Bayesian Skip-Autoencoders for Unsupervised Hyperintense Anomaly Detection in High Resolution Brain Mri

Baur C, Wiestler B, Albarqouni S, Navab N (2020)


Publication Type: Conference contribution

Publication year: 2020

Journal

Publisher: IEEE Computer Society

Book Volume: 2020-April

Pages Range: 1905-1909

Conference Proceedings Title: Proceedings - International Symposium on Biomedical Imaging

Event location: Iowa City, IA, USA

ISBN: 9781538693308

DOI: 10.1109/ISBI45749.2020.9098686

Abstract

Autoencoder-based approaches for Unsupervised Anomaly Detection (UAD) in brain MRI have recently gained a lot of attention and have shown promising performance. However, brain MR images are particularly complex and require large model capacity for learning a proper reconstruction, which existing methods encounter by restricting themselves to downsampled data or anatomical subregions. In this work, we show that models with limited capacity can be trained and used for UAD in full brain MR images at their native resolution by introducing skip-connections, a concept which has already proven beneficial for biomedical image segmentation and image-to-image translation, and a dropout-based mechanism to prevent the model from learning an identity mapping. In an ablative study on two different pathologies we show considerable improvements over State-of-the-Art Autoencoder-based UAD models. The stochastic nature of the model also allows to investigate epistemic uncertainty in our so-called Skip-Autoencoder, which is briefly portrayed.

Involved external institutions

How to cite

APA:

Baur, C., Wiestler, B., Albarqouni, S., & Navab, N. (2020). Bayesian Skip-Autoencoders for Unsupervised Hyperintense Anomaly Detection in High Resolution Brain Mri. In Proceedings - International Symposium on Biomedical Imaging (pp. 1905-1909). Iowa City, IA, USA: IEEE Computer Society.

MLA:

Baur, Christoph, et al. "Bayesian Skip-Autoencoders for Unsupervised Hyperintense Anomaly Detection in High Resolution Brain Mri." Proceedings of the 17th IEEE International Symposium on Biomedical Imaging, ISBI 2020, Iowa City, IA, USA IEEE Computer Society, 2020. 1905-1909.

BibTeX: Download