COVID-19 identification in chest X-ray images using intelligent multi-level classification scenario

Area of Science:

• Medical Imaging
• Artificial Intelligence
• Computational Biology

Background:

• COVID-19 pandemic necessitates rapid and accurate diagnostic tools.
• Chest X-rays are crucial for assessing respiratory diseases, including COVID-19.
• Artificial Intelligence (AI) offers potential for enhancing diagnostic capabilities.

Purpose of the Study:

• To develop an AI model for early detection of COVID-19 using chest X-ray images.
• To evaluate the efficacy of a novel Genetic Deep Learning Convolutional Neural Network (GDCNN) architecture.
• To utilize Huddle Particle Swarm Optimization (PSO) as an alternative to traditional gradient descent methods.

Main Methods:

• Proposed a Genetic Deep Learning Convolutional Neural Network (GDCNN) architecture.
• Integrated Huddle Particle Swarm Optimization (PSO) for model training.
• Trained the model on publicly available chest X-ray datasets to identify pneumonia and COVID-19.

Main Results:

• The GDCNN with Huddle PSO achieved high performance metrics.
• Achieved an accuracy of 97.23%, sensitivity of 98.62%, specificity of 97.0%, and precision of 93.0%.
• Demonstrated the model's effectiveness in identifying pneumonia and COVID-19 from X-ray images.

Conclusions:

• The proposed AI model facilitates earlier detection of COVID-19.
• GDCNN with Huddle PSO shows promise as a low-cost tool for healthcare professionals.
• Future work includes applying the model to larger datasets for broader lung disease prediction.