Abstract
Radiation therapy presents a need for dynamic tracking of a target tumor volume. Fiducial markers such as implanted gold seeds have been used to gate radiation delivery but the markers are invasive and gating significantly increases treatment time. Pretreatment acquisition of a respiratory correlated 4DCT allows for determination of accurate motion tracking which is useful in treatment planning. We design a patient-specific motion subspace and a deep convolutional neural network to recover anatomical positions from a single fluoroscopic projection in real-time. We use this deep network to approximate the nonlinear inverse of a diffeomorphic deformation composed with radiographic projection. This network recovers subspace coordinates to define the patient-specific deformation of the lungs from a baseline anatomic position. The geometric accuracy of the subspace deformations on real patient data is similar to accuracy attained by original image registration between individual respiratory-phase image volumes.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bauer, M., Joshi, S., Modin, K.: Diffeomorphic density matching by optimal information transport. SIAM J. Imaging Sci. 8(3), 1718–1751 (2015). https://doi.org/10.1137/151006238
Foote, M., Sabouri, P., Sawant, A., Joshi, S.: Rank constrained diffeomorphic density motion estimation for respiratory correlated computed tomography. In: Cardoso, M., et al. (eds.) GRAIL/MFCA/MICGen -2017. LNCS, vol. 10551, pp. 177–185. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-67675-3_16
Geneser, S., Hinkle, J., Kirby, R., Wang, B., Salter, B., Joshi, S.: Quantifying variability in radiation dose due to respiratory-induced tumor motion. Med. Image Anal. 15(4), 640–649 (2011). https://doi.org/10.1016/j.media.2010.07.003
Ha, I.Y., Wilms, M., Handels, H., Heinrich, M.P.: Model-based sparse-to-dense image registration for realtime respiratory motion estimation in image-guided interventions. IEEE Trans. Biomed. Eng. 66(2), 302–310 (2019). https://doi.org/10.1109/TBME.2018.2837387
Huang, G., Liu, Z., van der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2261–2269. IEEE, July 2017. https://doi.org/10.1109/CVPR.2017.243
Keall, P.J., Joshi, S., Vedam, S.S., Siebers, J.V., Kini, V.R., Mohan, R.: Four-dimensional radiotherapy planning for DMLC-based respiratory motion tracking. Med. Phys. 32(4), 942–951 (2005). https://doi.org/10.1118/1.1879152
Khesin, B., Lenells, J., Misiołek, G., Preston, S.C.: Geometry of diffeomorphism groups, complete integrability and Geometric statistics. Geom. Funct. Anal. 23(1), 334–366 (2013). https://doi.org/10.1007/s00039-013-0210-2
Li, R., et al.: On a PCA-based lung motion model. Phys. Med. Biol. 56(18), 6009–6030 (2011). https://doi.org/10.1088/0031-9155/56/18/015
Markelj, P., Tomaževič, D., Likar, B., Pernuš, F.: A review of 3D/2D registration methods for image-guided interventions. Med. Image Anal. 16(3), 642–661 (2012). https://doi.org/10.1016/j.media.2010.03.005. https://linkinghub.elsevier.com/retrieve/pii/S1361841510000368
Modin, K.: Generalized hunter-saxton equations, optimal information transport, and factorization of diffeomorphisms. J. Geom. Anal. 25(2), 1306–1334 (2015). https://doi.org/10.1007/s12220-014-9469-2
Paszke, A., et al.: Automatic differentiation in PyTorch. In: NIPS-W (2017)
Pleiss, G., Chen, D., Huang, G., Li, T., van der Maaten, L., Weinberger, K.Q.: Memory-efficient implementation of DenseNets. arXiv preprint http://arxiv.org/abs/1707.06990, July 2017
Preston, J., Hinkle, J., Singh, N., Rottman, C., Joshi, S.: PyCA: python for computational anatomy. https://bitbucket.org/scicompanat/pyca
Rottman, C., Bauer, M., Modin, K., Joshi, S.C.: Weighted diffeomorphic density matching with applications to thoracic image registration. In: 5th MICCAI Workshop on Mathematical Foundations of Computational Anatomy (MFCA 2015), pp. 1–12 (2015)
Rottman, C., Larson, B., Sabouri, P., Sawant, A., Joshi, S.: Diffeomorphic density registration in thoracic computed tomography. In: Ourselin, S., Joskowicz, L., Sabuncu, M.R., Unal, G., Wells, W. (eds.) MICCAI 2016. LNCS, vol. 9902, pp. 46–53. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46726-9_6
Rottman, C., McBride, L., Cheryauka, A., Whitaker, R., Joshi, S.: Mobile C-arm 3D reconstruction in the presence of uncertain geometry. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9350, pp. 692–699. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24571-3_83
Sabouri, P., et al.: A novel method using surface monitoring to capture breathing-induced cycle-to-cycle variations with 4DCT. In: 59th Annual Meeting of the American Association of Physicists in Medicine, Denver, CO (2017). http://www.aapm.org/meetings/2017AM/PRAbs.asp?mid=127&aid=37742
Sawant, A., et al.: Investigating the feasibility of rapid MRI for image-guided motion management in lung cancer radiotherapy. BioMed. Res. Int. 2014 (2014). https://doi.org/10.1155/2014/485067
Sawant, A., et al.: Management of three-dimensional intrafraction motion through real-time DMLC tracking. Med. Phys. 35(5), 2050–2061 (2008). https://doi.org/10.1118/1.2905355
Sherouse, G.W., Novins, K., Chaney, E.L.: Computation of digitally reconstructed radiographs for use in radiotherapy treatment design. Int. J. Radiat. Oncol. Biol. Phys. 18(3), 651–658 (1990). https://doi.org/10.1016/0360-3016(90)90074-T
Staub, D., Murphy, M.J.: A digitally reconstructed radiograph algorithm calculated from first principles. Med. Phys. 40(1) (2013). https://doi.org/10.1118/1.4769413
U.S. Cancer Statistics Working Group: U.S. Cancer Statistics Working Group. United States Cancer Statistics: 1999–2014 Incidence and Mortality Web-based Report. Atlanta: U.S. Department of Health and Human Services, Centers for Disease Control and Prevention and National Cancer Institute. Technical report, Centers for Disease Control and Prevention and National Cancer Institute (2017). https://nccd.cdc.gov/uscs/
Acknowledgements
This work was partially supported through research funding from the National Institute of Health (R01 CA169102 and R03 EB026132). Additional support was provided by internal funding from the Huntsman Cancer Institute. The authors are grateful for the support of NVIDIA Corporation by providing the GPU used for this research.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Foote, M.D., Zimmerman, B.E., Sawant, A., Joshi, S.C. (2019). Real-Time 2D-3D Deformable Registration with Deep Learning and Application to Lung Radiotherapy Targeting. In: Chung, A., Gee, J., Yushkevich, P., Bao, S. (eds) Information Processing in Medical Imaging. IPMI 2019. Lecture Notes in Computer Science(), vol 11492. Springer, Cham. https://doi.org/10.1007/978-3-030-20351-1_20
Download citation
DOI: https://doi.org/10.1007/978-3-030-20351-1_20
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-20350-4
Online ISBN: 978-3-030-20351-1
eBook Packages: Computer ScienceComputer Science (R0)