English

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

Image and Video Processing 2020-01-03 v2

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.

Keywords

Cite

@article{arxiv.1907.12258,
  title  = {Context-encoding Variational Autoencoder for Unsupervised Anomaly Detection -- Short Paper},
  author = {David Zimmerer and Simon Kohl and Jens Petersen and Fabian Isensee and Klaus Maier-Hein},
  journal= {arXiv preprint arXiv:1907.12258},
  year   = {2020}
}

Comments

MIDL 2019 [arXiv:1907.08612]

R2 v1 2026-06-23T10:33:28.070Z