Blemish Types, Skin Cancer ID

Description

More than 600 hours of processing time invested in training and improving the neural networks.

Identify different types of benign & malignant spots in the skin, just by taking a photo or uploading an image (ATTENTION: CONSULT A CERTIFIED DERMATOLOGIST FOR A MORE RELIABLE DIAGNOSIS).
If you decide to use this app, it is highly recommended to load a photo made with a dermatoscope as regular pictures don't show small details (YOU SHALL USE IMAGES OBTAINED WITH A DERMATOSCOPE TO GET MORE ACCURATE RESULTS).

Resulting validation general accuracy: 70.5% (note that a random result will obtain 12.5% accuracy given the 8-categories identification; in a basic Melanoma-Not Melanoma model it's 50.0%, which is not the case; also the model was trained with 5 different levels of detail instead of 1, which reduces bias but it results in lower validation accuracy).