Supervised classification of Dermatological diseases by Deep neural networks

Sourav Mishra, Toshihiko Yamasaki, Hideaki Imaizumi, Hiromi Hirano

Published 2018-02-11Version 1

This paper introduces a deep learning based classifier for common skin ailments, to help people without easy access to dermatologists. We have confirmed that it can classify at approximately 80% accuracy on average, when primary care doctors are reported to have 53% success as per recent literature. Dermatological diseases are common in every population and have a wide spectrum in severity. With a shortage of dermatological experts being observed in many countries, machine learning solutions can offer timely medical advice regarding existence of common skin diseases. The paper implements supervised classification of nine distinct dermatological diseases which have high occurrence in East Asian countries. Our current attempt establishes that deep learning based techniques are viable avenues for preliminary information.