Unpaired-paired learning for shading correction in cone-beam computed tomography

HS Park, K Jeon, SH Lee, JK Seo - IEEE Access, 2022 - ieeexplore.ieee.org
… two-stage GANbased image-to-image translation method that … image-to-image translation,
the application of GAN-based techniques, such as cycleGAN, in high-quality medical-imaging

Cycle-Generative Adversarial Network-Based Image Correction of 4-Dimensional Cone-Beam Computed Tomography for Lung Cancer Adaptive Radiation Therapy

K Usui, K Ogawa, M Goto, Y Sakano… - International Journal of …, 2021 - redjournal.org
… in quantitative and qualitative image qualities. … images could achieve near-ideal quality of
4D-CT images. Large structures were generally consistent with those in paired 4D-CT images, …

Visual enhancement of conebeam CT by use of CycleGAN

S Kida, S Kaji, K Nawa, T Imae, T Nakamoto… - Medical …, 2020 - Wiley Online Library
Cone-beam computed tomography imaging systems can be … aligned paired images, a
cycle-consistency GAN (CycleGAN)… constitutes bad mappings in a quantitative way in terms of a …

[HTML][HTML] Generating synthetic CT from low-dose cone-beam CT by using generative adversarial networks for adaptive radiotherapy

L Gao, K Xie, X Wu, Z Lu, C Li, J Sun, T Lin, J Sui… - Radiation Oncology, 2021 - Springer
image and reconstructed CBCT image based on corrected … Then, a quantitative assessment
of the generated sCT images … , 136 pairs as the training dataset and 34 pairs as testing …

Generative Adversarial Network based Quantitative Cone Beam CT for Bone Mineral Density

용태훈 - 2021 - s-space.snu.ac.kr
… We used paired training data in the Cycle-GANbased on the residual image and generate
corrected bone … and subjective image quality of cone-beam computed tomography images

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

K Usui, K Ogawa, M Goto, Y Sakano, S Kyougoku… - Radiation …, 2022 - Springer
… : one was correction effect of image noise and projection … by the CycleGAN model, quantitative
evaluation of image quality … A CycleGAN can be used with non-paired training data and …

[HTML][HTML] Frequency-Domain-Based Structure Losses for CycleGAN-Based Cone-Beam Computed Tomography Translation

S Pai, I Hadzic, C Rao, I Zhovannik, A Dekker… - Sensors, 2023 - mdpi.com
… of paired training approaches is the need to obtain paired … with existing CBCT correction
methods, both image and dosimetry-… to identify using pixel-based quantitative metrics and, to the …

[HTML][HTML] Anatomical evaluation of deep-learning synthetic computed tomography images generated from male pelvis cone-beam computed tomography

YJM de Hond, CEM Kerckhaert… - Physics and Imaging in …, 2023 - Elsevier
… , a cone-beam CT (CBCT) is often used to correct the … from CBCT scans was quantitatively
assessed for paired and unpaired dl… Single-UNet and unpaired CycleGAN. All three dl-models …

An unsupervised deep learning network model for artifact correction of cone-beam computed tomography images

W Zhang, H Ding, H Xu, MM Jin, G Huang - Biomedical Signal Processing …, 2024 - Elsevier
cycle-consistent generative adversarial network (CycleGAN) is … However, CBCT and PCT
images cannot be perfectly matched … The results of quantitative and qualitative analyses are …

[HTML][HTML] Cone-beam CT image quality improvement using Cycle-Deblur consistent adversarial networks (Cycle-Deblur GAN) for chest CT imaging in breast cancer …

HJ Tien, HC Yang, PW Shueng, JC Chen - Scientific reports, 2021 - nature.com
… fan-beam computed tomography (FBCT), the image quality of … CycleGAN does not need
paired data, and we could use … The mean absolute error (MAE) is one of the quantitative