CoviExpert: COVID-19 detection from chest X-ray using CNN

Area of Science:

• Medical Imaging and Artificial Intelligence
• Radiology and Diagnostic Tools
• Infectious Disease Detection

Background:

• COVID-19 pandemic presents significant challenges to healthcare systems globally.
• Increased demand for rapid and accessible diagnostic tools for COVID-19.
• Concerns regarding high radiation exposure and cost associated with CT scans for COVID-19 diagnosis.

Purpose of the Study:

• To develop an efficient and cost-effective method for detecting COVID-19 using Chest X-rays.
• To leverage deep learning for automated COVID-19 diagnosis.
• To provide a user-friendly tool for medical professionals to aid in rapid patient screening.

Main Methods:

• Development of a deep learning model using a Convolutional Neural Network (CNN) with Keras.
• Training the CNN model on a dataset of 1584 Chest X-ray images (COVID-19 positive and negative).
• Integration of the trained model into a software application named CoviExpert with a front-end user interface.

Main Results:

• The CoviExpert system achieved a high classification accuracy of 99% in detecting COVID-19 from Chest X-ray images.
• The model demonstrated the ability to differentiate between COVID-19 positive and negative cases effectively.
• The software provides rapid detection results within seconds.

Conclusions:

• Deep learning applied to Chest X-rays offers a promising, accurate, and efficient approach for COVID-19 detection.
• CoviExpert provides a valuable, low-radiation, and cost-effective alternative to CT scans for COVID-19 diagnosis.
• The developed tool can assist healthcare professionals in timely diagnosis and patient management during the pandemic.