If you have the same intuition like me, you check the first three points, but not the fourth one. But it turns out, in our data, some dermatologists had taken specific instances of skin diseases and edit yellow markers into the images for sizing and the neural network could have perfectly classified that specific disease by becoming a yellow marker detector. So, finding in our data set of 130,000 images, those images with yellow markers, even having the idea that might exist in there, that took months for us to do.