Background: The Coronavirus Disease 2019 (COVID-19) is highly contagious and spreading around the world like wildfire. For this reason, fast and accurate diagnosis of COVID-19 is of tremendous importance. Chest X-rays can be used to diagnose COVID-19 but there is a global shortage of radiologists who can interpret X-rays. This study aims to develop an artificial intelligence system that can diagnose COVID-19 from chest X-rays with no human intervention.
Methods: In this study, we used four pre-trained architectures - VGG16, MobileNetV2, InceptionV3 and Xception to detect COVID-19 from chest x-ray images. The architectures are optimized using Bayesian optimization and we used a weighted loss function to get better generalization capability in our models.
Results: Of the four architectures we optimized, our proposed model called COVIDXception-Net performed best on the test set with an accuracy 0.94, precision 0.95, recall 0.94, and F1-score 0.94. It outperforms previous state-of-the-art methods in terms of these evaluation metrics on similar datasets. In the ablation studies, we found that the accuracy of our model dropped from 0.994 to 0.950 when we used random search instead of Bayesian optimization and 0.994 to 0.983 when we used regular loss function instead of a weighted loss function.
Conclusions: In this study, we developed a model called COVIDXception-Net to diagnose COVID-19 from X-ray images. We hope that our research will assist all those involved in handling this pandemic.
