Related Experiment Video
Updated: Aug 14, 2025
04:17
DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning
Published on: May 10, 2024
842
Utilisation of deep learning for COVID-19 diagnosis
1Centre for Medical Image Computing and Department of Respiratory Medicine, University College London, London, UK.
Clinical Radiology
|January 13, 2023
Summary
This review examines artificial intelligence (AI) deep learning techniques for diagnosing COVID-19 using medical imaging. It highlights how AI methods detect the virus and notes limitations in current approaches.
Area of Science:
- Medical Imaging Analysis
- Artificial Intelligence in Healthcare
- Infectious Disease Diagnostics
Background:
- The COVID-19 pandemic has caused significant global mortality and long-term health consequences.
- Computer analysis of medical data, particularly deep learning (AI), has become crucial in pandemic research.
- Chest radiography and computed tomography are key imaging modalities for COVID-19 assessment.
Purpose of the Study:
- To review deep-learning-based AI techniques for COVID-19 diagnosis.
- To analyze the application of AI in interpreting chest radiography and computed tomography for COVID-19 detection.
- To identify and discuss limitations of current AI methods in COVID-19 diagnosis.
Main Methods:
- Systematic review of 30 papers published between February 2020 and March 2022.
- Focus on studies utilizing 2D/3D deep convolutional neural networks with transfer learning.
- Analysis of AI methodologies for COVID-19 detection in medical images.
Main Results:
- Deep learning models show promise in detecting COVID-19 from chest imaging.
- Transfer learning combined with convolutional neural networks is a common approach.
- Several limitations were identified in the reviewed deep learning methods.
Conclusions:
- Deep learning offers valuable tools for AI-driven COVID-19 diagnosis from medical images.
- Further research is needed to address the limitations of current AI techniques.
- Advancements in AI can improve the accuracy and efficiency of COVID-19 detection.
