Automatic classification of COVID-19 infected patients using convolution neural network models

ABSTRACT

Coronavirus (COVID-19) has infected millions of people and continues to have a disastrous impact on the economy and health. Timely diagnosis of the COVID-19 infection can help contain the virus and prevent much loss of life. The COVID-19 diagnosis can be achieved by the Reverse Transcript Polymerase Chain Reaction test (RT-PCR) but it has a high false-negative rate and has low sensitivity as compared to Computed Tomography (CT) and X-Ray images. In this study, we have trained six different architectures of the Convolution Neural Network (CNN) model to detect COVID-19. We tried to identify the most efficient CNN model based on accuracy and the number of trainable parameters. The model has been trained on a Chest X-Ray image dataset retrieved from the GitHub platform with 1811 images in the training dataset and 484 images in the validation dataset. The model with the highest accuracy has been trained for a variable number of epochs varying the filter size. It has been demonstrated that architecture 3 can achieve 99% accuracy for 500 epochs with a minimum number of trainable parameters. Using just a simple CNN architecture that can be deployed in any rural healthcare center we can achieve a high level of accuracy for classification with the added advantage of less complexity. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2022.