-Henri Conze
    • 2
    • 3
  • Patrick Pessaux
    • 4
  • Mathieu Lamard
    • 3
    • 5
  • Gwenolé Quellec
    • 3
  • Vincent Noblet
    • 1
  • Fabrice Heitz
    • 1
  1. 1.ICube UMR 7357, Université de Strasbourg, CNRS, FMTSStrasbourgFrance
  2. 2.IMT AtlantiqueBrestFrance
  3. 3.Inserm, LaTIM UMR 1101BrestFrance
  4. 4.Institut Hospitalo-Universitaire de StrasbourgStrasbourgFrance
  5. 5.Université de Bretagne OccidentaleBrestFrance

Personalised recommendations