Abstract
Four-dimensional computed tomography (4D-CT) has been used in radiation therapy, which allows for tumor and organ motion tracking through the breathing cycle. Based on the motion trajectory analysis of tumor and normal tissues, an adaptive treatment planning may be improved in terms of the accuracy of tumor delineation, or gating radiation. Image registration can be used to compensate the motion and supply the transformation between different scans in 4D-CT to help further analysis. The motion in the 4D-CT is mainly caused by the respiration, which requires deformable image registration. As the accurate and fast function facilitated by GPU, deep learning based deformable image registration methods are widely used for 4D-CT. In this paper, we apply a deep learning based deformable registration network (Reg-Net) to estimate the deformation field for the given scan pair of 4D-CT. The proposed network was trained in an unsupervised manner without the need of any expert annotation. For evaluation, 10 subjects are used for training, 5 subjects for testing. We use the Dice similarity coefficient (DSC) and intersection over union (IoU) over regions of interest (i.e., gross target volume) to evaluate the registration performance. The experimental results demonstrate that the proposed deformable Reg-Net can potentially improve the organ tracking performance.
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
Brandner, E. D., Wu, A., Chen, H., Heron, D., Kalnicki, S., Komanduri, K., Gerszten, K., Burton, S., Ahmed, I., & Shou, Z. (2006). Abdominal organ motion measured using 4d ct. International Journal of Radiation Oncology* Biology* Physics, 65(2), 554–560.
Tai, A., Liang, Z., Erickson, B., & Allen Li, X. (2013). Management of respiration-induced motion with 4-dimensional computed tomography (4dct) for pancreas irradiation. International Journal of Radiation Oncology Biology Physics, 86(5), 908–913.
D’Souza, Warren D., Nazareth, Daryl P., Zhang, Bin, Deyoung, Chad, Suntharalingam, Mohan, Kwok, Young, et al. (2007). The use of gated and 4d ct imaging in planning for stereotactic body radiation therapy. Medical Dosimetry, 32(2), 92–101.
Keall, Paul. (2004). 4-dimensional computed tomography imaging and treatment planning. Seminars in Radiation Oncology, 14(1), 81–90.
Gupta, V., Wang, Y., Romero, A., Myronenko, A., Jordan, P., Maurer, C., Heijmen, B., & Hoogeman, M. (2018). Fast and robust adaptation of organs-at-risk delineations from planning scans to match daily anatomy in pre-treatment scans for online-adaptive radiotherapy of abdominal tumors. Radiotherapy and Oncology, 127(2), 332–338.
McClelland, J. R., Hawkes, D. J., Schaeffter, T., & King, A. P. (2013). Respiratory motion models: A review. Medical Image Analysis, 17(1), 19–42.
Towards a generic respiratory motion model for 4D CT imaging of the thorax. (2009). IEEE Nuclear Science Symposium Conference Record, 3975–3979.
Harris, Wendy, Wang, Chunhao, Yin, Fang-Fang., Cai, Jing, & Ren, Lei. (2018). A Novel method to generate on-board 4D MRI using prior 4D MRI and on-board kV projections from a conventional LINAC for target localization in liver SBRT. Medical Physics, 45(7), 3238–3245.
Eppenhof, K. A. J., & Pluim, J. P. W. (2019). Pulmonary CT registration through supervised learning with convolutional neural networks. IEEE Transactions on Medical Imaging, 38(5), 1097–1105.
Dalca, Adrian V., Balakrishnan, Guha, Guttag, John V., & Sabuncu, Mert R. (2019). Unsupervised learning of probabilistic diffeomorphic registration for images and surfaces. Medical Image Analysis, 57, 226–236.
Balakrishnan, G., Zhao, A., Sabuncu, M. R., Guttag, J., & Dalca, A. V. (2019). Voxelmorph: A learning framework for deformable medical image registration. IEEE transactions on medical imaging, 38(8), 1788–1800.
Wei, D., Ahmad, S., Huo, J., Peng, W., Ge, Y., Xue, Z., Yap, P. T., Li, W., Shen, D., & Wang, Q. (2019). Synthesis and inpainting-based mr-ct registration for image-guided thermal ablation of liver tumors. In 22nd International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2019, pp. 512–520.
Lei, Y., Fu, Y., Harms, J., Wang, T., Curran, W. J., Liu, T., Higgins, K., & Yang, X. (2019). 4d-ct deformable image registration using an unsupervised deep convolutional neural network. Workshop on Artificial Intelligence in Radiation Therapy, pp. 26–33.
Jaderberg, M., Simonyan, K., Zisserman, A., Kavukcuoglu, K. (2015). Spatial transformer networks. In NIPS’15 Proceedings of the 28th International Conference on Neural Information Processing Systems, pp. 2017–2025.
Rueckert, D., Sonoda, L. I., Hayes, C., Hill, D. L. G., Leach, M. O., & Hawkes, D. J. (1999). Nonrigid registration using free-form deformations: Application to breast MR images. IEEE Transactions on Medical Imaging, 18(8), 712–721.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Wei, D., Yang, W., Paysan, P., Liu, H. (2021). An Unsupervised Learning Based Deformable Registration Network for 4D-CT Images. In: Miller, K., Wittek, A., Nash, M., Nielsen, P.M.F. (eds) Computational Biomechanics for Medicine. Springer, Cham. https://doi.org/10.1007/978-3-030-70123-9_5
Download citation
DOI: https://doi.org/10.1007/978-3-030-70123-9_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-70122-2
Online ISBN: 978-3-030-70123-9
eBook Packages: Physics and AstronomyPhysics and Astronomy (R0)