This work from scientists at DeepMind was trained on about 14 thousand optical coherence tomography scans, this is the OCT label that you see on the the left - these images are cross sections of the human retina.

DeepMind 的科学家们对大约14000个光学相干断层扫描进行了训练，你看左边，这是OCT标签，这些图像是人类的视网膜切片。