SQUID: Deep Feature In-Painting for Unsupervised Anomaly Detection
This addresses the problem of detecting anomalies in medical images for healthcare applications, representing a strong specific gain rather than a foundational advancement.
The paper tackles unsupervised anomaly detection in radiography images by proposing SQUID, a method that uses space-aware memory queues for in-painting to identify anomalies, achieving at least a 5-point AUC improvement over 13 state-of-the-art methods on two chest X-ray benchmarks.
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.