Machine Learning with Quantum Seagull Optimization Model for COVID-19 Chest X-Ray Image Classification

Area of Science:

• Medical Imaging
• Artificial Intelligence
• Computational Biology

Background:

• Early and accurate COVID-19 detection is crucial for controlling disease spread and mortality.
• Chest X-ray (CXR) imaging is a vital, accessible tool for diagnosing COVID-19 due to its respiratory system targeting.
• Artificial Intelligence (AI) and deep learning (DL) offer automated diagnostic solutions using CXR.

Purpose of the Study:

• To introduce a novel AI model for COVID-19 detection and classification using CXR images.
• To enhance diagnostic accuracy through optimized deep learning models.
• To leverage advanced optimization algorithms for improved medical image analysis.

Main Methods:

• Development of the Quantum Seagull Optimization Algorithm with DL-based COVID-19 diagnosis (QSGOA-DL) technique.
• Utilizing EfficientNet-B4 as a feature extractor for CXR images.
• Employing the Quantum Seagull Optimization Algorithm (QSGOA) for hyperparameter optimization and a multilayer extreme learning machine (MELM) for classification.

Main Results:

• The QSGOA-DL technique demonstrated promising performance in detecting and classifying COVID-19 from CXR images.
• Simulation results on a benchmark CXR dataset showed superior effectiveness compared to existing methods.
• The study highlights the successful application of QSGOA for optimizing EfficientNet-B4 hyperparameters.

Conclusions:

• The proposed QSGOA-DL technique offers an effective AI-driven solution for automated COVID-19 diagnosis via CXR.
• Optimizing DL models with advanced algorithms like QSGOA can significantly improve diagnostic accuracy.
• This approach holds potential for rapid and reliable screening of COVID-19 in clinical settings.