Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2022 Apr 7;17(1):69.
doi: 10.1186/s13014-022-02042-1.

A cycle generative adversarial network for improving the quality of four-dimensional cone-beam computed tomography images

Keisuke Usui  1 , Koichi Ogawa  2 , Masami Goto  3 , Yasuaki Sakano  3 , Shinsuke Kyougoku  3 , Hiroyuki Daida  3
Affiliations

A cycle generative adversarial network for improving the quality of four-dimensional cone-beam computed tomography images

Keisuke Usui et al. Radiat Oncol. .

Abstract

Background: Four-dimensional cone-beam computed tomography (4D-CBCT) can visualize moving tumors, thus adaptive radiation therapy (ART) could be improved if 4D-CBCT were used. However, 4D-CBCT images suffer from severe imaging artifacts. The aim of this study is to investigate the use of synthetic 4D-CBCT (sCT) images created by a cycle generative adversarial network (CycleGAN) for ART for lung cancer.

Methods: Unpaired thoracic 4D-CBCT images and four-dimensional multislice computed tomography (4D-MSCT) images of 20 lung-cancer patients were used for training. High-quality sCT lung images generated by the CycleGAN model were tested on another 10 cases. The mean and mean absolute errors were calculated to assess changes in the computed tomography number. The structural similarity index measure (SSIM) and peak signal-to-noise ratio (PSNR) were used to compare the sCT and original 4D-CBCT images. Moreover, a volumetric modulation arc therapy plan with a dose of 48 Gy in four fractions was recalculated using the sCT images and compared with ideal dose distributions observed in 4D-MSCT images.

Results: The generated sCT images had fewer artifacts, and lung tumor regions were clearly observed in the sCT images. The mean and mean absolute errors were near 0 Hounsfield units in all organ regions. The SSIM and PSNR results were significantly improved in the sCT images by approximately 51% and 18%, respectively. Moreover, the results of gamma analysis were significantly improved; the pass rate reached over 90% in the doses recalculated using the sCT images. Moreover, each organ dose index of the sCT images agreed well with those of the 4D-MSCT images and were within approximately 5%.

Conclusions: The proposed CycleGAN enhances the quality of 4D-CBCT images, making them comparable to 4D-MSCT images. Thus, clinical implementation of sCT-based ART for lung cancer is feasible.

Keywords: 4D-CBCT; ART; CycleGAN; Image quality correction; Lung cancer.

PubMed Disclaimer

Conflict of interest statement

We have no financial relationships to disclose.

Figures

Fig. 1
Fig. 1
Cycle generative adversarial network (CycleGAN) framework (a), and network structure of the generator (b) and discriminator (c). The training model consists of two generators and two discriminators. To train the CycleGAN, the overall network’s performance is enhanced through networks acting bidirectionally with each other. The sCT image is generated by a network that maps images from a source domain (4D-CBCT) to the target domain (4D-MSCT)
Fig. 2
Fig. 2
Creation of the virtual image quality deterioration image and deformation image. a The sparse projection data were acquired every 4° in a 360° direction. Image noise was added by applying convolution of 4D-CBCT-specific modulation transfer function. b The structural deformation was performed toward maximum exhalation to maximum intake images using the deformable image registration technique
Fig. 3
Fig. 3
Results of the image quality test (a) and image deformation test (b). All images are shown with the same window width and levels. a-1 Degraded 4D-MSCT image, a-2 generated image, and a-3 original 4D-MSCT image. b-1 Original 4D-CBCT image in maximum exhalation, b-2 generated image, and b-3 4D-CBCT image in maximum intake
Fig. 4
Fig. 4
a 4D-MSCT, b 4D-CBCT, and c synthetic 4D-CBCT (sCT) images of the same patients in the corresponding axial, coronal, and sagittal directions. All images are shown with the same window width and levels. d Two-dimensional histograms of the axial direction in each image. The height of each histogram represents the count for the CT number
Fig. 5
Fig. 5
Dose distributions in a volumetric modulation arc therapy (VMAT) plan based on a 4D-MSCT, b 4D-CBCT and c sCT images. Moreover, the dose difference image from the dose distribution of 4D-MSCT image, d 4D-MSCT minus 4D-CBCT, e 4D-MSCT minus sCT
Fig. 6
Fig. 6
Relative differences in each organ dose index obtained using the 4D-MSCT, 4D-CBCT, and sCT images in VMAT-SBRT planning. All doses correspond to the reference dose on the 4D-MSCT image. * indicates significance at p < 0.01
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

References

    1. Shultz DB, Diehn M, Loo BW., Jr To SABR or not to SABR? Indications and contraindications for stereotactic ablative radiotherapy in the treatment of early-stage, oligometastatic, or oligoprogressive non-small cell lung cancer. Semin Radiat Oncol. 2015;25:78–86. doi: 10.1016/j.semradonc.2014.11.005. - DOI - PubMed
    1. Hong TS, Tomé WA, Chappell RJ, Chinnaiyan P, Mehta MP, Harari PM. The impact of daily setup variations on head-and-neck intensity modulated radiation therapy. Int J Radiat Oncol. 2005;61:779–788. doi: 10.1016/j.ijrobp.2004.07.696. - DOI - PubMed
    1. Barney BM, Lee RJ, Handrahan D, Welsh KT, Cook JT, Sause WT. Image-guided radiotherapy (IGRT) for prostate cancer comparing KV imaging of fiduciary markers with cone beam computed tomography (CBCT) Int J Radiat Oncol. 2011;80:301–305. doi: 10.1016/j.ijrobp.2010.06.007. - DOI - PubMed
    1. Purdie TG, Moseley DJ, Bissonnette J, et al. Respiration correlated cone-beam computed tomography and 4DCT for evaluating target motion in stereotactic lung radiation therapy. Acta Oncol. 2006;45:915–922. doi: 10.1080/02841860600907345. - DOI - PubMed
    1. Qin A, Sun Y, Liang J, et al. Evaluation of online/offline image guidance/adaptation approaches for prostate cancer radiation therapy. Int J Radiat Oncol. 2015;91:1026–1033. doi: 10.1016/j.ijrobp.2014.12.043. - DOI - PubMed

MeSH terms