The goal is to help clinicians understand what exactly COVID-19 does to the lungs and thus help develop effective treatment strategies.
“There is no labeled dataset of this level of scale and diversity out there. What we've seen is companies have rushed to the media to publish results on models that use the whole picture of an X-ray and perform classification. The problem is that the differences between images of healthy lungs and those affected by COVID-19 can be spotted by the naked eye. Our goal is to find visual characteristics that would otherwise not be picked up.” Alberto Rizzoli, V7 CEO
Access the COVID-19 dataset on GitHub.
Read the full story here: V7 Labs & CloudFactory Release Annotated X-Ray Dataset to Aid in COVID-19 Research