[HTML][HTML] A two-stage deep-learning framework for CT denoising based on a clinically structure-unaligned paired data set

R Hu, Y Xie, L Zhang, L Liu, H Luo, R Wu… - Quantitative Imaging …, 2024 - ncbi.nlm.nih.gov
… (39), we used an attention module for feature correction in the … of the CycleGAN network for
CT image reconstruction. We … -enhanced computerised tomography angiograms without the …

Ring artifacts correction for computed tomography image using unsupervised contrastive learning

T Wang, X Liu, C Zhang, Y He, Y Chan… - … in Medicine & Biology, 2023 - iopscience.iop.org
… data, and cone beam computed tomography images of the … the corrected CT image better
matched the real reference CT … style transfer models is constantly evolving, with CycleGAN, …

A cycle generative adversarial network for generating synthetic contrast-enhanced computed tomographic images from non-contrast images in the internal jugular …

M Fukuda, S Kotaki, M Nozawa, C Kuwada, Y Kise… - Odontology, 2024 - Springer
… , cycle generative adversarial networks (cycleGANs) address the limitation of requiring paired
images for … two images, it serves as a quantitative measure of how different or similar those …

Cephalogram synthesis and landmark detection in dental cone-beam CT systems

Y Huang, F Fan, C Syben, P Roser, L Mill… - Medical Image Analysis, 2021 - Elsevier
… , 2D cephalograms synthesized from 3D cone-beam computed tomography (CBCT) volumes
… a cone-beam projection while the target output is the corresponding patch from the paired

Synthetic CT generation from CBCT images via unsupervised deep learning

L Chen, X Liang, C Shen, D Nguyen… - … in Medicine & Biology, 2021 - iopscience.iop.org
… Daily or weekly cone-beam computed tomography (CBCT) is … As obtaining exactly matched
CBCT and pCT is unlikely, we … scatter estimation in cone beam CT Proc SPIE 6510 65102E …

Investigation of low-dose CT image denoising using unpaired deep learning methods

Z Li, S Zhou, J Huang, L Yu… - IEEE transactions on …, 2020 - ieeexplore.ieee.org
… Furthermore, in its original form of GAN, the paired images … Ma et al., "Low-dose computed
tomography image restoration … Pan, "Image reconstruction in circular cone-beam computed

CT-Based Pelvic T1-Weighted MR Image Synthesis Using UNet, UNet++ and Cycle-Consistent Generative Adversarial Network (Cycle-GAN)

R Kalantar, C Messiou, JM Winfield, A Renn… - Frontiers in …, 2021 - frontiersin.org
Computed tomography (CT) is conventionally used for the … radiologist qualitative testing on
Cycle-GAN predicted images … developed paired and unpaired training for T 1 W MR image

A selective kernel-based cycle-consistent generative adversarial network for unpaired low-dose CT denoising

C Tan, M Yang, Z You, H Chen… - Precision Clinical …, 2022 - academic.oup.com
… Low-dose computed tomography (LDCT) denoising is an … In this paper, 135 250 pairs of 256
× 256 CT image patches from … has higher quantitative value and is closer to NDCT images. …

CBCT‐Based synthetic CT image generation using conditional denoising diffusion probabilistic model

J Peng, RLJ Qiu, JF Wynne, CW Chang, S Pan… - Medical …, 2024 - Wiley Online Library
… Daily or weekly cone-beam computed tomography (CBCT) … results in both visual quality
and quantitative analysis. … attention mechanism were introduced to paired Cycle-GAN, 20, 22 …

[PDF][PDF] Artifact Reduction in 3D and 4D Cone-beam Computed Tomography Images with Deep Learning-A Review

DB MOHAMMADREZA AMIRIAN, FP Schilling - core.ac.uk
… (initial corrections such as scatter corrections have already … The main qualitative evaluation
metrics, computed between … architecture coupled with a bilateral 3D filter and a 2D-based