Anomaly Detection for Skin Disease Images Using Variational Autoencoder

TL;DR

This paper explores using Variational Autoencoders to detect anomalies in skin disease images, achieving high accuracy in identifying specific conditions like melanoma and actinic keratosis, marking a novel application in dermatology.

Contribution

It introduces the first application of deep generative models for anomaly detection in dermatology, demonstrating effective detection of various skin diseases using VAE.

Findings

Achieved 0.779 AUCROC for overall disease detection

Detected melanoma with 0.864 AUCROC

Detected actinic keratosis with 0.872 AUCROC

Abstract

In this paper, we demonstrate the potential of applying Variational Autoencoder (VAE) [10] for anomaly detection in skin disease images. VAE is a class of deep generative models which is trained by maximizing the evidence lower bound of data distribution [10]. When trained on only normal data, the resulting model is able to perform efficient inference and to determine if a test image is normal or not. We perform experiments on ISIC2018 Challenge Disease Classification dataset (Task 3) and compare different methods to use VAE to detect anomaly. The model is able to detect all diseases with 0.779 AUCROC. If we focus on specific diseases, the model is able to detect melanoma with 0.864 AUCROC and detect actinic keratosis with 0.872 AUCROC, even if it only sees the images of nevus. To the best of our knowledge, this is the first applied work of deep generative models for anomaly detection in dermatology.