Background and purpose: To investigate the feasibility of synthesizing computed tomography (CT) images from magnetic resonance (MR) images using generative adversarial networks (GANs) for nasopharyngeal carcinoma (NPC) intensity-modulated radiotherapy (IMRT) planning. Materials and methods: Conventional T1-weighted MR images and CT images were acquired from 173 NPC patients. The MR and CT images of 28 patients were randomly chosen as the independent tested set. The remaining images were used to build a conditional GAN (cGAN) and a cycle-consistency GAN (cycleGAN). A U-net was used as the generator in cGAN, whereas a residual-Unet was used as the generator in cycleGAN. The cGAN was trained using the deformable registered MR-CT image pairs, whereas the cycleGAN was trained using the unregistered MR and CT images. The generated synthetic CT (SCT) images from cGAN and cycleGAN were compared with the true CT images with respect to their Hounsfield Unit (HU) discrepancy and dosimetric accuracy for NPC IMRT plans. Results: The mean absolute errors within the body were 69.67 ± 9.27 HU and 100.62 ± 7.39 HU for the cGAN and cycleGAN, respectively. The 2%/2-mm c passing rates were (98.68 ± 0.94)% and (98.52 ± 1.13)% for the cGAN and cycleGAN, respectively. Meanwhile, the absolute dose discrepancies within the regions of interest were (0.49 ± 0.24)% and (0.62 ± 0.36)%, respectively. Conclusion: Both cGAN and cycleGAN could swiftly generate accurate SCT volume images from MR images, with high dosimetric accuracy for NPC IMRT planning. cGAN was preferable if high-quality MR-CT image pairs were available.

No abstract

Purpose Clinical implementation of magnetic resonance imaging (MRI)‐only radiotherapy requires a method to derive synthetic CT image (S‐CT) for dose calculation. This study investigated the feasibility of building a deep convolutional neural network for MRI‐based S‐CT generation and evaluated the dosimetric accuracy on prostate IMRT planning. Methods A paired CT and T2‐weighted MR images were acquired from each of 51 prostate cancer patients. Fifteen pairs were randomly chosen as tested set and the remaining 36 pairs as training set. The training subjects were augmented by applying artificial deformations and feed to a two‐dimensional U‐net which contains 23 convolutional layers and 25.29 million trainable parameters. The U‐net represents a nonlinear function with input an MR slice and output the corresponding S‐CT slice. The mean absolute error (MAE) of Hounsfield unit (HU) between the true CT and S‐CT images was used to evaluate the HU estimation accuracy. IMRT plans with dose 79.2 Gy prescribed to the PTV were applied using the true CT images. The true CT images then were replaced by the S‐CT images and the dose matrices were recalculated on the same plan and compared to the one obtained from the true CT using gamma index analysis and absolute point dose discrepancy. Results The U‐net was trained from scratch in 58.67 h using a GP100‐GPU. The computation time for generating a new S‐CT volume image was 3.84–7.65 s. Within body, the (mean ± SD) of MAE was (29.96 ± 4.87) HU. The 1%/1 mm and 2%/2 mm gamma pass rates were over 98.03% and 99.36% respectively. The DVH parameters discrepancy was less than 0.87% and the maximum point dose discrepancy within PTV was less than 1.01% respect to the prescription. Conclusion The U‐net can generate S‐CT images from conventional MR image within seconds with high dosimetric accuracy for prostate IMRT plan.

No abstract