Machine Learning (ML) same image different dermatology answer (diagnosis)
Here are two examples of cases that have been verified by dermatologists on the skin diagnosis. However when we upload the images to our machine learning (ML) image recognition algorithm we get different answers when we turn the images around, 90 and 180 respectfully. This is an important observation about our algorithm that we probably do not have sufficient images. However they have all been annotated, so a trick here is to upload the images to our deep convoluted neural network (CNN), with the images turned 90 and 180 degrees.
Ask a Dermatologist
Anonymous, fast and secure!
The Specialist doctor from the University Hospital in Gothenburg, alumnus UC Berkeley. My doctoral dissertation is about Digital Health and I have published 5 scientific articles in teledermatology and artificial intelligence and others.