[an error occurred while processing this directive] | [an error occurred while processing this directive]
A deep learning method for generating pseudo-CT by cone beam CT in radiotherapy
Liu Yuxiang1, Yang Bining2, Wei Ran2, Liu Yueping2, Chen Xinyuan2, Xiong Rui1, Men Kuo2, Quan Hong1, Dai Jianrong2
1School of Physics and Technology, Wuhan University, Wuhan 430072, China; 2Department of Radiation Oncology, National Cancer Center / National Clinical Research Center for Cancer / Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing 100021, China
AbstractObjective To investigate the pseudo-CT generation from cone beam CT (CBCT) by a deep learning method for the clinical need of adaptive radiotherapy. Methods CBCT data from 74 prostate cancer patients collected by Varian On-Board Imager and their simulated positioning CT images were used for this study. The deformable registration was implemented by MIM software. And the data were randomly divided into the training set (n=59) and test set (n=15). U-net, Pix2PixGAN and CycleGAN were employed to learn the mapping from CBCT to simulated positioning CT. The evaluation indexes included mean absolute error (MAE), structural similarity index (SSIM) and peak signal to noise ratio (PSNR), with the deformed CT chosen as the reference. In addition, the quality of image was analyzed separately, including soft tissue resolution, image noise and artifacts, etc. Results The MAE of images generated by U-net, Pix2PixGAN and CycleGAN were (29.4±16.1) HU, (37.1±14.4) HU and (34.3±17.3) HU, respectively. In terms of image quality, the images generated by U-net and Pix2PixGAN had excessive blur, resulting in image distortion; while the images generated by CycleGAN retained the CBCT image structure and improved the image quality. Conclusion CycleGAN is able to effectively improve the quality of CBCT images, and has potential to be used in adaptive radiotherapy.
Fund:National Natural Science Foundation of China (11975313, 12175312); Beijing Nova Program (Z201100006820058)
Corresponding Authors:
Men Kuo, Email: menkuo@cicams.ac.cn; Xiong Rui, Email: xiongrui@whu.edu.cn
Cite this article:
Liu Yuxiang,Yang Bining,Wei Ran et al. A deep learning method for generating pseudo-CT by cone beam CT in radiotherapy[J]. Chinese Journal of Radiation Oncology, 2023, 32(1): 42-47.
Liu Yuxiang,Yang Bining,Wei Ran et al. A deep learning method for generating pseudo-CT by cone beam CT in radiotherapy[J]. Chinese Journal of Radiation Oncology, 2023, 32(1): 42-47.
[1] Yan D, Vicini F, Wong J, et al.Adaptive radiation therapy[J]. Phys Med Biol, 1997,42(1):123-132. DOI: 10.1088/0031-9155/42/1/008. [2] Albertini F, Matter M, Nenoff L, et al.Online daily adaptive proton therapy[J]. Br J Radiol, 2020,93(1107):20190594. DOI: 10.1259/bjr.20190594. [3] Acharya S, Fischer-Valuck BW, Kashani R, et al.Online magnetic resonance image guided adaptive radiation therapy: first clinical applications[J]. Int J Radiat Oncol Biol Phys, 2016,94(2):394-403. DOI: 10.1016/j.ijrobp.2015.10.015. [4] Wang J, Li T, Xing L.Iterative image reconstruction for CBCT using edge-preserving prior[J]. Med Phys, 2009,36(1):252-260. DOI: 10.1118/1.3036112. [5] Park YK, Sharp GC, Phillips J, et al.Proton dose calculation on scatter-corrected CBCT image: feasibility study for adaptive proton therapy[J]. Med Phys, 2015,42(8):4449-4459. DOI: 10.1118/1.4923179. [6] Nomura Y, Xu Q, Shirato H, et al.Projection-domain scatter correction for cone beam computed tomography using a residual convolutional neural network[J]. Med Phys, 2019,46(7):3142-3155. DOI: 10.1002/mp.13583. [7] Jiang Y, Yang C, Yang P, et al.Scatter correction of cone-beam CT using a deep residual convolution neural network (DRCNN)[J]. Phys Med Biol, 2019,64(14):145003. DOI: 10.1088/1361-6560/ab23a6. [8] Hansen DC, Landry G, Kamp F, et al.ScatterNet: a convolutional neural network for cone-beam CT intensity correction[J]. Med Phys, 2018,45(11):4916-4926. DOI: 10.1002/mp.13175. [9] Lalonde A, Winey B, Verburg J, et al.Evaluation of CBCT scatter correction using deep convolutional neural networks for head and neck adaptive proton therapy[J]. Phys Med Biol, 2020,65(24):10. DOI: 10.1088/1361-6560/ab9fcb. [10] Liu Y, Lei Y, Wang T, et al.CBCT-based synthetic CT generation using deep-attention cycleGAN for pancreatic adaptive radiotherapy[J]. Med Phys, 2020,47(6):2472-2483. DOI: 10.1002/mp.14121. [11] Landry G, Hansen D, Kamp F, et al.Comparing Unet training with three different datasets to correct CBCT images for prostate radiotherapy dose calculations[J]. Phys Med Biol, 2019,64(3):035011. DOI: 10.1088/1361-6560/aaf496. [12] Barateau A, De Crevoisier R, Largent A, et al.Comparison of CBCT-based dose calculation methods in head and neck cancer radiotherapy: from Hounsfield unit to density calibration curve to deep learning[J]. Med Phys, 2020,47(10):4683-4693. DOI: 10.1002/mp.14387. [13] Zhang Y, Yue N, Su MY, et al.Improving CBCT quality to CT level using deep learning with generative adversarial network[J]. Med Phys, 2021,48(6):2816-2826. DOI: 10.1002/mp.14624. [14] Harms J, Lei Y, Wang T, et al.Paired cycle-GAN-based image correction for quantitative cone-beam computed tomography[J]. Med Phys, 2019,46(9):3998-4009. DOI: 10.1002/mp.13656. [15] Chen L, Liang X, Shen C, et al.Synthetic CT generation from CBCT images via deep learning[J]. Med Phys, 2020,47(3):1115-1125. DOI: 10.1002/mp.13978. [16] Liang X, Chen L, Nguyen D, et al.Generating synthesized computed tomography (CT) from cone-beam computed tomography (CBCT) using CycleGAN for adaptive radiation therapy[J]. Phys Med Biol, 2019,64(12):125002. DOI: 10.1088/1361-6560/ab22f9. [17] Chen L, Liang X, Shen C, et al.Synthetic CT generation from CBCT images via unsupervised deep learning[J]. Phys Med Biol, 2021,66(11). DOI: 10.1088/1361-6560/ac01b6. [18] Ronneberger O, Fischer P, Brox T.U-net: convolutional networks for biomedical image segmentation[C]. Cham: Springer International Publishing, 2015. [19] Isola P, Zhu JY, Zhou TH, et al.Image-to-image translation with conditional adversarial networks[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu: IEEE, 2017. [20] Zhu JY, Park T, Isola P, et al.Unpaired image-to-image translation using cycle-consistent adversarial networks[C]//2017 IEEE International Conference on Computer Vision (ICCV). Venice: IEEE, 2017.
2023, Vol. 32 
