Context-encoding Variational Autoencoder for Unsupervised Anomaly Detection

Abstract

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 shortcomings 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.

References in corpus (5)

• Stochastic Backpropagation and Approximate Inference in Deep Generative Models
• SmoothGrad: removing noise by adding noise
• Sanity Checks for Saliency Maps
• Deep Autoencoding Models for Unsupervised Anomaly Segmentation in Brain MR Images
• Deep Generative Models in the Real-World: An Open Challenge from Medical Imaging

Cited by in corpus (12)

• Deep Learning in Medical Image Registration: A Review
• Dual-distribution discrepancy with self-supervised refinement for anomaly detection in medical images
• Encoding Structure-Texture Relation with P-Net for Anomaly Detection in Retinal Images
• Brain Tumor Anomaly Detection via Latent Regularized Adversarial Network
• Unsupervised Anomaly Segmentation using Image-Semantic Cycle Translation
• Evaluation of pseudo-healthy image reconstruction for anomaly detection with deep generative models: Application to brain FDG PET
• Synomaly Noise and Multi-Stage Diffusion: A Novel Approach for Unsupervised Anomaly Detection in Medical Images
• Simple statistical methods for unsupervised brain anomaly detection on MRI are competitive to deep learning methods
• SincVAE: A new semi-supervised approach to improve anomaly detection on EEG data using SincNet and variational autoencoder
• InstantGroup: Instant Template Generation for Scalable Group of Brain MRI Registration
• Evaluating the Use of Reconstruction Error for Novelty Localization
• OLED: One-Class Learned Encoder-Decoder Network with Adversarial Context Masking for Novelty Detection