A customized convolutional neural network model for the detection of COVID-19 at an early stage using chest X-ray images
Loading...
Date
2021-05-28
Journal Title
Journal ISSN
Volume Title
Publisher
UMT Lahore
Abstract
COVID-19 has been difficult to diagnose and treat at an early stage all over the world. Patients showing symptoms for COVID-19 are resulting in medical facilities at hospitals becoming unavailable or overcrowded, which is becoming a major challenge. Studies have recently allowed us to determine that COVID-19 can be diagnosed with the aid of chest X-ray images. To combat the COVID-19 outbreak, developing a deep learning (DL)–based model for automatic COVID-19 diagnosis on chest X-ray images is beneficial. In this research, we proposed a customized convolutional neural network (CNN) model to detect COVID-19 from chest X-ray images. The model is based on nine layers and uses binary classification to differentiate between COVID-19 and normal chest X-rays, providing early COVID-19 detection so that patients can be admitted in a timely manner. Six hundred X-ray images were used for training and two hundred X-ray images were used for validation of the model from two publicly available datasets. The X-ray images in the dataset were preprocessed to improve results and were visualized for better analysis. The developed algorithm achieved 98% precision, recall, and F1-score. The average accuracy of the model was 98.5%. Furthermore, a comparison table was created that clearly showed our proposed model outperformed other models in terms of accuracy. The quick and high performance of the proposed DL-based customized model enables rapid identification of COVID-19 patients, which is helpful in controlling the COVID-19 outbreak.