They created a neural network, with multiple layers of processing, and trained it by giving it many CT scans from patients whose diagnoses were known: Some had lung cancer, some did not and some had nodules that later turned cancerous. “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. Pitted against six expert radiologists, when no prior scan was available, the deep learning model beat the doctors: It had fewer false positives and false negatives. Given the high rate of false positives and false negatives on the lung scans as currently performed, he said, “Lung CT for smokers, it’s so bad that it’s hard to make it worse.”

Source: New York Times May 20, 2019 15:00 UTC