Transfer Learning-Based Automatic Detection of Coronavirus Disease ۲۰۱۹ (COVID-۱۹) from Chest X-ray Images

Background: Coronavirus disease ۲۰۱۹ (COVID-۱۹) is an emerging infectious disease and global health crisis. Although real-time reverse transcription polymerase chain reaction (RT-PCR) is known as the most widely laboratory method to detect the COVID-۱۹ from respiratory specimens. It suffers from several main drawbacks such as time-consuming, high false-negative results, and limited availability. Therefore, the automatically detect of COVID-۱۹ will be required. Objective: This study aimed to use an automated deep convolution neural network based pre-trained transfer models for detection of COVID-۱۹ infection in chest X-rays.Material and Methods: In a retrospective study, we have applied Visual Geometry Group (VGG)-۱۶, VGG-۱۹, MobileNet, and InceptionResNetV۲ pre-trained models for detection COVID-۱۹ infection from ۳۴۸ chest X-ray images. Results: Our proposed models have been trained and tested on a dataset which previously prepared. The all proposed models provide accuracy greater than ۹۰.۰%. The pre-trained MobileNet model provides the highest classification performance of automated COVID-۱۹ classification with ۹۹.۱% accuracy in comparison with other three proposed models. The plotted area under curve (AUC) of receiver operating characteristics (ROC) of VGG۱۶, VGG۱۹, MobileNet, and InceptionResNetV۲ models are ۰.۹۲, ۰.۹۱, ۰.۹۹, and ۰.۹۷, respectively.  Conclusion: The all proposed models were able to perform binary classification with the accuracy more than ۹۰.۰% for COVID-۱۹ diagnosis. Our data indicated that the MobileNet can be considered as a promising model to detect COVID-۱۹ cases. In the future, by increasing the number of samples of COVID-۱۹ chest X-rays to the training dataset, the accuracy and robustness of our proposed models increase further.