Deep Convolutional Neural Networks for Detecting COVID-19 Using Medical Images: A Survey

Area of Science:

• Medical Imaging Analysis
• Artificial Intelligence in Healthcare
• Infectious Disease Diagnostics

Background:

• The COVID-19 pandemic, caused by SARS-COV-2, has had a profound global impact.
• Public health measures like lockdowns and curfews were implemented to control the spread.
• Early and accurate detection of COVID-19 is crucial for effective management and treatment.

Purpose of the Study:

• To review and analyze deep learning (DL) models for COVID-19 detection using medical imaging.
• To compare different DL approaches applied to common imaging modalities.
• To identify future research directions in AI-driven COVID-19 diagnostics.

Main Methods:

• Systematic review of research studies from January 2020 to September 2022.
• Focus on deep learning models applied to X-ray, Computed Tomography (CT), and Ultrasound (US) images.
• Comparative analysis of various DL techniques and their performance in COVID-19 detection.

Main Results:

• Deep learning models demonstrate significant potential in identifying COVID-19 indicators across X-ray, CT, and US modalities.
• Various DL architectures and approaches have been explored for COVID-19 detection.
• The review synthesizes findings on the effectiveness of different DL methods.

Conclusions:

• Deep learning offers a powerful tool for the rapid and accurate detection of COVID-19 from medical images.
• Further research is needed to optimize DL models and integrate them into clinical workflows.
• AI-driven diagnostic tools can play a vital role in combating future pandemics.