Deep Learning–Based CT-to-CBCT Deformable Image Registration for Autosegmentation in Head and Neck Adaptive Radiation Therapy

Authors

  • Xiao Liang Medical Artificial Intelligence and Automation Laboratory and Department of Radiation Oncology, University of Texas Southwestern Medical Center, Dallas, TX, USA https://orcid.org/0000-0002-2472-2396
  • Howard Morgan Medical Artificial Intelligence and Automation Laboratory and Department of Radiation Oncology, University of Texas Southwestern Medical Center, Dallas, TX, USA https://orcid.org/0000-0002-8572-9292
  • Dan Nguyen Medical Artificial Intelligence and Automation Laboratory and Department of Radiation Oncology, University of Texas Southwestern Medical Center, Dallas, TX, USA
  • Steve Jiang Medical Artificial Intelligence and Automation Laboratory and Department of Radiation Oncology, University of Texas Southwestern Medical Center, Dallas, TX, USA

DOI:

https://doi.org/10.2991/jaims.d.210527.001

Keywords:

Deep learning, Deformable image registration, Segmentation, CBCT

Abstract

The purpose of this study is to develop a deep learning–based method that can automatically generate segmentations on cone-beam computed tomography (CBCT) for head and neck online adaptive radiation therapy (ART), where expert-drawn contours in planning CT (pCT) images serve as prior knowledge. Because of the many artifacts and truncations that characterize CBCT, we propose to utilize a learning-based deformable image registration method and contour propagation to get updated contours on CBCT. Our method takes CBCT and pCT as inputs, and it outputs a deformation vector field and synthetic CT (sCT) simultaneously by jointly training a CycleGAN model and 5-cascaded Voxelmorph model. The CycleGAN generates the sCT from CBCT, while the 5-cascaded Voxelmorph warps the pCT to the sCT's anatomy. We compared the segmentation results to Elastix, Voxelmorph and 5-cascaded Voxelmorph models on 18 structures including target and organs-at-risk. Our proposed method achieved an average Dice similarity coefficient of 0.83 ± 0.09 and an average 95% Hausdorff distance of 2.01 ± 1.81 mm. Our method showed better accuracy than Voxelmorph and 5-cascaded Voxelmorph and comparable accuracy to Elastix, but with much higher efficiency. The proposed method can rapidly and simultaneously generate sCT with correct CT numbers and propagate contours from pCT to CBCT for online ART replanning.

References

Q. Wu, T. Li, Q. Wu, F. Yin, Adaptive radiation therapy: technical components and clinical applications, Cancer J. 17 (2011), 182–189.

Y. Archambault, C. Boylan, D. Bullock, T. Morgas, J. Peltola, E. Ruokokoski, A. Genghi, B. Haas, P. Suhonen, S. Thompson, Making on-line adaptive radiotherapy possible using artificial intelligence and machine learning for efficient daily re-planning, Med. Phys. 8 (2020), 77–86. http://mpijournal.org/pdf/2020-02/MPI- 2020-02-p077.pdf

S. Klüter, [I091]C linical deployment of the mridian linac, Phys. Medica Eur. J. Med. Phys. 52 (2018), 36.

D. Winkel, G.H. Bol, P.S. Kroon, V.A. Bram, S.S. Hackett, A.M. Werensteijn-Honingh, et al., Adaptive radiotherapy: the Elekta Unity MR-linac concept, Clin. Transl. Radiat. Oncol. 18 (2019), 54–59.

D.L. Schwartz, A.S. Garden, S.J. Shah, G. Chronowski, S. Sejpal, D.I. Rosenthal, et al., Adaptive radiotherapy for head and neck cancer—dosimetric results from a prospective clinical trial, Radiother. Oncol. 106 (2013), 80–84.

Nill, P.E. Huber, R. Bendl, J. Debus, M.W. Münter, A clinical concept for interfractional adaptive radiation therapy in the treatment of head and neck cancer, Int. J. Radiat. Oncol. Biol. Phys. 82 (2012), 590–596.

X. Liang, L. Chen, D. Nguyen, Z. Zhou, X. Gu, M. Yang, J. Wang, S. Jiang, Generating synthesized Computed Tomography (CT) from Cone-Beam Computed Tomography (CBCT) using CycleGAN for adaptive radiation therapy, Phy. Med. Biol. 64 (2019), 125002.

Y. Liu, Y. Lei, Y. Fu, T. Wang, J. Zhou, X. Jiang, et al., Head and neck multi-organ auto-segmentation on CT images aided by synthetic MRI, Med. Phys. 47 (2020), 4294–4302.

X. Li, Y. Zhang, Y. Shi, S. Wu, Y. Xiao, X. Gu, X. Zhen, L. Zhou, Comprehensive evaluation of ten deformable image registration algorithms for contour propagation between CT and cone-beam CT images in adaptive head & neck radiotherapy, PLOS ONE. 12 (2017), e0175906.

C. Kurz, F. Kamp, Y.-K. Park, C. Zöllner, S. Rit, D. Hansen, et al., Investigating deformable image registration and scatter correction for CBCT-based dose calculation in adaptive IMPT, Med. Phys. 43 (2016), 5635–5646.

D. Yang, S. Brame, I. El Naqa, A. Aditya, Y. Wu, S.M. Goddu, S. Mutic, J.O. Deasy, D.A. Low, Technical note: DIRART – a software suite for deformable image registration and adaptive radiotherapy research, Med. Phys. 38 (2011), 67–77.

D. Yang, H. Li, D.A. Low, J.O. Deasy, I.E. Naqa, A fast inverse consistent deformable image registration method based on symmetric optical flow computation, Phys. Med. Biol. 53 (2008), 6143–6165.

R. Szeliski, J. Coughlan, Spline-based image registration, Int. J. Comput. Vis. 22 (1997), 199–218.

T. Vercauteren, X. Pennec, A. Perchant, N. Ayache, Diffeomorphic demons: efficient non-parametric image registration, NeuroImage. 45 (2009), S61–S72.

B.B. Avants, N.J. Tustison, G. Song, P.A. Cook, A. Klein, J.C. Gee, A reproducible evaluation of ANTs similarity metric performance in brain image registration, NeuroImage. 54 (2011), 2033–2044.

Y. Fu, Y. Lei, T. Wang, W.J. Curran, T. Liu, X. Yang, Deep learning in medical image registration: a review, Phys. Med. Biol. 65 (2020), 20TR01.

M. Jaderberg, K. Simonyan, A. Zisserman, K. Kavukcuoglu, Spatial transformer networks, 2015. https://arxiv.org/abs/1506.0 2025.

A.V. Dalca, G. Balakrishnan, J. Guttag, M.R. Sabuncu, Unsupervised learning of probabilistic diffeomorphic registration for images and surfaces, Med. Image Anal. 57 (2019), 226–236.

D. Kuang, T. Schmah, FAIM – a ConvNet method for unsupervised 3D medical image registration, in: H.-I. Suk, M. Liu, P. Yan, C. Lian (Eds.), Machine Learning in Medical Imaging, Springer International Publishing, Cham, Switzerland, 2019, pp. 646–654.

S. Zhao, T. Lau, J. Luo, E. Chang, Y. Xu, Unsupervised 3D end-toend medical image registration with volume tweening network, IEEE J. Biomed. Health Inf. 24 (2020), 1394–1404.

R.Y. Wu, A.Y. Liu, T.D. Williamson, J. Yang, P.G. Wisdom, X.R. Zhu, S.J. Frank, C.D. Fuller, G.B. Gunn, S. Gao, Quantifying the accuracy of deformable image registration for cone-beam computed tomography with a physical phantom, J. Appl. Clin. Med. Phys. 20 (2019), 92–100.

S. Zhao, Y. Dong, E.I. Chang, Y. Xu, Recursive cascaded networks for unsupervised medical image registration, in Proceedings of the IEEE/CVF International Conference on Computer Vision, Seoul, South Korea, 2019, pp. 10600–10610.

S. Klein, M. Staring, K. Murphy, M.A. Viergever, J.P.W. Pluim, Elastix: a toolbox for intensity-based medical image registration, IEEE Trans. Med. Imaging. 29 (2010), 196–205.

X. Liang, D. Nguyen, S. Jiang, Generalizability issues with deep learning models in medicine and their potential solutions: illustrated with Cone-Beam Computed Tomography (CBCT) to Computed Tomography (CT) image conversion, Mach. Learn. Sci. Technol. 2 (2020), 015007.

W. Wu, D. Hu, S. Wang, H. Yu, V. Vardhanabhuti, G. Wang, Stabilizing deep tomographic reconstruction networks, 2020. https:/ /arxiv.org/abs/2008.01846.

Published

2021-05-05

How to Cite

1.
Liang X, Morgan H, Nguyen D, Jiang S. Deep Learning–Based CT-to-CBCT Deformable Image Registration for Autosegmentation in Head and Neck Adaptive Radiation Therapy. JAIMS [Internet]. 2021 May 5 [cited 2023 Feb. 4];2(1-2):62-75. Available from: http://oapublishing-jaims.com/jaims/article/view/66