Objectives
The current study aimed to design an ultra-low-dose CT examination protocol using a deep learning approach suitable for clinical diagnosis of COVID-19 patients.
Methods
In this study, 800, 170, and 171 pairs of ultra-low-dose and full-dose CT images were used as input/output as training, test, and external validation set, respectively, to implement the full-dose prediction technique. A residual convolutional neural network was applied to generate full-dose from ultra-low-dose CT images. The quality of predicted CT images was assessed using root mean square error (RMSE), structural similarity index (SSIM), and peak signal-to-noise ratio (PSNR). Scores ranging from 1 to 5 were assigned reflecting subjective assessment of image quality and related COVID-19 features, including ground glass opacities (GGO), crazy paving (CP), consolidation (CS), nodular infiltrates (NI), bronchovascular thickening (BVT), and pleural effusion (PE).
Results
The radiation dose in terms of CT dose index (CTDI
vol
) was reduced by up to 89%. The RMSE decreased from 0.16 ± 0.05 to 0.09 ± 0.02 and from 0.16 ± 0.06 to 0.08 ± 0.02 for the predicted compared with ultra-low-dose CT images in the test and external validation set, respectively. The overall scoring assigned by radiologists showed an acceptance rate of 4.72 ± 0.57 out of 5 for reference full-dose CT images, while ultra-low-dose CT images rated 2.78 ± 0.9. The predicted CT images using the deep learning algorithm achieved a score of 4.42 ± 0.8.
Conclusions
The results demonstrated that the deep learning algorithm is capable of predicting standard full-dose CT images with acceptable quality for the clinical diagnosis of COVID-19 positive patients with substantial radiation dose reduction.
Key Points
• Ultra-low-dose CT imaging of COVID-19 patients would result in the loss of critical information about lesion types, which could potentially affect clinical diagnosis.
• Deep learning–based prediction of full-dose from ultra-low-dose CT images for the diagnosis of COVID-19 could reduce the radiation dose by up to 89%.
• Deep learning algorithms failed to recover the correct lesion structure/density for a number of patients considered outliers, and as such, further research and development is warranted to address these limitations.
Electronic supplementary material
The online version of this article (10.1007/s00330-020-07225-6) contains supplementary material, which is available to authorized users.
Abstract-In this paper, periodic structures are investigated in antenna design for wireless applications. These antennas were compared with CRLH miniaturization method. Three different models of patch antenna with coaxial feed on EBG ground, metamaterial substrate or EBG/AMC structure have been presented here. Also two compact dual-band antennas have been designed and fabricated based on CRLH techniques for wireless and GSM applications. The first antenna has directional pattern and operates at 1760, 2550 and 3850 MHz (three-band antenna) with gain 2.1, −3.9 and 2.5 dBi, and it is dual polarized. The size of prototype patch antenna is 20 × 20 mm 2 which is reduced about 47% in comparison to conventional patch antenna at 2.5 GHz. The second antenna is designed by the use of interdigital capacitor and spiral inductor. Dimensions of antenna are 15.5×12 mm 2 , so the size is reduced about 69% in comparison to conventional microstrip patch antennas at 1.8 GHz. The second tri-band antenna operates at 1060 MHz, 1800 MHz and 2500 MHz in which two frequencies (1.8 and 2.5 GHz) are suitable for GMS and WLAN applications. Both structures have been designed and fabricated on FR4 low cost substrate with ε r = 4.4 and thickness of 1.6 mm. All simulations are done with CST and HFSS. Equivalent circuit and experimental results are also presented and compared.
Enhanced chromosomal radiosensitivity is a feature of many cancer predisposition conditions, indicative of the important role of chromosomal alterations in carcinogenesis. In this study the cytokinesis-blocked micronucleous assay was used to compare the radiosensitivity of blood lymphocytes obtained from Iranian breast or esophageal cancer patients (n = 50, n = 16; respectively) with that of control individuals (n = 40). For each sample, one thousand binucleate lymphocytes were analyzed before and after in vitro exposure to 3 Gy of gamma rays. The radiation-induced frequency of micronucleus was significantly higher in the breast cancer group (261/1,000 binucleated cells) than in esophageal cancer group (241/1,000 binucleated cells, P < 0.01) or in the control group (240/1,000 binucleated cells, P < 0.01). The results indicate that breast cancer patients are more radiosensitive compared to normal healthy individuals or esophageal cancer patients. Increased radiosensitivity could be due to defects in DNA repair genes involved in breast cancer formation. Since patients with esophageal cancer did not show elevated radiosensitivity, it is assumed that the contribution of radiosensitivity-related genes to the development of esophageal cancer may be smaller than the contribution of those genes to breast cancer.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.