# Anomaly Detection for Skin Disease Images Using Variational Autoencoder

arXiv: https://arxiv.org/abs/1807.01349 · HTML: https://mlsanity.com/paper/1807.01349/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Jul 2018.

## Built on by (most cited first, 20 of 20)

- [Inpainting Transformer for Anomaly Detection](https://mlsanity.com/paper/2104.13897/) (2021)
- [Anomaly Detection with Conditioned Denoising Diffusion Models](https://mlsanity.com/paper/2305.15956/) (2023)
- [Autoencoding Under Normalization Constraints](https://mlsanity.com/paper/2105.05735/) (2021)
- [MedIAnomaly: A comparative study of anomaly detection in medical images](https://mlsanity.com/paper/2404.04518/) (2024)
- [Out-of-distribution Detection in Medical Image Analysis: A survey](https://mlsanity.com/paper/2404.18279/) (2024)
- [Evaluation of pseudo-healthy image reconstruction for anomaly detection with deep generative models: Application to brain FDG PET](https://mlsanity.com/paper/2401.16363/) (2024)
- [Can self-training identify suspicious ugly duckling lesions?](https://mlsanity.com/paper/2105.07116/) (2021)
- [Statistical Test for Anomaly Detections by Variational Auto-Encoders](https://mlsanity.com/paper/2402.03724/) (2024)
- [Scale-Aware Contrastive Reverse Distillation for Unsupervised Medical Anomaly Detection](https://mlsanity.com/paper/2503.13828/) (2025)
- [Assessing Dataset Bias in Computer Vision](https://mlsanity.com/paper/2205.01811/) (2022)
- [Anomaly Detection for Solder Joints Using β-VAE](https://mlsanity.com/paper/2104.11927/) (2021)
- [Positive Difference Distribution for Image Outlier Detection using Normalizing Flows and Contrastive Data](https://mlsanity.com/paper/2208.14024/) (2022)
- [Frequency-Guided Multi-Level Human Action Anomaly Detection with Normalizing Flows](https://mlsanity.com/paper/2404.17381/) (2024)
- [Discrepancy-based Diffusion Models for Lesion Detection in Brain MRI](https://mlsanity.com/paper/2405.04974/) (2024)
- [Exploring the Intrinsic Probability Distribution for Hyperspectral Anomaly Detection](https://mlsanity.com/paper/2105.06775/) (2021)
- [Joint Embedding of 2D and 3D Networks for Medical Image Anomaly Detection](https://mlsanity.com/paper/2212.10939/) (2022)
- [Technical outlier detection via convolutional variational autoencoder for the ADMANI breast mammogram dataset](https://mlsanity.com/paper/2305.12068/) (2023)
- [Multiresolution Feature Guidance Based Transformer for Anomaly Detection](https://mlsanity.com/paper/2305.14880/) (2023)
- [Latent Space Analysis for Interpretable Uncertainty in Melanoma Classification](https://mlsanity.com/paper/2506.18414/) (2025)
- [MaRS: Robust Out-of-Distribution Detection via Mahalanobis Residual Scoring](https://mlsanity.com/paper/2606.22649/) (2026)

## Abstract (arXiv)

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.