scholarly journals Generating synthetic CT from low-dose cone-beam CT by using generative adversarial networks for adaptive radiotherapy

2021 ◽  
Vol 16 (1) ◽  
Author(s):  
Liugang Gao ◽  
Kai Xie ◽  
Xiaojin Wu ◽  
Zhengda Lu ◽  
Chunying Li ◽  
...  
Keyword(s):  
Image Quality ◽  
Low Dose ◽  
Cone Beam Ct ◽  
Dose Calculation ◽  
Cone Beam ◽  
Generative Adversarial Networks ◽  
High Quality ◽  
Passing Rates ◽  
Adversarial Networks ◽  
Synthetic Ct

Abstract Objective To develop high-quality synthetic CT (sCT) generation method from low-dose cone-beam CT (CBCT) images by using attention-guided generative adversarial networks (AGGAN) and apply these images to dose calculations in radiotherapy. Methods The CBCT/planning CT images of 170 patients undergoing thoracic radiotherapy were used for training and testing. The CBCT images were scanned under a fast protocol with 50% less clinical projection frames compared with standard chest M20 protocol. Training with aligned paired images was performed using conditional adversarial networks (so-called pix2pix), and training with unpaired images was carried out with cycle-consistent adversarial networks (cycleGAN) and AGGAN, through which sCT images were generated. The image quality and Hounsfield unit (HU) value of the sCT images generated by the three neural networks were compared. The treatment plan was designed on CT and copied to sCT images to calculated dose distribution. Results The image quality of sCT images by all the three methods are significantly improved compared with original CBCT images. The AGGAN achieves the best image quality in the testing patients with the smallest mean absolute error (MAE, 43.5 ± 6.69), largest structural similarity (SSIM, 93.7 ± 3.88) and peak signal-to-noise ratio (PSNR, 29.5 ± 2.36). The sCT images generated by all the three methods showed superior dose calculation accuracy with higher gamma passing rates compared with original CBCT image. The AGGAN offered the highest gamma passing rates (91.4 ± 3.26) under the strictest criteria of 1 mm/1% compared with other methods. In the phantom study, the sCT images generated by AGGAN demonstrated the best image quality and the highest dose calculation accuracy. Conclusions High-quality sCT images were generated from low-dose thoracic CBCT images by using the proposed AGGAN through unpaired CBCT and CT images. The dose distribution could be calculated accurately based on sCT images in radiotherapy.

scholarly journals Evaluation of a low-dose protocol for cone beam computed tomography of the temporomandibular joint

2020 ◽  
Vol 49 (6) ◽  
pp. 20190495 ◽  
Author(s):  
Durer Iskanderani ◽  
Mats Nilsson ◽  
Per Alstergren ◽  
Xie-Qi Shi ◽  
Kristina Hellen-halme
Keyword(s):  
Image Quality ◽  
Radiation Dose ◽  
Temporomandibular Joint ◽  
Low Dose ◽  
Cone Beam Ct ◽  
Cone Beam ◽  
Sign Test ◽  
Intraobserver Agreement ◽  
Radiographic Findings ◽  
Need To Evaluate

Objective: Evaluation of cone beam CT (CBCT) examination with a low-dose scanning protocol for assessment of the temporomandibular joint (TMJ). Methods: 34 adult patients referred for CBCT imaging of the TMJ underwent two examinations with two scanning protocols, a manufacturer-recommended protocol (default) and a low-dose protocol where the tube current was reduced to 20% of the default protocol. Three image stacks were reconstructed: default protocol, low-dose protocol, and processed (using a noise reduction algorithm) low-dose protocol. Four radiologists evaluated the images. The Sign test was used to evaluate visibility of TMJ anatomic structures and image quality. Receiver operating characteristic analyzes were performed to assess the diagnostic accuracy. κ values were used to evaluate intraobserver agreement. Results: With the low-dose and processed protocols, visibility of the TMJ anatomical structures and overall image quality were comparable to the default protocol. No significant differences in radiographic findings were found for the two low-dose protocols compared to the default protocol. The area under the curves (Az) averaged for the low-dose and processed protocols, according to all observers, were 0.931 and 0.941, respectively. Intraobserver agreement was good to very good. Conclusion: For the CBCT unit used in this study, the low-dose CBCT protocol for TMJ examination was diagnostically comparable to the manufacturer-recommended protocol, but delivered a five times lower radiation dose. There is an urgent need to evaluate protocols for CBCT examinations of TMJ in order to optimize them for a radiation dose as low as diagnostically acceptable (the as low as diagnostically acceptable principle recommended by NCRP).

scholarly journals Patient-based low dose cone beam CT acquisition settings for prostate image-guided radiotherapy treatments on a Varian TrueBeam linear accelerator

2020 ◽  
Vol 93 (1115) ◽  
pp. 20200412
Author(s):  
Maria Antonietta Piliero ◽  
Margherita Casiraghi ◽  
Davide Giovanni Bosetti ◽  
Simona Cima ◽  
Letizia Deantonio ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Image Quality ◽  
Low Dose ◽  
Cone Beam Ct ◽  
Subjective Evaluation ◽  
Cone Beam ◽  
Low Contrast ◽  
Image Guided Radiotherapy ◽  
Image Guided ◽  
Prostate Cancer Radiotherapy

Objective: To evaluate the performance of low dose cone beam CT (CBCT) acquisition protocols for image-guided radiotherapy of prostate cancer. Methods: CBCT images of patients undergoing prostate cancer radiotherapy were acquired with the settings currently used in our department and two low dose settings at 50% and 63% lower exposure. Four experienced radiation oncologists and two radiation therapy technologists graded the images on five image quality characteristics. The scores were analysed through Visual Grading Regression, using the acquisition settings and the patient size as covariates. Results: The low dose acquisition settings have no impact on the image quality for patients with body profile length at hip level below 100 cm. Conclusions: A reduction of about 60% of the dose is feasible for patients with size below 100 cm. The visibility of low contrast features can be compromised if using the low dose acquisition settings for patients with hip size above 100 cm. Advances in knowledge: Low dose CBCT acquisition protocols for the pelvis, based on subjective evaluation of patient images.

SU-F-J-109: Generate Synthetic CT From Cone Beam CT for CBCT-Based Dose Calculation

2016 ◽  
Vol 43 (6Part10) ◽  
pp. 3432-3432
Author(s):  
H Wang ◽  
D Barbee ◽  
W Wang ◽  
R Pennell ◽  
K Hu ◽  
...  
Keyword(s):  
Cone Beam Ct ◽  
Dose Calculation ◽  
Cone Beam ◽  
Synthetic Ct

Low dose cone beam CT for paediatric image-guided radiotherapy: image quality and practical recommendations

2021 ◽  
Author(s):  
Abigail Bryce-Atkinson ◽  
Rianne De Jong ◽  
Tom Marchant ◽  
Gillian Whitfield ◽  
Marianne C Aznar ◽  
...  
Keyword(s):  
Image Quality ◽  
Low Dose ◽  
Cone Beam Ct ◽  
Cone Beam ◽  
Image Guided Radiotherapy ◽  
Image Guided ◽  
Practical Recommendations

scholarly journals EP-2059 Assessment of image quality in simulated low-dose paediatric cone beam CT

2019 ◽  
Vol 133 ◽  
pp. S1133-S1134
Author(s):  
J.W.H. Lindsay ◽  
A. Bryce-Atkinson ◽  
M. Van Herk ◽  
M.C. Aznar
Keyword(s):  
Image Quality ◽  
Low Dose ◽  
Cone Beam Ct ◽  
Cone Beam

Flat Panel Cone Beam Computed Tomography of the Sinuses

2008 ◽  
Vol 139 (2_suppl) ◽  
pp. P77-P78
Author(s):  
Richard A Zoumalan ◽  
Kathryn Shouyee Yung ◽  
Edwin Wang ◽  
Richard A Lebowitz ◽  
Joseph B Jacobs
Keyword(s):  
Image Quality ◽  
Ct Scan ◽  
Low Dose ◽  
Multidetector Ct ◽  
Imaging Modality ◽  
Cone Beam Ct ◽  
Image Noise ◽  
Cone Beam ◽  
High Dose ◽  
Flat Panel

Objective Flat panel cone beam CT is a relatively new technology that improves upon traditional multidetector CT scanners by generating images with greater spatial resolution at lower radiation doses. 1) Learn whether flat panel cone beam CT evaluation is an effective imaging modality for the sinuses. 2) Learn which doses of radiation provide quality evaluation of the sinuses while exposing the patient to the least amount of radiation. Methods In 2007, a panel consisting of neuroradiologists and otolaryngologists blindly reviewed images from flat panel sinus CTs (Xoran MiniCAT) of 11 live human subjects, each irradiated at all 3 different techniques (denoted as: low dose mAs=9.27, medium dose mAs = 18.41, high dose mAs=36.7) and rated the image quality of a pre-designated list of sinus anatomic structures. Techniques were compared in a pairwise manner using a Wilcoxon matched-pairs signed ranks test. Results Compared to the low dose technique CT scan, the high dose CT scan technique had significantly better image quality (P=.0029) and image noise (P=.0049). Similarly, the medium dose CT scan technique had significantly better image quality (P=.0020) and image noise (P = .0010) compared to the low dose technique. No difference in image quality and image noise existed between the medium and high dose techniques. No difference in visualization of 13 specific anatomic structures existed between any of the dose techniques. Conclusions Lower dose CT techniques achieved by flat panel cone beam CT may be an effective and safe alternative to traditional multidetector CT scanners. This imaging modality may help patients avoid unnecessary radiation to sensitive organs.

Sign in / Sign up

Export Citation Format

Share Document