Improving reproducibility and performance of radiomics in low-dose CT using cycle GANs.

BACKGROUND: As a means to extract biomarkers from medical imaging, radiomics has attracted increased attention from researchers. However, reproducibility and performance of radiomics in low-dose CT scans are still poor, mostly due to noise. Deep learning generative models can be used to denoise these images and in turn improve radiomics' reproducibility and performance. However, most generative models are trained on paired data, which can be difficult or impossible to collect. PURPOSE: In this article, we investigate the possibility of denoising low-dose CTs using cycle generative adversarial networks (GANs) to improve radiomics reproducibility and performance based on unpaired datasets. METHODS AND MATERIALS: Two cycle GANs were trained: (1) from paired data, by simulating low-dose CTs (i.e., introducing noise) from high-dose CTs and (2) from unpaired real low dose CTs. To accelerate convergence, during GAN training, a slice-paired training strategy was introduced. The trained GANs were applied to three scenarios: (1) improving radiomics reproducibility in simulated low-dose CT images and (2) same-day repeat low dose CTs (RIDER dataset), and (3) improving radiomics performance in survival prediction. Cycle GAN results were compared with a conditional GAN (CGAN) and an encoder-decoder network (EDN) trained on simulated paired data. RESULTS: The cycle GAN trained on simulated data improved concordance correlation coefficients (CCC) of radiomic features from 0.87 (95%CI, [0.833,0.901]) to 0.93 (95%CI, [0.916,0.949]) on simulated noise CT and from 0.89 (95%CI, [0.881,0.914]) to 0.92 (95%CI, [0.908,0.937]) on the RIDER dataset, as well improving the area under the receiver operating characteristic curve (AUC) of survival prediction from 0.52 (95%CI, [0.511,0.538]) to 0.59 (95%CI, [0.578,0.602]). The cycle GAN trained on real data increased the CCCs of features in RIDER to 0.95 (95%CI, [0.933,0.961]) and the AUC of survival prediction to 0.58 (95%CI, [0.576,0.596]). CONCLUSION: The results show that cycle GANs trained on both simulated and real data can improve radiomics' reproducibility and performance in low-dose CT and achieve similar results compared to CGANs and EDNs.

An Automatic Defect Detection System for Petrochemical Pipeline Based on Cycle-GAN and YOLO v5.

Defect detection of petrochemical pipelines is an important task for industrial production safety. At present, pipeline defect detection mainly relies on closed circuit television method (CCTV) to take video of the pipeline inner wall and then detect the defective area manually, so the detection is very time-consuming and has a high rate of false and missed detections. To solve the above issues, we proposed an automatic defect detection system for petrochemical pipeline based on Cycle-GAN and improved YOLO v5. Firstly, in order to create the pipeline defect dataset, the original pipeline videos need pre-processing, which includes frame extraction, unfolding, illumination balancing, and image stitching to create coherent and tiled pipeline inner wall images. Secondly, aiming at the problems of small amount of samples and the imbalance of defect and non-defect classes, a sample enhancement strategy based on Cycle-GAN is proposed to generate defect images and expand the data set. Finally, in order to detect defective areas on the pipeline and improve the detection accuracy, a robust defect detection model based on improved YOLO v5 and Transformer attention mechanism is proposed, with the average precision and recall as 93.10% and 90.96%, and the F1-score as 0.920 on the test set. The proposed system can provide reference for operators in pipeline health inspection, improving the efficiency and accuracy of detection.

A Novel Method for Estimating Monocular Depth Using Cycle GAN and Segmentation.

Modern image processing techniques use three-dimensional (3D) images, which contain spatial information such as depth and scale, in addition to visual information. These images are indispensable in virtual reality, augmented reality (AR), and autonomous driving applications. We propose a novel method to estimate monocular depth using a cycle generative adversarial network (GAN) and segmentation. In this paper, we propose a method for estimating depth information by combining segmentation. It uses three processes: segmentation and depth estimation, adversarial loss calculations, and cycle consistency loss calculations. The cycle consistency loss calculation process evaluates the similarity of two images when they are restored to their original forms after being estimated separately from two adversarial losses. To evaluate the objective reliability of the proposed method, we compared our proposed method with other monocular depth estimation (MDE) methods using the NYU Depth Dataset V2. Our results show that the benchmark value for our proposed method is better than other methods. Therefore, we demonstrated that our proposed method is more efficient in determining depth estimation.

Prediction of prognosis in glioblastoma with radiomics features extracted by synthetic MRI images using cycle-consistent GAN.

To propose a style transfer model for multi-contrast magnetic resonance imaging (MRI) images with a cycle-consistent generative adversarial network (CycleGAN) and evaluate the image quality and prognosis prediction performance for glioblastoma (GBM) patients from the extracted radiomics features. Style transfer models of T1 weighted MRI image (T1w) to T2 weighted MRI image (T2w) and T2w to T1w with CycleGAN were constructed using the BraTS dataset. The style transfer model was validated with the Cancer Genome Atlas Glioblastoma Multiforme (TCGA-GBM) dataset. Moreover, imaging features were extracted from real and synthesized images. These features were transformed to rad-scores by the least absolute shrinkage and selection operator (LASSO)-Cox regression. The prognosis performance was estimated by the Kaplan-Meier method. For the accuracy of the image quality of the real and synthesized MRI images, the MI, RMSE, PSNR, and SSIM were 0.991 ± 2.10 × 10 - 4 , 2.79 ± 0.16, 40.16 ± 0.38, and 0.995 ± 2.11 × 10 - 4 , for T2w, and .992 ± 2.63 × 10 - 4 , 2.49 ± 6.89 × 10 - 2 , 40.51 ± 0.22, and 0.993 ± 3.40 × 10 - 4 for T1w, respectively. The survival time had a significant difference between good and poor prognosis groups for both real and synthesized T2w (p < 0.05). However, the survival time had no significant difference between good and poor prognosis groups for both real and synthesized T1w. On the other hand, there was no significant difference between the real and synthesized T2w in both good and poor prognoses. The results of T1w were similar in the point that there was no significant difference between the real and synthesized T1w. It was found that the synthesized image could be used for prognosis prediction. The proposed prognostic model using CycleGAN could reduce the cost and time of image scanning, leading to a promotion to build the patient's outcome prediction with multi-contrast images.

Anatomy-Constrained Synthesis for Spleen Segmentation Improvement in Unpaired Mouse Micro-CT Scans with 3D CycleGAN.

OBJECTIVE: Auto-segmentation in mouse micro-CT enhances the efficiency and consistency of preclinical experiments but often struggles with low-native-contrast and morphologically complex organs, such as the spleen, resulting in poor segmentation performance. While CT contrast agents can improve organ conspicuity, their use complicates experimental protocols and reduces feasibility. We developed a 3D Cycle Generative Adversarial Network (CycleGAN) incorporating anatomy-constrained U-Net models to leverage contrast-enhanced CT (CECT) insights to improve unenhanced native CT (NACT) segmentation. Approach: We employed a standard CycleGAN with an anatomical loss function to synthesize virtual CECT images from unpaired NACT scans at two different resolutions. Prior to training, two U-Nets were trained to automatically segment six major organs in NACT and CECT datasets, respectively. These pretrained 3D U-Nets were integrated during the CycleGAN training, segmenting synthetic images, and comparing them against ground truth annotations. The compound loss within the CycleGAN maintained anatomical fidelity. Full image processing was achieved for low-resolution datasets, while high-resolution datasets employed a patch-based method due to GPU memory constraints. Automated segmentation was applied to original NACT and synthetic CECT scans to evaluate CycleGAN performance using the Dice Similarity Coefficient (DSC) and the 95th percentile Hausdorff Distance (HD95p). Main Results: High-resolution scans showed improved auto-segmentation, with an average DSC increase from 0.728 to 0.773 and a reduced HD95p from 1.19 mm to 0.94 mm. Low-resolution scans benefited more from synthetic contrast, showing a DSC increase from 0.586 to 0.682 and an HD95p reduction from 3.46 mm to 1.24 mm. Significance: Implementing CycleGAN to synthesize CECT scans substantially improved the visibility of the mouse spleen, leading to more precise auto-segmentation. This approach shows the potential in preclinical imaging studies where contrast agent use is impractical. .

Computed tomography synthesis from magnetic resonance imaging using cycle Generative Adversarial Networks with multicenter learning.

Background and Purpose: Addressing the need for accurate dose calculation in MRI-only radiotherapy, the generation of synthetic Computed Tomography (sCT) from MRI has emerged. Deep learning (DL) techniques, have shown promising results in achieving high sCT accuracies. However, existing sCT synthesis methods are often center-specific, posing a challenge to their generalizability. To overcome this limitation, recent studies have proposed approaches, such as multicenter training . Material and methods: The purpose of this work was to propose a multicenter sCT synthesis by DL, using a 2D cycle-GAN on 128 prostate cancer patients, from four different centers. Four cases were compared: monocenter cases, monocenter training and test on another center, multicenter trainings and a test on a center not included in the training and multicenter trainings with an included center in the test. Trainings were performed using 20 patients. sCT accuracy evaluation was performed using Mean Absolute Error, Mean Error and Peak-Signal-to-Noise-Ratio. Dose accuracy was assessed with gamma index and Dose Volume Histogram comparison. Results: Qualitative, quantitative and dose results show that the accuracy of sCTs for monocenter trainings and multicenter trainings using a seen center in the test did not differ significantly. However, when the test involved an unseen center, the sCT quality was inferior. Conclusions: The aim of this work was to propose generalizable multicenter training for MR-to-CT synthesis. It was shown that only a few data from one center included in the training cohort allows sCT accuracy equivalent to a monocenter study.

A multi-centric evaluation of self-learning GAN based pseudo-CT generation software for low field pelvic magnetic resonance imaging.

Purpose/objectives: An artificial intelligence-based pseudo-CT from low-field MR images is proposed and clinically evaluated to unlock the full potential of MRI-guided adaptive radiotherapy for pelvic cancer care. Materials and method: In collaboration with TheraPanacea (TheraPanacea, Paris, France) a pseudo-CT AI-model was generated using end-to-end ensembled self-supervised GANs endowed with cycle consistency using data from 350 pairs of weakly aligned data of pelvis planning CTs and TrueFisp-(0.35T)MRIs. The image accuracy of the generated pCT were evaluated using a retrospective cohort involving 20 test cases coming from eight different institutions (US: 2, EU: 5, AS: 1) and different CT vendors. Reconstruction performance was assessed using the organs at risk used for treatment. Concerning the dosimetric evaluation, twenty-nine prostate cancer patients treated on the low field MR-Linac (ViewRay) at Montpellier Cancer Institute were selected. Planning CTs were non-rigidly registered to the MRIs for each patient. Treatment plans were optimized on the planning CT with a clinical TPS fulfilling all clinical criteria and recalculated on the warped CT (wCT) and the pCT. Three different algorithms were used: AAA, AcurosXB and MonteCarlo. Dose distributions were compared using the global gamma passing rates and dose metrics. Results: The observed average scaled (between maximum and minimum HU values of the CT) difference between the pCT and the planning CT was 33.20 with significant discrepancies across organs. Femoral heads were the most reliably reconstructed (4.51 and 4.77) while anal canal and rectum were the less precise ones (63.08 and 53.13). Mean gamma passing rates for 1%1mm, 2%/2mm, and 3%/3mm tolerance criteria and 10% threshold were greater than 96%, 99% and 99%, respectively, regardless the algorithm used. Dose metrics analysis showed a good agreement between the pCT and the wCT. The mean relative difference were within 1% for the target volumes (CTV and PTV) and 2% for the OARs. Conclusion: This study demonstrated the feasibility of generating clinically acceptable an artificial intelligence-based pseudo CT for low field MR in pelvis with consistent image accuracy and dosimetric results.

Use of a deep-learning-based lumen extraction method to detect significant stenosis on coronary computed tomography angiography in patients with severe coronary calcification.

BACKGROUND: Coronary computed tomography angiography examinations are increasingly becoming established as a minimally invasive method for diagnosing coronary diseases. However, although various imaging and processing methods have been developed, coronary artery calcification remains a major limitation in the evaluation of the vascular lumen. Subtraction coronary computed tomography angiography (Sub-CCTA) is a method known to be able to reduce the influence of coronary artery calcification and is therefore feasible for improving the diagnosis of significant stenosis in patients with severe calcification. However, Sub-CCTA still involves some problems, such as the increased radiation dose due to plain (mask) imaging, extended breath-holding time, and misregistration due to differences in the imaging phase. Therefore, we considered using artificial intelligence instead of Sub-CCTA to visualize the coronary lumen with high calcification. Given this background, the present study aimed to evaluate the diagnostic performance of a deep learning-based lumen extraction method (DL-LEM) to detect significant stenosis on CCTA in 99 consecutive patients (891 segments) with severe coronary calcification from November 2015 to March 2018. We also estimated the impact of DL-LEM on the medical economics in Japan. RESULTS: The DL-LEM slightly improved the per-segment diagnostic accuracy from 74.5 to 76.4%, and the area under the curve (AUC) slightly improved from 0.752 to 0.767 (p = 0.030). When analyzing the 228 segments that could not be evaluated because of severe calcification on the original CCTA images, the DL-LEM improved the accuracy from 35.5 to 42.5%, and the AUC improved from 0.500 to 0.587 (p = 0.00018). As a result, DL-LEM analysis could have avoided invasive coronary angiography in 4/99 cases (per patient). From the calculated results, it was estimated that the number of exams that can be avoided in Japan in one year is approximately 747 for invasive coronary angiography, 219 for fractional flow reserve, and 248 for nuclear exam. The total amount of medical fee that could be reduced was 225,629,368 JPY. CONCLUSIONS: These findings suggest that the DL-LEM may improve the diagnostic performance in detecting significant stenosis in patients with severe coronary calcification. In addition, the results suggest that not a small medical economic effect can be expected.

Facilitating MR-Guided Adaptive Proton Therapy in Children Using Deep Learning-Based Synthetic CT.

PURPOSE: To determine whether self-attention cycle-generative adversarial networks (cycle-GANs), a novel deep-learning method, can generate accurate synthetic computed tomography (sCT) to facilitate adaptive proton therapy in children with brain tumors. MATERIALS AND METHODS: Both CT and T1-weighted magnetic resonance imaging (MRI) of 125 children (ages 1-20 years) with brain tumors were included in the training dataset. A model introducing a self-attention mechanism into the conventional cycle-GAN was created to enhance tissue interfaces and reduce noise. The test dataset consisted of 7 patients (ages 2-14 years) who underwent adaptive planning because of changes in anatomy discovered on MRI during proton therapy. The MRI during proton therapy-based sCT was compared with replanning CT (ground truth). RESULTS: The Hounsfield unit-mean absolute error was significantly reduced with self-attention cycle-GAN, as compared with conventional cycle-GAN (65.3 ± 13.9 versus 88.9 ± 19.3, P < .01). The average 3-dimensional gamma passing rates (2%/2 mm criteria) for the original plan on the anatomy of the day and for the adapted plan were high (97.6% ± 1.2% and 98.9 ± 0.9%, respectively) when using sCT generated by self-attention cycle-GAN. The mean absolute differences in clinical target volume (CTV) receiving 95% of the prescription dose and 80% distal falloff along the beam axis were 1.1% ± 0.8% and 1.1 ± 0.9 mm, respectively. Areas of greatest dose difference were distal to the CTV and corresponded to shifts in distal falloff. Plan adaptation was appropriately triggered in all test patients when using sCT. CONCLUSION: The novel cycle-GAN model with self-attention outperforms conventional cycle-GAN for children with brain tumors. Encouraging dosimetric results suggest that sCT generation can be used to identify patients who would benefit from adaptive replanning.

Data Management and Network Architecture Effect on Performance Variability in Direct Attenuation Correction via Deep Learning for Cardiac SPECT: A Feasibility Study.

Attenuation correction (AC) is important for accurate interpretation of SPECT myocardial perfusion imaging (MPI). However, it is challenging to perform AC in dedicated cardiac systems not equipped with a transmission imaging capability. Previously, we demonstrated the feasibility of generating attenuation-corrected SPECT images using a deep learning technique (SPECTDL) directly from non-corrected images (SPECTNC). However, we observed performance variability across patients which is an important factor for clinical translation of the technique. In this study, we investigate the feasibility of overcoming the performance variability across patients for the direct AC in SPECT MPI by proposing to develop an advanced network and a data management strategy. To investigate, we compared the accuracy of the SPECTDL for the conventional U-Net and Wasserstein cycle GAN (WCycleGAN) networks. To manage the training data, clustering was applied to a representation of data in the lower-dimensional space, and the training data were chosen based on the similarity of data in this space. Quantitative analysis demonstrated that DL model with an advanced network improves the global performance for the AC task with the limited data. However, the regional results were not improved. The proposed data management strategy demonstrated that the clustered training has potential benefit for effective training.

Diagnosis of Typical Apple Diseases: A Deep Learning Method Based on Multi-Scale Dense Classification Network.

Disease has always been one of the main reasons for the decline of apple quality and yield, which directly harms the development of agricultural economy. Therefore, precise diagnosis of apple diseases and correct decision making are important measures to reduce agricultural losses and promote economic growth. In this paper, a novel Multi-scale Dense classification network is adopted to realize the diagnosis of 11 types of images, including healthy and diseased apple fruits and leaves. The diagnosis of different kinds of diseases and the same disease with different grades was accomplished. First of all, to solve the problem of insufficient images of anthracnose and ring rot, Cycle-GAN algorithm was applied to achieve dataset expansion on the basis of traditional image augmentation methods. Cycle-GAN learned the image characteristics of healthy apples and diseased apples to generate anthracnose and ring rot lesions on the surface of healthy apple fruits. The diseased apple images generated by Cycle-GAN were added to the training set, which improved the diagnosis performance compared with other traditional image augmentation methods. Subsequently, DenseNet and Multi-scale connection were adopted to establish two kinds of models, Multi-scale Dense Inception-V4 and Multi-scale Dense Inception-Resnet-V2, which facilitated the reuse of image features of the bottom layers in the classification neural networks. Both models accomplished the diagnosis of 11 different types of images. The classification accuracy was 94.31 and 94.74%, respectively, which exceeded DenseNet-121 network and reached the state-of-the-art level.

Training a deep neural network coping with diversities in abdominal and pelvic images of children and young adults for CBCT-based adaptive proton therapy.

PURPOSE: To train a deep neural network for correcting abdominal and pelvic cone-beam computed tomography (CBCT) of children and young adults in the presence of diverse patient size, anatomic extent, and scan parameters. MATERIALS AND METHODS: Pretreatment CBCT and planning/repeat CT image pairs from 64 children and young adults treated with proton therapy (aged 1-23 years) were analyzed. To evaluate the impact of anatomic extent in CBCT and data size in the training data, we compared the performance of three cycle-consistent generative adversarial network models that were separately trained by three datasets comprising abdominal (n = 21), pelvic (n = 29), and combined abdominal-pelvic image pairs (n = 50), respectively. The maximum body width of each patient was normalized to a fixed width before training and model application to reduce the impact of variations in body size. The corrected CBCT images by the three models were comparatively evaluated against the repeat CT closest in time to the CBCT (median gap, 0 days; range, 0-6 days) in HU accuracy, estimated dose distribution, and proton range. RESULTS: The network model trained by the combined dataset significantly outperformed the abdomen and pelvis models in mean absolute HU error of the corrected CBCT from 14 testing patients (47 ± 7 HU versus 51 ± 8 HU; paired Wilcoxon signed-rank test, P < 0.01). The larger error (60 ± 7 HU) without the body-size normalization confirmed the efficacy of the preprocessing. The model trained with the combined dataset resulted in gamma passing rates of 98.5 ± 1.9% (2%/2 mm criterion) and the range (80% distal fall-off) differences from the reference within ±3 mm for 91.2 ± 11.5% beamlets. CONCLUSION: Combining data from adjacent anatomic sites and normalizing age-dependent body sizes in children and young adults were beneficial in training a neural network to accurately estimate proton dose from CBCT despite limited training data size and anatomic diversities.

CT synthesis from MRI using multi-cycle GAN for head-and-neck radiation therapy.

Magnetic Resonance Imaging (MRI) guided Radiation Therapy is a hot topic in the current studies of radiotherapy planning, which requires using MRI to generate synthetic Computed Tomography (sCT). Despite recent progress in image-to-image translation, it remains challenging to apply such techniques to generate high-quality medical images. This paper proposes a novel framework named Multi-Cycle GAN, which uses the Pseudo-Cycle Consistent module to control the consistency of generation and the domain control module to provide additional identical constraints. Besides, we design a new generator named Z-Net to improve the accuracy of anatomy details. Extensive experiments show that Multi-Cycle GAN outperforms state-of-the-art CT synthesis methods such as Cycle GAN, which improves MAE to 0.0416, ME to 0.0340, PSNR to 39.1053.

High tissue contrast image synthesis via multistage attention-GAN: Application to segmenting brain MR scans.

Magnetic resonance imaging (MRI) presents a detailed image of the internal organs via a magnetic field. Given MRI's non-invasive advantage in repeated imaging, the low-contrast MR images in the target area make segmentation of tissue a challenging problem. This study shows the potential advantages of synthetic high tissue contrast (HTC) images through image-to-image translation techniques. Mainly, we use a novel cycle generative adversarial network (Cycle-GAN), which provides a mechanism of attention to increase the contrast within the tissue. The attention block and training on HTC images are beneficial to our model to enhance tissue visibility. We use a multistage architecture to concentrate on a single tissue as a preliminary and filter out the irrelevant context in every stage in order to increase the resolution of HTC images. The multistage architecture reduces the gap between source and target domains and alleviates synthetic images' artefacts. We apply our HTC image synthesising method to two public datasets. In order to validate the effectiveness of these images we use HTC MR images in both end-to-end and two-stage segmentation structures. The experiments on three segmentation baselines on BraTS'18 demonstrate that joining the synthetic HTC images in the multimodal segmentation framework develops the average Dice similarity scores (DSCs) of 0.8%, 0.6%, and 0.5% respectively on the whole tumour (WT), tumour core (TC), and enhancing tumour (ET) while removing one real MRI channels from the segmentation pipeline. Moreover, segmentation of infant brain tissue in T1w MR slices through our framework improves DSCs approximately 1% in cerebrospinal fluid (CSF), grey matter (GM), and white matter (WM) compared to state-of-the-art segmentation techniques. The source code of synthesising HTC images is publicly available.

Magnetic resonance-based synthetic computed tomography images generated using generative adversarial networks for nasopharyngeal carcinoma radiotherapy treatment planning.

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 ±â€¯9.27 HU and 100.62 ±â€¯7.39 HU for the cGAN and cycleGAN, respectively. The 2%/2-mm γ passing rates were (98.68 ±â€¯0.94)% and (98.52 ±â€¯1.13)% for the cGAN and cycleGAN, respectively. Meanwhile, the absolute dose discrepancies within the regions of interest were (0.49 ±â€¯0.24)% and (0.62 ±â€¯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.

Paired cycle-GAN-based image correction for quantitative cone-beam computed tomography.

PURPOSE: The incorporation of cone-beam computed tomography (CBCT) has allowed for enhanced image-guided radiation therapy. While CBCT allows for daily 3D imaging, images suffer from severe artifacts, limiting the clinical potential of CBCT. In this work, a deep learning-based method for generating high quality corrected CBCT (CCBCT) images is proposed. METHODS: The proposed method integrates a residual block concept into a cycle-consistent adversarial network (cycle-GAN) framework, called res-cycle GAN, to learn a mapping between CBCT images and paired planning CT images. Compared with a GAN, a cycle-GAN includes an inverse transformation from CBCT to CT images, which constrains the model by forcing calculation of both a CCBCT and a synthetic CBCT. A fully convolution neural network with residual blocks is used in the generator to enable end-to-end CBCT-to-CT transformations. The proposed algorithm was evaluated using 24 sets of patient data in the brain and 20 sets of patient data in the pelvis. The mean absolute error (MAE), peak signal-to-noise ratio (PSNR), normalized cross-correlation (NCC) indices, and spatial non-uniformity (SNU) were used to quantify the correction accuracy of the proposed algorithm. The proposed method is compared to both a conventional scatter correction and another machine learning-based CBCT correction method. RESULTS: Overall, the MAE, PSNR, NCC, and SNU were 13.0 HU, 37.5 dB, 0.99, and 0.05 in the brain, 16.1 HU, 30.7 dB, 0.98, and 0.09 in the pelvis for the proposed method, improvements of 45%, 16%, 1%, and 93% in the brain, and 71%, 38%, 2%, and 65% in the pelvis, over the CBCT image. The proposed method showed superior image quality as compared to the scatter correction method, reducing noise and artifact severity. The proposed method produced images with less noise and artifacts than the comparison machine learning-based method. CONCLUSIONS: The authors have developed a novel deep learning-based method to generate high-quality corrected CBCT images. The proposed method increases onboard CBCT image quality, making it comparable to that of the planning CT. With further evaluation and clinical implementation, this method could lead to quantitative adaptive radiation therapy.