This repository serves as a curated collection of research papers, datasets, and challenges related to Artificial Intelligence (AI) in medical imaging for COVID-19 diagnosis and analysis. It targets researchers, engineers, and medical professionals interested in leveraging AI for understanding and combating the pandemic through imaging data. The primary benefit is a centralized, up-to-date resource for staying abreast of the rapidly evolving field.

How It Works

The collection is organized into categories: Survey and comments, Datasets, Imaging-based Clinical Papers, and AI-related Technical Papers. Technical papers are further sub-categorized by imaging modality (CT-based, CXR-based, Other imaging methods). It links to preprints, published articles, and relevant datasets, providing DOIs and arXiv links for easy access.

Quick Start & Requirements

This is a curated list, not a software package. No installation or specific requirements are needed beyond a web browser to access the linked resources.

Highlighted Details

• Comprehensive coverage of AI applications in COVID-19 imaging, including CT, X-ray, and ultrasound.
• Links to numerous datasets and challenges, facilitating reproducible research.
• Includes a significant number of preprints, offering early access to cutting-edge research.
• Organized by imaging modality and AI technique, allowing targeted exploration.

Maintenance & Community

The repository was last updated on 25/05/2021. It is contributed to by Huazhu Fu, Deng-Ping Fan, Geng Chen, and Tao Zhou. Contact information is provided for recommendations and suggestions.

Licensing & Compatibility

The repository itself is hosted on GitHub, implying a standard MIT license for the repository's code/structure. However, the linked papers and datasets are subject to their respective licenses and terms of use.

Limitations & Caveats

The collection includes preprints, which are preliminary reports not yet peer-reviewed and should be treated with caution regarding clinical application. The last update was in May 2021, meaning it may not reflect the most recent advancements in the field.