A COMPARATIVE STUDY OF X-RAY AND CT IMAGES IN COVID-19 DETECTION USING IMAGE PROCESSING AND DEEP LEARNING TECHNIQUES

Area of Science:

• Medical Imaging
• Artificial Intelligence
• Infectious Diseases

Background:

• The COVID-19 pandemic has severely impacted global health systems.
• Early diagnosis is critical for disease containment and patient management.
• Medical imaging combined with AI shows promise for rapid and accurate detection.

Purpose of the Study:

• To review recent deep learning techniques for COVID-19 diagnosis using medical images.
• To summarize the role of Convolutional Neural Networks (CNNs) in this field.
• To provide insights for future research in AI-driven diagnostics.

Main Methods:

• Review of recent research articles on deep learning for COVID-19 detection.
• Focus on Convolutional Neural Networks (CNNs) as a primary deep learning algorithm.
• Discussion of image pre-processing, transfer learning, and data augmentation.

Main Results:

• Convolutional Neural Networks (CNNs) are the most prevalent deep learning models for COVID-19 detection from medical images.
• Techniques like pre-processing, transfer learning, and data augmentation are essential for effective model performance.
• Pre-trained models can accelerate the development process.

Conclusions:

• Deep learning, especially CNNs, significantly enhances the speed and accuracy of COVID-19 diagnosis from medical images.
• Addressing data scarcity through augmentation and transfer learning is crucial.
• Further development of CNN models holds promise for early disease detection.