SQUID: Deep Feature In-Painting for Unsupervised Anomaly Detection

Abstract

Radiography imaging protocols focus on particular body regions, therefore producing images of great similarity and yielding recurrent anatomical structures across patients. To exploit this structured information, we propose the use of Space-aware Memory Queues for In-painting and Detecting anomalies from radiography images (abbreviated as SQUID). We show that SQUID can taxonomize the ingrained anatomical structures into recurrent patterns; and in the inference, it can identify anomalies (unseen/modified patterns) in the image. SQUID surpasses 13 state-of-the-art methods in unsupervised anomaly detection by at least 5 points on two chest X-ray benchmark datasets measured by the Area Under the Curve (AUC). Additionally, we have created a new dataset (DigitAnatomy), which synthesizes the spatial correlation and consistent shape in chest anatomy. We hope DigitAnatomy can prompt the development, evaluation, and interpretability of anomaly detection methods.

arXiv commentCVPR 2023

References in corpus (13)

• Auto-Encoding Variational Bayes
• Distilling the Knowledge in a Neural Network
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Categorical Reparameterization with Gumbel-Softmax
• A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks
• A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks
• Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddings
• Deep Anomaly Detection with Outlier Exposure
• Learning Confidence for Out-of-Distribution Detection in Neural Networks
• Learning to Remember Rare Events
• Anomaly Detection in Medical Imaging -- A Mini Review
• Partial Graph Reasoning for Neural Network Regularization
• Divide-and-Assemble: Learning Block-wise Memory for Unsupervised Anomaly Detection