Advertisement

Similarity Metric Learning for 2D to 3D Registration of Brain Vasculature

Conference paper
First Online:
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10072)

Abstract

2D to 3D image registration techniques are useful in the treatment of neurological diseases such as stroke. Image registration can aid physicians and neurosurgeons in the visualization of the brain for treatment planning, provide 3D information during treatment, and enable serial comparisons. In the context of stroke, image registration is challenged by the occluded vessels and deformed anatomy due to the ischemic process. In this paper, we present an algorithm to register 2D digital subtraction angiography (DSA) with 3D magnetic resonance angiography (MRA) based upon local point cloud descriptors. The similarity between these local descriptors is learned using a machine learning algorithm, allowing flexibility in the matching process. In our experiments, the error rate of 2D/3D registration using our machine learning similarity metric (52.29) shows significant improvement when compared to a Euclidean metric (152.54). The proposed similarity metric is versatile and could be applied to a wide range of 2D/3D registration.

Keywords

Point Cloud Magnetic Resonance Angiography Digital Subtraction Angiography Image Registration Target Image 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
This is a preview of subscription content, log in to check access.

Notes

Acknowledgments

Prof. Scalzo was partially supported by a AHA grant 16BGIA27760152, a Spitzer grant, and received hardware donations from Gigabyte, Nvidia, and Intel. Alice Tang was partially supported by a UC Leads Fellowship.

References

  1. 1.
    Holmes, D., Rettmann, M., Robb, R.: Visualization in image-guided interventions. In: Peters, T., Cleary, K. (eds.) Image-Guided Interventions: Technology and Applications, pp. 45–80. Springer, New York (2008)CrossRefGoogle Scholar
  2. 2.
    Flood, P.D., Banks, S.A.: Automated registration of three-dimensional knee implant models to fluoroscopic images using lipschitzian optimization. IEEE Trans. Med. Imaging PP(99), 1 (2016). doi: 10.1109/TMI.2016.2553111 CrossRefGoogle Scholar
  3. 3.
    Otake, Y., Wang, A.S., Stayman, J.W., Uneri, A., Kleinszig, G., Vogt, S., Khanna, A.J., Gokaslan, Z.L., Siewerdsen, J.H.: Robust 3D–2D image registration: application to spine interventions and vertebral labeling in the presence of anatomical deformation. Phys. Med. Biol. 58, 8535–8553 (2013)CrossRefGoogle Scholar
  4. 4.
    Fu, D., Kuduvalli, G.: A fast, accurate, and automatic 2D–3D image registration for image-guided cranial radiosurgery. Med. Phys. 35(5), 2180–2194 (2008)CrossRefGoogle Scholar
  5. 5.
    Markelj, P., Tomaevi, D., Likar, B., Pernu, F.: A review of 3D/2D registration methods for image-guided interventions. Med. Image Anal. 16, 642–661 (2012)CrossRefGoogle Scholar
  6. 6.
    Alves, R.S., Tavares, J.M.R.S.: Computer image registration techniques applied to nuclear medicine images. In: Tavares, J.M.R.S., Natal Jorge, R.M. (eds.) Computational and Experimental Biomedical Sciences: Methods and Applications. LNCVB, vol. 21, pp. 173–191. Springer, Heidelberg (2015). doi: 10.1007/978-3-319-15799-3_13 Google Scholar
  7. 7.
    Tavares, J.M.R.S.: Analysis of biomedical images based on automated methods of image registration. In: Bebis, G., et al. (eds.) ISVC 2014. LNCS, vol. 8887, pp. 21–30. Springer, Heidelberg (2014). doi: 10.1007/978-3-319-14249-4_3 Google Scholar
  8. 8.
    Oliveira, F.P., Tavares, J.M.R.: Medical image registration: a review. Comput. Methods Biomech. Biomed. Engin. 17, 73–93 (2014)CrossRefGoogle Scholar
  9. 9.
    Chen, X., Varley, M.R., Shark, L.K., Shentall, G.S., Kirby, M.C.: An extension of iterative closest point algorithm for 3D–2D registration for pre-treatment validation in radiotherapy. In: MedVis, pp. 3–8 (2006)Google Scholar
  10. 10.
    Birkfellner, W., Stock, M., Figl, M., Gendrin, C., Hummel, J., Dong, S., Kettenbach, J., Georg, D., Bergmann, H.: Stochastic rank correlation: a robust merit function for 2D/3D registration of image data obtained at different energies. Med. Phys. 36, 3420–3428 (2009)CrossRefGoogle Scholar
  11. 11.
    Vermandel, M., Betrouni, N., Gauvrit, J.Y., Pasquier, D., Vasseur, C., Rousseau, J.: Intrinsic 2D/3D registration based on a hybrid approach: use in the radiosurgical imaging process. Cell. Mol. Biol. 52, 44–53 (2006)Google Scholar
  12. 12.
    Oliveira, F.P., Pataky, T.C., Tavares, J.M.R.: Registration of pedobarographic image data in the frequency domain. Comput. Methods Biomech. Biomed. Engin 13, 731–740 (2010)CrossRefGoogle Scholar
  13. 13.
    Khandelwal, P., Yavagal, D.R., Sacco, R.L.: Acute ischemic stroke intervention. J. Am. Coll. Cardiol. 67, 2631–2644 (2016)CrossRefGoogle Scholar
  14. 14.
    Frangi, A.F., Niessen, W.J., Vincken, K.L., Viergever, M.A.: Multiscale vessel enhancement filtering. In: Wells, W.M., Colchester, A., Delp, S. (eds.) MICCAI 1998. LNCS, vol. 1496, pp. 130–137. Springer, Heidelberg (1998). doi: 10.1007/BFb0056195 CrossRefGoogle Scholar
  15. 15.
    Cai, D., He, X., Han, J.: Spectral regression for efficient regularized subspace learning. In: ICCV, pp. 1–8 (2007)Google Scholar
  16. 16.
    Lagarias, J.C., Reeds, J.A., Wright, M.H., Wright, P.E.: Convergence properties of the nelder-mead simplex method in low dimensions. SIAM J. Optim. 9, 112–147 (1998)MathSciNetCrossRefzbMATHGoogle Scholar
  17. 17.
    Scalzo, F., Liebeskind, D.S.: Perfusion angiography in acute ischemic stroke. Comput. Math. Methods Med. 2014, 1–14 (2016). doi: 10.1155/2016/2478324. Article ID 2478324MathSciNetCrossRefGoogle Scholar
  18. 18.
    Scalzo, F., Hao, Q., Walczak, A.M., Hu, X., Hoi, Y., Hoffmann, K.R., Liebeskind, D.S.: Computational hemodynamics in intracranial vessels reconstructed from biplane angiograms. In: Bebis, G., et al. (eds.) ISVC 2010. LNCS, vol. 6455, pp. 359–367. Springer, Heidelberg (2010). doi: 10.1007/978-3-642-17277-9_37 CrossRefGoogle Scholar
  19. 19.
    Nam, H.S., Scalzo, F., Leng, X., Ip, H.L., Lee, H.S., Fan, F., Chen, X., Soo, Y., Miao, Z., Liu, L., Feldmann, E., Leung, T., Wong, K.S., Liebeskind, D.S.: Hemodynamic impact of systolic blood pressure and hematocrit calculated by computational fluid dynamics in patients with intracranial atherosclerosis. J. Neuroimaging 26, 331–338 (2016)CrossRefGoogle Scholar
  20. 20.
    Leng, X., Scalzo, F., Fong, A.K., Johnson, M., Ip, H.L., Soo, Y., Leung, T., Liu, L., Feldmann, E., Wong, K.S., Liebeskind, D.S.: Computational fluid dynamics of computed tomography angiography to detect the hemodynamic impact of intracranial atherosclerotic stenosis. Neurovascular Imaging 1, 1 (2015)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2016

Authors and Affiliations

  1. 1.Neurovascular Imaging Research Core, Department of Neurology and Computer ScienceUniversity of California, Los Angeles (UCLA)Los AngelesUSA

Personalised recommendations

Cite paper

Buy options