Automatic Diagnosis of COVID-19 Pneumonia using Artificial Intelligence Deep Learning Algorithm Based on Lung Computed Tomography Images.

Background: The lung computed tomography (CT) scan contains valuable information and patterns that provide the possibility of early diagnosis of COVID-19 disease as a global pandemic by the image processing software. In this research, based on deep learning of artificial intelligence, the software has been designed that is used clinically to diagnose COVID-19 disease with high accuracy. Methods: Convolutional neural network architecture developed based on Inception-V3 for deep learning of lung image patterns, feature extraction, and image classification. The theory of transfer learning was utilized to increase the learning power of the system. Changes applied in the network layers to increase the detection power. The process of learning was repeated 30 times. All diagnostic statistical parameters of the diagnostic were analyzed to validate the software. Results: Based on the data of Imam Khomeini Hospital in Sari, the validity, sensitivity, and accuracy of the software in diagnosing of affected to COVID-19 and nonaffected to it were obtained 98%, 98%, and 98%, respectively. Diagnostic statistical parameters on some data were 100%. The modified algorithm of Inception-V3 applied to heterogeneous data also had acceptable precision. Conclusion: The proposed basic architecture of Inception-v3 utilized for this research has an admissible speed and exactness in learning CT scan images of patients' lungs, and diagnosis of COVID-19 pneumonia, which can be utilized clinically as a powerful diagnostic tool.

Assessment of target volume doses in radiotherapy based on the standard and measured calibration curves.

CONTEXT: In radiation treatments, estimation of the dose distribution in the target volume is one of the main components of the treatment planning procedure. To estimate the dose distribution, the information of electron densities is necessary. The standard curves determined by computed tomography (CT) scanner that may be different from that of other oncology centers. In this study, the changes of dose calculation due to the different calibration curves (HU-ρel) were investigated. MATERIALS AND METHODS: Dose values were calculated based on the standard calibration curve that was predefined for the treatment planning system (TPS). The calibration curve was also extracted from the CT images of the phantom, and dose values were calculated based on this curve. The percentage errors of the calculated values were determined. STATISTICAL ANALYSIS USED: The statistical analyses of the mean differences were performed using the Wilcoxon rank-sum test for both of the calibration curves. RESULTS AND DISCUSSION: The results show no significant difference for both of the measured and standard calibration curves (HU-ρel) in 6, 15, and 18 MeV energies. In Wilcoxon ranked sum nonparametric test for independent samples with P<0.05, the equality of monitor units for both of the curves to transfer 200 cGy doses to reference points was resulted. The percentage errors of the calculated values were lower than 2% and 1.5% in 6 and 15 MeV, respectively. CONCLUSION: From the results, it could be concluded that the standard calibration curve could be used in TPS dose calculation accurately.