Abstract
Accurate MR-to-CT synthesis plays an important role in MRI-only radiotherapy treatment planning. In medical image synthesis, the cycle-generative adversarial network (CycleGAN) is becoming an influential method, however, its image quality of synthesis is not optimal yet. In this study, we proposed a new learning method named U-Net-CycleGAN (UC-GAN) to generate synthetic CT (sCT) image for MRI-only radiation treatment planning, which integrated an improved U-Net concept into the original CycleGAN framework. After experimental comparison, The MAE value and PSNR of our UC-GAN model are 76.7 ± 4.5 and 46.1 ± 1.5, respectively, which are statistics significantly better than the 94.0 ± 4.3 (MAE) and 45.1 ± 1.5 (PSNR) of the original CycleGAN model. The results of our quantitative evaluation show that the UC-GAN model can synthesize a CT image closer to the reference real CT image with better performance.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Edmund, J.M., Nyholm, T.: A review of substitute CT generation for MRI-only radiation therapy. Radiat. Oncol. 12(1), 28 (2017)
Huo, Y., et al.: SynSeg-Net: synthetic segmentation without target modality ground truth. IEEE Trans. Med. Imag. 38(4), 1016–1025 (2018)
Dowling, J.A., et al.: An atlas-based electron density mapping method for magnetic resonance imaging (MRI)-alone treatment planning and adaptive MRI-based prostate radiation therapy. Int. J. Radiat. Oncol. Biol. Phys. 83(1), e5–e11 (2012)
Chin, A.L., Lin, A., Anamalayil, S., Teo, B.K.: Feasibility and limitations of bulk density assignment in MRI for head and neck IMRT treatment planning. J. Appl. Clin. Med. Phys. 15(5), 100–111 (2014)
Van Nguyen, V., Zhou, K., Vemulapalli, R.: Cross-domain synthesis of medical images using efficient location-sensitive deep network. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015, Part I. LNCS, vol. 9349, pp. 677–684. Springer, Heidelberg (2015)
Kapanen, M., Tenhunen, M.: T1/T2*-weighted MRI provides clinically relevant pseudo-CT density data for the pelvic bones in MRI-only based radiotherapy treatment planning. Acta Oncol. 52(3), 612–618 (2013)
Johansson, A., Karlsson, M., Nyholm, T.: CT substitute derived from MRI sequences with ultrashort echo time. Med. Phys. 38(5), 2708–2714 (2011)
Zheng, W., Kim, J.P., Kadbi, M., Movsas, B., Chetty, I.J., Glide-Hurst, C.K.: Magnetic resonance-based automatic air segmentation for generation of synthetic computed tomography scans in the head region. Int. J. Radiat. Oncol. Biol. Phys. 93(3), 497–506 (2015)
Sevetlidis, V., Giuffrida, M.V., Tsaftaris, S.A.: Whole image synthesis using a deep encoder-decoder network. In: Tsaftaris, S.A., Gooya, A., Frangi, A.F., Prince, J.L. (eds.) SASHIMI 2016. LNCS, vol. 9968, pp. 127–137. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46630-9_13
Xiang, L., et al.: Deep embedding convolutional neural network for synthesizing CT image from T1-Weighted MR image. Med. Image Anal. 47, 31–44 (2018)
Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, pp. 2672–2680 (2014)
Nie, D., et al.: Medical image synthesis with context-aware generative adversarial networks. In: Descoteaux, M., Maier-Hein, L., Franz, A., Jannin, P., Collins, D.L., Duchesne, S. (eds.) MICCAI 2017. LNCS, vol. 10435, pp. 417–425. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-66179-7_48
Yi, Z., Zhang, H., Tan, P., Gong, M.: DualGAN: unsupervised dual learning for image-to-image translation. In: 2017 IEEE ICCV, pp. 2849–2857. IEEE (2017)
Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: 2017 IEEE ICCV, pp. 2223–2232. IEEE (2017)
Han, X.: MR-based synthetic CT generation using a deep convolutional neural network method. Med. Phys. 44(4), 1408–1419 (2017)
Nie, D., Cao, X., Gao, Y., Wang, L., Shen, D.: Estimating CT image from MRI data using 3D fully convolutional networks. In: Carneiro, G., et al. (eds.) Deep Learning and Data Labeling for Medical Applications, pp. 170–178. Springer, Cham (2016)
Wolterink, J.M., Dinkla, A.M., Savenije, M.H., Seevinck, P.R., van den Berg, C.A.T., Išgum, I.: Deep MR to CT synthesis using unpaired data. In: International Workshop on Simulation and Synthesis in Medical Imaging, pp. 14–23 (2017)
Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28
Jin, C.B., et al.: Deep CT to MR synthesis using paired and unpaired data. Sensors (Basel) 19(10), E2361 (2019)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: International Conference on Learning Representations (ICLR) (2015)
Acknowledgments
This work was supported in part by Shenzhen Key Basic Science Program (JCYJ20170413162213765 and JCYJ20180507182437217), the Shenzhen Key Laboratory Program (ZDSYS201707271637577), the NSFC-Shenzhen Union Program (U1613221), and the National Key Research and Development Program (2017YFC0110903).
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
Wu, H., Jiang, X., Jia, F. (2019). UC-GAN for MR to CT Image Synthesis. In: Nguyen, D., Xing, L., Jiang, S. (eds) Artificial Intelligence in Radiation Therapy. AIRT 2019. Lecture Notes in Computer Science(), vol 11850. Springer, Cham. https://doi.org/10.1007/978-3-030-32486-5_18
Download citation
DOI: https://doi.org/10.1007/978-3-030-32486-5_18
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-32485-8
Online ISBN: 978-3-030-32486-5
eBook Packages: Computer ScienceComputer Science (R0)