Study of Metadata Impact on COVID-19 Detection using Convolutional Neural Networks

ABSTRACT

COVID-19 is a lethal viral disease that attacks the respiratory system. This contagious disease started spreading all around the world in December 2019. A Computerized chest Tomography (CT) scan is a trusted and recommended imaging tool to detect the COVID-19. Although manual CT image examination is an option, it takes significant time to get analyzed by a technician. Automating this process can be done by deep Convolutional Neural Networks (CNN). Applying these networks in analyzing the CT images could result in great success. There are several works focused on detecting COVID-19 by applying CNN uses different algorithms to classify COVID-19 patients from normal or pneumonia patients. The proposed models in these works mostly use limited and small data sets that could lead to generalization issues or biased predictions. In this paper we explore three methods for training a classifier for COVID-19 detection tasks using a large-scale public data set. In our first method, we only rely on CT images with training the CNN models. In the second method, we use pre-trained CNN models for image feature extraction and use those features for training classical machine learning models. In the last method, we propose an end-to-end model that gets both image and the metadata such as age and gender to experiment with the impact of metadata on COVID-19 detection task. We conclude that adding metadata improves the accuracy. © 2022 IEEE.