Artificial Intelligence Based COVID-19 Detection and Classification Model on Chest X-ray Images.

Area of Science:

• Medical Imaging and Artificial Intelligence
• Infectious Disease Diagnostics
• Computational Health

Background:

• Accurate and timely diagnosis of COVID-19 is crucial for disease control and reducing mortality.
• Chest X-ray (CXR) imaging offers a rapid, cost-effective, and accessible method for COVID-19 diagnosis.
• While effective, CXR interpretation requires expert analysis, highlighting the need for automated solutions.

Purpose of the Study:

• To develop and evaluate an automated deep learning (DL) based system for COVID-19 detection and classification using CXR images.
• To introduce a novel Sine Cosine Optimization with Deep Learning-based Disease Detection and Classification (SCODL-DDC) technique.
• To enhance diagnostic accuracy and efficiency in identifying COVID-19 from radiological scans.

Main Methods:

• The proposed SCODL-DDC technique utilizes the EfficientNet model for feature extraction from CXR images.
• Hyperparameter optimization for EfficientNet is performed using the Sine Cosine Optimization (SCO) algorithm.
• A Quantum Neural Network (QNN) model is employed for accurate COVID-19 classification, with parameters optimized by the Equilibrium Optimizer (EO).

Main Results:

• The SCODL-DDC technique demonstrated superior performance in detecting and classifying COVID-19 from CXR images compared to existing methods.
• The integration of SCO for hyperparameter tuning and EO for QNN parameter optimization led to enhanced diagnostic accuracy.
• The study validates the effectiveness of AI-driven approaches in medical image analysis for infectious diseases.

Conclusions:

• The SCODL-DDC technique presents a highly effective and automated approach for COVID-19 diagnosis using CXR images.
• The proposed method offers a promising tool for healthcare professionals to improve early detection and management of COVID-19.
• This AI-powered diagnostic system has the potential to significantly impact public health strategies during pandemics.