Development of an Unsupervised Cycle Contrastive Unpaired Translation Network for MRI-to-CT Synthesis

Overview

Journal J Appl Clin Med Phys

Specialties Biophysics
General Medicine

Date 2022 Sep 28

PMID 36168935

Authors

Jiangtao Wang

Bing Yan

Xinhong Wu

Xiao Jiang

Yang Zuo

Yidong Yang

Affiliations

Soon will be listed here.

Abstract

Purpose: The purpose of this work is to develop and evaluate a novel cycle-contrastive unpaired translation network (cycleCUT) for synthetic computed tomography (sCT) generation from T1-weighted magnetic resonance images (MRI).

Methods: The cycleCUT proposed in this work integrated the contrastive learning module from contrastive unpaired translation network (CUT) into the cycle-consistent generative adversarial network (cycleGAN) framework to effectively achieve unsupervised CT synthesis from MRI. The diagnostic MRI and radiotherapy planning CT images of 24 brain cancer patients were obtained and reshuffled to train the network. For comparison, the traditional cycleGAN and CUT were also implemented. The sCT images were then imported into a treatment planning system to verify their feasibility for radiotherapy planning. The mean absolute error (MAE), peak signal-to-noise ratio (PSNR), and structural similarity index (SSIM) between the sCT and the corresponding real CT images were calculated. Gamma analysis between sCT- and CT-based dose distributions was also conducted.

Results: Quantitative evaluation of an independent test set of six patients showed that the average MAE was 69.62 ± 5.68 Hounsfield Units (HU) for the proposed cycleCUT, significantly (p-value < 0.05) lower than that for cycleGAN (77.02 ± 6.00 HU) and CUT (78.05 ± 8.29). The average PSNR was 28.73 ± 0.46 decibels (dB) for cycleCUT, significantly larger than that for cycleGAN (27.96 ± 0.49 dB) and CUT (27.95 ± 0.69 dB). The average SSIM for cycleCUT (0.918 ± 0.012) was also significantly higher than that for cycleGAN (0.906 ± 0.012) and CUT (0.903 ± 0.015). Regarding gamma analysis, cycleCUT achieved the highest passing rate (97.95 ± 1.24% at the 2%/2 mm criteria and 10% dose threshold) but was not significantly different from the others.

Conclusion: The proposed cycleCUT could be effectively trained using unaligned image data, and could generate better sCT images than cycleGAN and CUT in terms of HU number accuracy and fine structural details.

Citing Articles

Synthetic polarization-sensitive optical coherence tomography using contrastive unpaired translation.

Le T, Lee Y, Park E, Kim M, Eom T, Lee C Sci Rep. 2024; 14(1):31366.

PMID: 39733058 PMC: 11682212. DOI: 10.1038/s41598-024-82839-0.

Proton dose calculation on cone-beam computed tomography using unsupervised 3D deep learning networks.

Dueholm Vestergaard C, Vindelev Elstrom U, Paul Muren L, Ren J, Norrevang O, Jensen K Phys Imaging Radiat Oncol. 2024; 32:100658.

PMID: 39534276 PMC: 11554915. DOI: 10.1016/j.phro.2024.100658.

CT synthesis with deep learning for MR-only radiotherapy planning: a review.

Roh J, Ryu D, Lee J Biomed Eng Lett. 2024; 14(6):1259-1278.

PMID: 39465111 PMC: 11502731. DOI: 10.1007/s13534-024-00430-y.

Channel-wise attention enhanced and structural similarity constrained cycleGAN for effective synthetic CT generation from head and neck MRI images.

Gong C, Huang Y, Luo M, Cao S, Gong X, Ding S Radiat Oncol. 2024; 19(1):37.

PMID: 38486193 PMC: 10938692. DOI: 10.1186/s13014-024-02429-2.

Machine Learning for Medical Image Translation: A Systematic Review.

McNaughton J, Fernandez J, Holdsworth S, Chong B, Shim V, Wang A Bioengineering (Basel). 2023; 10(9).

PMID: 37760180 PMC: 10525905. DOI: 10.3390/bioengineering10091078.

References

Xiang L, Wang Q, Nie D, Zhang L, Jin X, Qiao Y . Deep embedding convolutional neural network for synthesizing CT image from T1-Weighted MR image. Med Image Anal. 2018; 47:31-44. PMC: 6410565. DOI: 10.1016/j.media.2018.03.011. View

Uh J, Merchant T, Li Y, Li X, Hua C . MRI-based treatment planning with pseudo CT generated through atlas registration. Med Phys. 2014; 41(5):051711. PMC: 5148041. DOI: 10.1118/1.4873315. View

Nyul L, Udupa J, Zhang X . New variants of a method of MRI scale standardization. IEEE Trans Med Imaging. 2000; 19(2):143-50. DOI: 10.1109/42.836373. View

Hsu S, Cao Y, Huang K, Feng M, Balter J . Investigation of a method for generating synthetic CT models from MRI scans of the head and neck for radiation therapy. Phys Med Biol. 2013; 58(23):8419-35. PMC: 3886820. DOI: 10.1088/0031-9155/58/23/8419. View

Brou Boni K, Klein J, Gulyban A, Reynaert N, Pasquier D . Improving generalization in MR-to-CT synthesis in radiotherapy by using an augmented cycle generative adversarial network with unpaired data. Med Phys. 2021; 48(6):3003-3010. DOI: 10.1002/mp.14866. View

Han X . MR-based synthetic CT generation using a deep convolutional neural network method. Med Phys. 2017; 44(4):1408-1419. DOI: 10.1002/mp.12155. View

Lei Y, Harms J, Wang T, Liu Y, Shu H, Jani A . MRI-only based synthetic CT generation using dense cycle consistent generative adversarial networks. Med Phys. 2019; 46(8):3565-3581. PMC: 6692192. DOI: 10.1002/mp.13617. View

Largent A, Barateau A, Nunes J, Mylona E, Castelli J, Lafond C . Comparison of Deep Learning-Based and Patch-Based Methods for Pseudo-CT Generation in MRI-Based Prostate Dose Planning. Int J Radiat Oncol Biol Phys. 2019; 105(5):1137-1150. DOI: 10.1016/j.ijrobp.2019.08.049. View

Spadea M, Pileggi G, Zaffino P, Salome P, Catana C, Izquierdo-Garcia D . Deep Convolution Neural Network (DCNN) Multiplane Approach to Synthetic CT Generation From MR images-Application in Brain Proton Therapy. Int J Radiat Oncol Biol Phys. 2019; 105(3):495-503. DOI: 10.1016/j.ijrobp.2019.06.2535. View

10.

Kazemifar S, McGuire S, Timmerman R, Wardak Z, Nguyen D, Park Y . MRI-only brain radiotherapy: Assessing the dosimetric accuracy of synthetic CT images generated using a deep learning approach. Radiother Oncol. 2019; 136:56-63. DOI: 10.1016/j.radonc.2019.03.026. View

11.

van der Meer D, Karim-Kos H, van der Mark M, Aben K, Bijlsma R, Rijneveld A . Incidence, Survival, and Mortality Trends of Cancers Diagnosed in Adolescents and Young Adults (15-39 Years): A Population-Based Study in The Netherlands 1990-2016. Cancers (Basel). 2020; 12(11). PMC: 7698904. DOI: 10.3390/cancers12113421. View

12.

Demol B, Boydev C, Korhonen J, Reynaert N . Dosimetric characterization of MRI-only treatment planning for brain tumors in atlas-based pseudo-CT images generated from standard T1-weighted MR images. Med Phys. 2016; 43(12):6557. DOI: 10.1118/1.4967480. View

13.

Singh H, Koomson A, Decker K, Park J, Demers A . Continued increasing incidence of malignant appendiceal tumors in Canada and the United States: A population-based study. Cancer. 2020; 126(10):2206-2216. DOI: 10.1002/cncr.32793. View

14.

Ulin K, Urie M, Cherlow J . Results of a multi-institutional benchmark test for cranial CT/MR image registration. Int J Radiat Oncol Biol Phys. 2010; 77(5):1584-9. PMC: 2906611. DOI: 10.1016/j.ijrobp.2009.10.017. View

15.

Lee Y, Bollet M, Charles-Edwards G, Flower M, Leach M, McNair H . Radiotherapy treatment planning of prostate cancer using magnetic resonance imaging alone. Radiother Oncol. 2003; 66(2):203-16. DOI: 10.1016/s0167-8140(02)00440-1. View

16.

Qi M, Li Y, Wu A, Jia Q, Li B, Sun W . Multi-sequence MR image-based synthetic CT generation using a generative adversarial network for head and neck MRI-only radiotherapy. Med Phys. 2020; 47(4):1880-1894. DOI: 10.1002/mp.14075. View

17.

Peng Y, Chen S, Qin A, Chen M, Gao X, Liu Y . Magnetic resonance-based synthetic computed tomography images generated using generative adversarial networks for nasopharyngeal carcinoma radiotherapy treatment planning. Radiother Oncol. 2020; 150:217-224. DOI: 10.1016/j.radonc.2020.06.049. View

18.

Liu Y, Lei Y, Wang Y, Shafai-Erfani G, Wang T, Tian S . Evaluation of a deep learning-based pelvic synthetic CT generation technique for MRI-based prostate proton treatment planning. Phys Med Biol. 2019; 64(20):205022. PMC: 7765705. DOI: 10.1088/1361-6560/ab41af. View

19.

Tustison N, Avants B, Cook P, Zheng Y, Egan A, Yushkevich P . N4ITK: improved N3 bias correction. IEEE Trans Med Imaging. 2010; 29(6):1310-20. PMC: 3071855. DOI: 10.1109/TMI.2010.2046908. View

20.

Tie X, Lam S, Zhang Y, Lee K, Au K, Cai J . Pseudo-CT generation from multi-parametric MRI using a novel multi-channel multi-path conditional generative adversarial network for nasopharyngeal carcinoma patients. Med Phys. 2020; 47(4):1750-1762. DOI: 10.1002/mp.14062. View