In this article of the New York Times, you can find a presentation of a study on lung cancer CT scans and how AI could help to detect specific nodules. With 6716 cases for the training set, the model shows more than 90% of success with “reductions of 11% in false positives and 5% in false negatives”. You note that Google team are deeply involved in this study.
“The whole experimentation process is like a student in school,” Dr. Tse said. “We’re using a large data set for training, giving it lessons and pop quizzes so it can begin to learn for itself what is cancer, and what will or will not be cancer in the future. We gave it a final exam on data it’s never seen after we spent a lot of time training, and the result we saw on final exam — it got an A.”