Medical Diagnostics

The medical diagnostic process is inherently difficult. There are thousands of known diseases but only a relatively small number of possible symptoms. Diagnosis takes time, often requiring multiple lab tests and there’s plenty of opportunity for unintentional errors. Medical computer vision models are changing that by providing healthcare workers with real-time insights that drive better outcomes.

CloudFactory works closely with clients to understand medical use cases and develop training materials that help our teams execute on highly-technical tasks.

Aiding in COVID-19 Research

V7 Labs wanted to apply their machine learning expertise to lung images to help researchers study COVID-19 and, eventually, help clinicians spot and triage more serious cases earlier. They partnered with CloudFactory to create an open source dataset that could be used to help researchers understand both COVID-19 and other lung conditions going forward.

CloudFactory used a combination of V7 Darwin’s auto-labeling tool and human-refined segmentation annotations to create a lung dataset that helps eliminate age bias in pulmonary research and ML training
Over 6,000 chest x-rays were annotated to create a dataset that’s now freely available on GitHub and V7 Labs’ website.
The models have successfully identified COVID-19 and other lung ailments during preliminary tests but their efficacy will need to be confirmed through official clinical tests.