2019/07/29 by David Zimmerer, Simon Kohl, Zimmerer, David +9
Computer Science · Engineering · Medicine · #Anomaly (physics) #Anomaly Detection Techniques and Applications #Anomaly detection #Artificial intelligence #Artificial neural network #Autoencoder #COVID-19 diagnosis using AI #Computer science #Context (archaeology) #Encoding (memory) #FOS: Electrical engineering #Geography #Image and Video Processing (eess.IV) #Network Security and Intrusion Detection #Pattern recognition (psychology) #Physics #eess.IV #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.1907.12258
published in arXiv (Cornell University) (Cornell University) · MIDL 2019 [arXiv:1907.08612]
openalex publication_date 2019/07/29 · arxiv created 2020/01/01 · arxiv updated 2020/01/03 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
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.