An Efficient Method for Coronavirus Detection Through X-rays Using Deep Neural Network.

Area of Science:

• Medical Imaging
• Artificial Intelligence
• Infectious Diseases

Background:

• Coronavirus disease (COVID-19) presents a spectrum of respiratory illnesses, ranging from mild to lethal.
• Severe cases disproportionately affect the elderly and individuals with pre-existing conditions like diabetes and cardiovascular disease.
• Limited availability of COVID-19 test kits necessitates alternative diagnostic solutions to curb transmission.

Purpose of the Study:

• To propose a deep learning model for automated COVID-19 detection.
• To classify patients as infected or healthy based on chest X-ray images.

Main Methods:

• Development of a fully connected convolutional neural network (CNN) model.
• The CNN architecture includes seven convolutional layers, rectified linear unit activation, and max-pooling.
• Training and validation were performed on a publicly available dataset of chest X-ray radiographs.

Main Results:

• The proposed CNN model achieved a high accuracy of 98.07% in classifying COVID-19 positive and normal cases.
• Performance was evaluated using metrics including precision, recall, Mean Squared Error (MSE), and Root Mean Squared Error (RMSE).

Conclusions:

• Deep learning models can effectively classify COVID-19 from chest X-rays.
• The developed automated system shows promise as an immediate diagnostic tool.
• This approach can aid in controlling the spread of COVID-19.