FocusCovid: automated COVID-19 detection using deep learning with chest X-ray images

Area of Science:

• Medical Imaging
• Artificial Intelligence
• Infectious Diseases

Background:

• Coronavirus disease 2019 (COVID-19), initially 2019-nCoV and later SARS-CoV-2, was declared a pandemic by the WHO in January 2020.
• The escalating number of COVID-19 cases strains medical infrastructure, necessitating efficient diagnostic tools.
• Medical imaging, including Computed Tomography (CT) and chest radiography, is crucial for early screening and detection of COVID-19.

Purpose of the Study:

• To propose a deep convolutional neural network (CNN) architecture for automated COVID-19 detection.
• To leverage chest radiographs for accurate and rapid identification of COVID-19 cases.
• To explore the role of Artificial Intelligence (AI) in alleviating the burden on healthcare systems during the pandemic.

Main Methods:

• Development of a deep convolutional neural network-based model.
• Training and testing the model using a dataset of chest radiographs from public repositories.
• Evaluation of the model's performance in detecting COVID-19.

Main Results:

• The proposed deep convolutional neural network achieved high accuracy in detecting COVID-19 from chest radiographs.
• The AI model demonstrates potential for efficient screening and early case identification.
• The study highlights the utility of AI in supporting medical imaging diagnostics for infectious diseases.

Conclusions:

• Deep learning models, specifically CNNs, show significant promise for COVID-19 detection using chest radiography.
• AI-assisted diagnosis can enhance the efficiency of medical infrastructure in managing public health crises.
• Clinical decisions regarding COVID-19 diagnosis must remain in consultation with trained medical professionals.