Deep learning
A kind of machine learning that uses layered neural networks to learn patterns from large amounts of data, such as millions of medical images. It is what made image-based AI like diabetic retinopathy screening work.
A diabetic eye screening program adopts a deep learning model that grades retinal photographs for referable retinopathy. Because the model learned its own features from the raw pixels, the program cannot list which signs it relies on, and a heatmap shows where it looked without saying what it saw there. When a community clinic switches to a new fundus camera, referrals from that site jump. Treat any change of camera or image settings as a trigger to have a sample of the new photos graded by people and compared with the model's grades before relying on it at that site.
Terms like this come up in real clinical scenarios across the HelloAI courses: bite-sized modules with verifiable certificates. An account takes one minute, no password needed.
Sign in →