Advertisement

4D Continuous Medial Representation Trajectory Estimation for Longitudinal Shape Analysis

  • Sungmin HongEmail author
  • James Fishbaugh
  • Guido Gerig
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11167)

Abstract

Morphological change of anatomy over time has been of great interest for tracking disease progression, aging, and growth. Shape regression methods have shown great success to model the shape changes over time to create a smooth and representative shape trajectory of sparsely scanned medical images. Shape changes modeled by shape regression methods can be affected by pose changes of shapes caused by neighboring anatomies. Such pose changes can cause informative local shape changes to be obscured and neglected in longitudinal shape analysis. In this paper, we propose a method that estimates a continuous trajectory of medial surfaces with correspondence over time to track longitudinal pose changes and local thickness changes separately. A spatiotemporally continuous medial surface trajectory is estimated by integrating velocity fields from a series of continuous medial representations individually estimated for each shape in a continuous 3D shape trajectory. The proposed method enables straightforward analysis on continuous local thickness changes and pose changes of a continuous multi-object shape trajectory. Longitudinal shape analysis which makes use of correspondence and temporal coherence of the estimated continuous medial surface trajectory is demonstrated with experiments on synthetic examples and real anatomical shape complexes.

Notes

Acknowledgement

This research was supported by NIH NIBIB RO1EB021391 and New York Center for Advanced Technology in Telecommunications (CATT).

References

  1. 1.
    Durrleman, S., Pennec, X., Trouvé, A., Braga, J., Gerig, G., Ayache, N.: Toward a comprehensive framework for the spatiotemporal statistical analysis of longitudinal shape data. Int. J. Comput. Vis. 103(1), 22–59 (2013)MathSciNetCrossRefGoogle Scholar
  2. 2.
    Fishbaugh, J., Prastawa, M., Gerig, G., Durrleman, S.: Geodesic shape regression in the framework of currents. In: Gee, J.C., Joshi, S., Pohl, K.M., Wells, W.M., Zöllei, L. (eds.) IPMI 2013. LNCS, vol. 7917, pp. 718–729. Springer, Heidelberg (2013).  https://doi.org/10.1007/978-3-642-38868-2_60CrossRefGoogle Scholar
  3. 3.
    Gerig, G., Fishbaugh, J., Sadeghi, N.: Longitudinal modeling of appearance and shape and its potential for clinical use. Med. Image Anal. 33, 114–121 (2016)CrossRefGoogle Scholar
  4. 4.
    Gorczowski, K., et al.: Statistical shape analysis of multi-object complexes. In: Computer Vision and Pattern Recognition, pp. 1–8. IEEE (2007)Google Scholar
  5. 5.
    Hong, S., Fishbaugh, J., Gerig, G.: 4D continuous medial representation by geodesic shape regression. In: ISBI 2018. IEEE EMBS (2018)Google Scholar
  6. 6.
    Hong, S., et al.: Subject-specific longitudinal shape analysis by coupling spatiotemporal shape modeling with medial analysis. In: Medical Imaging. SPIE (2017)Google Scholar
  7. 7.
    Joshi, S.C., Miller, M.I., Grenander, U.: On the geometry and shape of brain sub-manifolds. IJPRAI 11(8), 1317–1343 (1997)Google Scholar
  8. 8.
    Kim, E.Y., Johnson, H.J.: Robust multi-site MR data processing: iterative optimization of bias correction, tissue classification, and registration. Front. Neuroinform. 7, 29 (2013)Google Scholar
  9. 9.
    Paulsen, J.S., et al.: Clinical and biomarker changes in premanifest Huntington disease show trial feasibility: a decade of the PREDICT-HD study. Front. Aging Neurosci. 6, 78 (2014)CrossRefGoogle Scholar
  10. 10.
    Pizer, S.M., Gerig, G., Joshi, S., Aylward, S.R.: Multiscale medial shape-based analysis of image objects. Proc. IEEE 91(10), 1670–1679 (2003)CrossRefGoogle Scholar
  11. 11.
    Siddiqi, K., Bouix, S., Tannenbaum, A., Zucker, S.W.: Hamilton-Jacobi skeletons. Int. J. Comput. Vis. 48(3), 215–231 (2002)CrossRefGoogle Scholar
  12. 12.
    Yushkevich, P.A.: Continuous medial representation of brain structures using the biharmonic PDE. NeuroImage 45(1), S99–S110 (2009)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  1. 1.Department of Computer ScienceTandon School of Engineering, New York UniversityBrooklynUSA

Personalised recommendations