Context-encoding Variational Autoencoder for Unsupervised Anomaly Detection [article]

David Zimmerer, Simon A. A. Kohl, Jens Petersen, Fabian Isensee, Klaus H. Maier-Hein
2018 arXiv   pre-print
Unsupervised learning can leverage large-scale data sources without the need for annotations. In this context, deep learning-based auto encoders have shown great potential in detecting anomalies in medical images. However, state-of-the-art anomaly scores are still based on the reconstruction error, which lacks in two essential parts: it ignores the model-internal representation employed for reconstruction, and it lacks formal assertions and comparability between samples. We address these
more » ... mings by proposing the Context-encoding Variational Autoencoder (ceVAE) which combines reconstruction- with density-based anomaly scoring. This improves the sample- as well as pixel-wise results. In our experiments on the BraTS-2017 and ISLES-2015 segmentation benchmarks, the ceVAE achieves unsupervised ROC-AUCs of 0.95 and 0.89, respectively, thus outperforming state-of-the-art methods by a considerable margin.
arXiv:1812.05941v1 fatcat:xnellrlzo5g6tdnj3nhr5jzgva