Radiological Analysis of COVID-19 Using Computational Intelligence: A Broad Gauge Study.

Area of Science:

• Medical Imaging
• Artificial Intelligence
• Pulmonary Medicine

Background:

• The COVID-19 pandemic necessitated AI-driven solutions for disease diagnosis and management.
• Pulmonary medical image analysis, using deep learning, has shown promise in lung disease assessment.

Purpose of the Study:

• To identify and analyze COVID-19 medical imaging models.
• To discuss merits, demerits, and challenges of existing detection methodologies.
• To explore future research avenues in medical image analysis.

Main Methods:

• Review of existing literature on COVID-19 medical imaging analysis models.
• Discussion of deep learning and image processing techniques.
• Analysis of preprocessing and post-processing methods.

Main Results:

• Identified various COVID-19 detection models with their strengths and weaknesses.
• Detailed existing methodologies for diagnosis, prognosis, and severity assessment.
• Highlighted limitations of current deep learning approaches.

Conclusions:

• Deep learning offers high efficiency in medical image analysis but has limitations.
• Research on COVID-19 imaging can significantly advance pulmonary image analysis.
• Understanding AI's role is crucial for medical image interpretation.