Coronavirus Disease (COVID-19) X-Ray Film Classification Based on Convolutional Neural Network

The main incidence of pneumonia in Wuhan is that Coronavirus Disease (COVID-19) infects the lungs and causes respiratory failure [1]. Based on the technical research of lung infection detection, the medical image X-ray film can be detected by artificial intelligence technology to effectively improve the diagnosis accuracy and efficiency. We propose an end-to-end solution based on a deep learning method. This method uses a variety of convolutional neural networks to generate feature maps, and then stitch the feature maps by channel to obtain good performance on our data set. In our experiments, the accuracy rate obtained by experimenting with only one feature map is best at 0.89, and then the feature maps are stitched using four convolutional neural networks to obtain 0.91.