Chaotic Satin Bowerbird Optimizer Based Advanced AI Techniques for Detection of COVID-19 Diseases from CT Scans Images

Background

The SARS-CoV-2 virus, which caused the COVID-19 pandemic, emerged in late 2019, leading to significant global health challenges due to the lack of targeted treatments and the need for rapid diagnosis.

Aim/objective

This study aims to develop an AI-based system to accurately detect COVID-19 from CT scans, enhancing the diagnostic process.

Methodology

We employ a faster region-based convolutional neural network (faster R-CNN) for extracting features from pre-processed CT images and use the chaotic satin bowerbird optimization algorithm (CSBOA) for fine-tuning the model parameters.

Results

Our experimental results show high performance in terms of precision, recall, accuracy, and f-measure, effectively identifying COVID-19 affected areas in CT images. The suggested model attained 91.78% F1-score, 91.37% accuracy, 91.87% precision, and 90.3% recall with a learning rate of 0.0001.

Conclusion

This method contributes to the advancement of AI-driven diagnostic tools, providing a pathway for improved early detection and treatment strategies for COVID-19, thus aiding in better clinical management.