Towards Universal Unsupervised Anomaly Detection in Medical Imaging

TL;DR

This paper presents Reversed Auto-Encoders, a novel unsupervised method for anomaly detection in medical imaging that effectively identifies a wide range of pathologies across multiple imaging modalities.

Contribution

Introduction of Reversed Auto-Encoders, a new unsupervised approach that improves anomaly detection across diverse medical imaging data compared to existing methods.

Findings

Outperforms state-of-the-art in anomaly detection accuracy

Effective across MRI, X-ray, and pediatric wrist images

Enhances detection of diverse and unknown pathologies

Abstract

The increasing complexity of medical imaging data underscores the need for advanced anomaly detection methods to automatically identify diverse pathologies. Current methods face challenges in capturing the broad spectrum of anomalies, often limiting their use to specific lesion types in brain scans. To address this challenge, we introduce a novel unsupervised approach, termed \textit{Reversed Auto-Encoders (RA)}, designed to create realistic pseudo-healthy reconstructions that enable the detection of a wider range of pathologies. We evaluate the proposed method across various imaging modalities, including magnetic resonance imaging (MRI) of the brain, pediatric wrist X-ray, and chest X-ray, and demonstrate superior performance in detecting anomalies compared to existing state-of-the-art methods. Our unsupervised anomaly detection approach may enhance diagnostic accuracy in medical imaging by identifying a broader range of unknown pathologies. Our code is publicly available at: \url{https://github.com/ci-ber/RA}.