COVID-Net Update: More data, New models

Dear Colleague,

The response to our release of COVID-Net continues to move and inspire us.

Here are the latest updates with the project:

1. Thanks to the continued support of the global community, the total number of COVID-19 positive cases in the COVIDx dataset has grown significantly, with the test benchmark set now more than 3x larger than the last release. This makes COVIDx one of the largest open-access benchmark datasets in terms of number of COVID-19 positive cases. Instructions and scripts on generating this latest collection are available on our GitHub repo. We’d especially like to thank Figure 1, Actualmed, and researchers at Universitat Jaume I for their support on this front.
2. We were co-authors of an important study conducted on COVID-Net neural networks for COVID-19 lung disease severity assessment. The study can be found here. We would especially like to thank Dr. Timothy Q. Duong, Dr. Beiyi Shen, MD, Dr. Almas Abbasi, MD, and Dr. Mahsa Hoshmand-Kochi, MD at Stony Brook School of Medicine.
3. We’ve released three new models based on the dataset above: COVIDNet-CXR3-A, COVIDNet-CXR3-B, and COVIDNet-CXR3-C. Each model was built using our GenSynth platform with varying performance/efficiency tradeoffs, and are smaller, higher-resolution, and higher-performing than our previously released COVID-Net models. All three models are available at the GitHub repo.
   Again, our intention is to provide these models as reference models to build upon and improve as new data becomes available and to drive model improvements and innovations. They are not, at present, production-ready models, and we intend on improving them over time and making improvements publicly accessible.
4. Finally, our team is also hard at work on COVID-Net-Risk, a neural network tailored for COVID-19 risk stratification. The goal with COVID-Net-Risk is to provide greater insights into risk level and severity to assist caregivers with triage and treatment plans.

Finally, if you’re a researcher or clinician and would like access to our explainability platform to assist with this project and gain transparency or have data to share, please email us at info@darwinai.ca.

In Solidarity,

The DarwinAI team