AI- Iterative Quality Control Strategies for Expert Medical Image Labeling (Google Health)

#AI #Health #Labeling

In this talk,  Beverly Freeman, Google user experience researcher,  explores the challenges of collecting high-quality training data from medical experts for the development of artificial intelligence solutions for disease detection. Drawing from interviews with AI practitioners and domain experts in ophthalmology, radiology, pathology, and dermatology, this talk describes the collaborative and iterative strategies that help teams identify and address issues before they proliferate. The key lesson learned in this research is "An ounce of prevention is worth a pound of cure."