Synthetic CT generation based on CBCT using respath-cycleGAN

Cone-beam computed tomography (CBCT) plays an important role in radiotherapy, but the presence of a large number of artifacts limits its application. The purpose of this study was to use respath-cycleGAN to synthesize CT (sCT) similar to planning CT (pCT) from CBCT for future clinical practice.

The method integrates the respath concept into the original cycleGAN, called respath-cycleGAN, to map CBCT to pCT. Thirty patients were used for training and 15 for testing.

The mean absolute error (MAE), root mean square error (RMSE), peak signal to noise ratio (PSNR), structural similarity index (SSIM), and spatial nonuniformity (SNU) were calculated to assess the quality of sCT generated from CBCT. Compared with CBCT images, the MAE improved from 197.72 to 140.7, RMSE from 339.17 to 266.51, and PSNR from 22.07 to 24.44, while SSIM increased from 0.948 to 0.964. Both visually and quantitatively, sCT with respath is superior to sCT without respath. We also performed a generalization test of the head-and-neck (H&N) model on a pelvic data set. The results again showed that our model was superior.

We developed a respath-cycleGAN method to synthesize CT with good quality from CBCT. In future clinical practice, this method may be used to develop radiotherapy plans.