Unsupervised Anomaly Detection in MR Images using Multi-Contrast Information

TL;DR

This paper presents an unsupervised pixel-wise anomaly detection method for multi-contrast MRI that leverages contrast translation and density estimation, outperforming previous approaches without requiring labeled anomalies.

Contribution

The paper introduces a novel unsupervised framework combining contrast translation and Gaussian mixture modeling for effective anomaly detection in multi-contrast MRI.

Findings

Outperforms previous anomaly detection methods

Effective in identifying anomalies in multi-contrast MRI

Handles singularity issues in density estimation

Abstract

Anomaly detection in medical imaging is to distinguish the relevant biomarkers of diseases from those of normal tissues. Deep supervised learning methods have shown potentials in various detection tasks, but its performances would be limited in medical imaging fields where collecting annotated anomaly data is limited and labor-intensive. Therefore, unsupervised anomaly detection can be an effective tool for clinical practices, which uses only unlabeled normal images as training data. In this paper, we developed an unsupervised learning framework for pixel-wise anomaly detection in multi-contrast magnetic resonance imaging (MRI). The framework has two steps of feature generation and density estimation with Gaussian mixture model (GMM). A feature is derived through the learning of contrast-to-contrast translation that effectively captures the normal tissue characteristics in multi-contrast MRI. The feature is collaboratively used with another feature that is the low-dimensional representation of multi-contrast images. In density estimation using GMM, a simple but efficient way is introduced to handle the singularity problem which interrupts the joint learning process. The proposed method outperforms previous anomaly detection approaches. Quantitative and qualitative analyses demonstrate the effectiveness of the proposed method in anomaly detection for multi-contrast MRI.