COVID-opt-aiNet

COVID-opt-aiNet applies optimized artificial immune networks (opt-aiNet) combined with deep learning to select features from medical imaging and classify COVID-19 cases from chest X-ray images to support diagnostic decision-making.

Key Features:

• Ensemble learning approach: Integrates opt-aiNet feature selection with multiple machine learning algorithms including deep neural networks (DNN), convolutional neural networks (CNN), bidirectional long-short-term memory networks, support vector machines (SVM), and logistic regression for image-based COVID-19 prediction.
• Optimized feature selection (opt-aiNet): Uses artificial immune network optimization to select discriminative features from medical imaging data.
• Reported classification accuracy: Empirical results report up to 98%–99% accuracy for SVM, 96%–97% for DNN, and approximately 70.85%–71% for CNN on chest X-ray datasets.
• Adaptability to imaging modalities: Designed to operate on various medical imaging modalities for COVID-19 detection.
• Statistical validation: Employs rigorous statistical analysis to validate algorithm performance.

Scientific Applications:

• Clinical diagnosis: Supports image-based diagnosis and differentiation of COVID-19 from other conditions using chest X-ray images.
• Patient management: Aids healthcare professionals in informing patient management and treatment decisions based on imaging classification.
• Large-scale image analysis: Enables processing of large medical imaging datasets to provide timely detection during the COVID-19 pandemic.

Methodology:

Optimizes feature selection using artificial immune networks (opt-aiNet), integrates selected features into machine learning models (DNN, CNN, bidirectional long-short-term memory networks, SVM, logistic regression), applies ensemble learning, and conducts statistical validation.