Localizing Anomalies via Multiscale Score Matching Analysis

TL;DR

This paper presents Spatial-MSMA, an unsupervised multiscale score matching method that effectively localizes anomalies in brain MRIs by incorporating spatial information, outperforming existing techniques in detection and segmentation accuracy.

Contribution

The paper introduces Spatial-MSMA, a novel unsupervised approach that integrates spatial context into multiscale score matching for improved anomaly localization in volumetric medical images.

Findings

Spatial-MSMA outperforms existing methods in lesion detection and segmentation.

The model achieves high accuracy in distance-based and component-wise metrics.

Code is publicly available for reproducibility and further research.

Abstract

Anomaly detection and localization in medical imaging remain critical challenges in healthcare. This paper introduces Spatial-MSMA (Multiscale Score Matching Analysis), a novel unsupervised method for anomaly localization in volumetric brain MRIs. Building upon the MSMA framework, our approach incorporates spatial information and conditional likelihoods to enhance anomaly detection capabilities. We employ a flexible normalizing flow model conditioned on patch positions and global image features to estimate patch-wise anomaly scores. The method is evaluated on a dataset of 1,650 T1- and T2-weighted brain MRIs from typically developing children, with simulated lesions added to the test set. Spatial-MSMA significantly outperforms existing methods, including reconstruction-based, generative-based, and interpretation-based approaches, in lesion detection and segmentation tasks. Our model achieves superior performance in both distance-based metrics (99th percentile Hausdorff Distance: $7.05 \pm 0.61$, Mean Surface Distance: $2.10 \pm 0.43$) and component-wise metrics (True Positive Rate: $0.83 \pm 0.01$, Positive Predictive Value: $0.96 \pm 0.01$). These results demonstrate Spatial-MSMA's potential for accurate and interpretable anomaly localization in medical imaging, with implications for improved diagnosis and treatment planning in clinical settings. Our code is available at~\url{https://github.com/ahsanMah/sade/}.