Generating synthesized computed tomography from CBCT using  a conditional generative adversarial  network for head and neck  cancer patients

Kerun

et al. 2023

Sci Rep

This study aims to utilize a hybrid approach of phantom correction and deep learning for synthesized CT (sCT) images generation based on cone-beam CT (CBCT) images for nasopharyngeal carcinoma (NPC). 52 CBCT/CT paired images of NPC patients were used for model training (41), validation (11). Hounsfield Units (HU) of the CBCT images was calibrated by a commercially available CIRS phantom. Then the original CBCT and the corrected CBCT (CBCT_cor) were trained separately with the same cycle generative adversarial network (CycleGAN) to generate SCT1 and SCT2. The mean error and mean absolute error (MAE) were used to quantify the image quality. For validations, the contours and treatment plans in CT images were transferred to original CBCT, CBCT_cor, SCT1 and SCT2 for dosimetric comparison. Dose distribution, dosimetric parameters and 3D gamma passing rate were analyzed. Compared with rigidly registered CT (RCT), the MAE of CBCT, CBCT_cor, SCT1 and SCT2 were 346.11 ± 13.58 HU, 145.95 ± 17.64 HU, 105.62 ± 16.08 HU and 83.51 ± 7.71 HU, respectively. Moreover, the average dosimetric parameter differences for the CBCT_cor, SCT1 and SCT2 were 2.7% ± 1.4%, 1.2% ± 1.0% and 0.6% ± 0.6%, respectively. Using the dose distribution of RCT images as reference, the 3D gamma passing rate of the hybrid method was significantly better than the other methods. The effectiveness of CBCT-based sCT generated using CycleGAN with HU correction for adaptive radiotherapy of nasopharyngeal carcinoma was confirmed. The image quality and dose accuracy of SCT2 were outperform the simple CycleGAN method. This finding has great significance for the clinical application of adaptive radiotherapy for NPC.

Section: Discussionsupporting

confidence: 90%

CBCT-based synthetic CT generated using CycleGAN with HU correction for adaptive radiotherapy of nasopharyngeal carcinoma

Kerun

et al. 2023

Sci Rep

“…Moreover, the HU pro le of STC images in different regions, especially SCT2, was closer to that of RCT images. It indicated that HU value of SCT1 and SCT2 images were well corrected to that of RCT images, consistent with previous studies 18,30 . It's worth noting that the MAE of SCT2 was signi cantly less than that of SCT1 (83.51 versus 105.62, P < 0.05), indicating that the training result may be improved by training with corrected CBCT images.…”

supporting

confidence: 91%

CBCT-based synthetic CT generation using a hybrid approach for adaptive radiotherapy of nasopharyngeal carcinoma

Kerun

et al. 2023

Preprint

Objective: This study aims to utilize a hybrid approach of phantom correction and deep learning for synthesized CT (sCT) images generation based on cone-beam CT (CBCT) images for nasopharyngeal carcinoma (NPC). Methods: A total of 52 CBCT/CT paired images of NPC patients were used for training (41), validation (11) datasets. Hounsfield Units (HU) of the CBCT images was corrected by a commercial CIRS phantom. Then the original CBCT and the corrected CBCT (CBCT_cor) were trained separately with the some cycle generative adversarial network (CycleGAN) to generate SCT1 and SCT2. The mean error (ME) and mean absolute error (MAE) were used to quantify the image quality. For the patients in the validation datasets, the contours and treatment plans in CT images were transferred to original CBCT, CBCT_cor, SCT1 and SCT2 for dosimetric comparison. Finally, dose distribution, dosimetric parameters and 3D gamma pass rate were analyzed. Results: Compared with rigidly registered CT (RCT), the MAE of CBCT, CBCT_cor, SCT1 and SCT2 were 346.11 ± 13.58HU, 145.95 ± 17.64HU, 105.62 ± 16.08HU and 83.51 ± 7.71HU, respectively. Moreover, the average dosimetric parameter differences for the CBCT_cor, SCT1 and SCT2 were 2.7% ± 1.4%, 1.2% ± 1.0% and 0.6% ± 0.6%, respectively. Using the dose distribution of RCT images as reference, the 3D gamma pass rate of the hybrid method was significantly better than the other methods. Conclusion: A novel hybrid approach based on HU-ED correction and CycleGAN was developed to generate sCT images for CBCT images of NPC patients. The image quality and dose accuracy of the hybrid approach were outperform the simple CycleGAN method. This finding has great significance for the clinical application of adaptive radiotherapy for NPC.

“…At last, cGAN will be trained for this task. 27 As shown in Figure 1d, cGAN does not require cycle-consistency so will not preserve strong artifact features of CBCT and incorporates CBCT as a conditional input for discriminator to enhance network learning. The generator and discriminator of cGAN are consistent with those of cycleGAN in the second method for subsequent comparison.…”

Section: Deep Learning Methodsmentioning

confidence: 99%

“…At last, cGAN will be trained for this task 27 . As shown in Figure 1d, cGAN does not require cycle‐consistency so will not preserve strong artifact features of CBCT and incorporates CBCT as a conditional input for discriminator to enhance network learning.…”

Section: Methodsmentioning

confidence: 99%

Comparison and evaluation of different deep learning models of synthetic CT generation from CBCT for nasopharynx cancer adaptive proton therapy

Pang,

Si,

Liu

et al. 2023

Medical Physics

BackgroundCone‐beam computed tomography (CBCT) scanning is used for patient setup in image‐guided radiotherapy. However, its inaccurate CT numbers limit its applicability in dose calculation and treatment planning.PurposeThis study compares four deep learning methods for generating synthetic CT (sCT) to determine which method is more appropriate and offers potential for further clinical exploration in adaptive proton therapy for nasopharynx cancer.MethodsCBCTs and deformed planning CT (dCT) from 75 patients (60/5/10 for training, validation and testing) were used to compare cycle‐consistent Generative Adversarial Network (cycleGAN), Unet, Unet+cycleGAN and conditionalGenerative Adversarial Network (cGAN) for sCT generation. The sCT images generated by each method were evaluated against dCT images using mean absolute error (MAE), structural similarity (SSIM), peak signal‐to‐noise ratio (PSNR), spatial non‐uniformity (SNU) and radial averaging in the frequency domain. In addition, dosimetric accuracy was assessed through gamma analysis, differences in water equivalent thickness (WET), and dose‐volume histogram metrics.ResultsThe cGAN model has demonstrated optimal performance in the four models across various indicators. In terms of image quality under global condition, the average MAE has been reduced to 16.39HU, SSIM has increased to 95.24%, and PSNR has increased to 28.98. Regarding dosimetric accuracy, the gamma passing rate (2%/2 mm) has reached 99.02%, and the WET difference is only 1.28 mm. The D95 value of CTVs coverage and Dmax value of spinal cord, brainstem show no significant differences between dCT and sCT generated by cGAN model.ConclusionsThe cGAN model has been shown to be a more suitable approach for generating sCT using CBCT, considering its characteristics and concepts. The resulting sCT has the potential for application in adaptive proton therapy.