3D Reasoning for Unsupervised Anomaly Detection in Pediatric WbMRI

TL;DR

This paper introduces a 3D-aware generative model for unsupervised anomaly detection in pediatric whole-body MRI, demonstrating improved accuracy by leveraging spatial context and patient-specific data.

Contribution

It proposes a novel multi-channel sliding window generative model that incorporates 3D context and patient features for enhanced anomaly detection in wbMRI.

Findings

Significant performance improvement over slice-wise methods

3D reasoning is crucial for accurate anomaly detection

Including patient-specific features further boosts detection accuracy

Abstract

Modern deep unsupervised learning methods have shown great promise for detecting diseases across a variety of medical imaging modalities. While previous generative modeling approaches successfully perform anomaly detection by learning the distribution of healthy 2D image slices, they process such slices independently and ignore the fact that they are correlated, all being sampled from a 3D volume. We show that incorporating the 3D context and processing whole-body MRI volumes is beneficial to distinguishing anomalies from their benign counterparts. In our work, we introduce a multi-channel sliding window generative model to perform lesion detection in whole-body MRI (wbMRI). Our experiments demonstrate that our proposed method significantly outperforms processing individual images in isolation and our ablations clearly show the importance of 3D reasoning. Moreover, our work also shows that it is beneficial to include additional patient-specific features to further improve anomaly detection in pediatric scans.