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

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.

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

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

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

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

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

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