# Context-encoding Variational Autoencoder for Unsupervised Anomaly Detection -- Short Paper

## TL;DR

This paper introduces the context-encoding Variational Autoencoder (ceVAE), a novel unsupervised model that enhances anomaly detection in medical images by capturing high-level data structures, outperforming existing methods on benchmark datasets.

## Contribution

The paper proposes the ceVAE, which improves high-level structure modeling in VAEs for unsupervised anomaly detection in medical imaging.

## Key findings

- Achieves AUROC of 0.95 on BraTS-2017
- Achieves AUROC of 0.89 on ISLES-2015
- Outperforms existing deep-learning approaches

## Abstract

Unsupervised learning can leverage large-scale data sources without the need for annotations. In this context, deep learning-based autoencoders have shown great potential in detecting anomalies in medical images. However, especially Variational Autoencoders (VAEs)often fail to capture the high-level structure in the data. We address these shortcomings by proposing the context-encoding Variational Autoencoder (ceVAE), which improves both, the sample, as well as pixelwise results. In our experiments on the BraTS-2017 and ISLES-2015 segmentation benchmarks the ceVAE achieves unsupervised AUROCs of 0.95 and 0.89, respectively, thus outperforming other reported deep-learning based approaches.