Leveraging the Mahalanobis Distance to enhance Unsupervised Brain MRI Anomaly Detection
This work addresses a specific bottleneck in medical imaging for clinicians by refining anomaly segmentation, though it is incremental as it builds on existing reconstruction-based methods.
The paper tackles the problem of false positives in unsupervised anomaly detection for brain MRI by using multiple reconstructions from diffusion models and analyzing their distribution with the Mahalanobis distance, resulting in relative AUPRC improvements of up to 48.0% across datasets.
Unsupervised Anomaly Detection (UAD) methods rely on healthy data distributions to identify anomalies as outliers. In brain MRI, a common approach is reconstruction-based UAD, where generative models reconstruct healthy brain MRIs, and anomalies are detected as deviations between input and reconstruction. However, this method is sensitive to imperfect reconstructions, leading to false positives that impede the segmentation. To address this limitation, we construct multiple reconstructions with probabilistic diffusion models. We then analyze the resulting distribution of these reconstructions using the Mahalanobis distance to identify anomalies as outliers. By leveraging information about normal variations and covariance of individual pixels within this distribution, we effectively refine anomaly scoring, leading to improved segmentation. Our experimental results demonstrate substantial performance improvements across various data sets. Specifically, compared to relying solely on single reconstructions, our approach achieves relative improvements of 15.9%, 35.4%, 48.0%, and 4.7% in terms of AUPRC for the BRATS21, ATLAS, MSLUB and WMH data sets, respectively.