Dimensionality Reduction for Improving Out-of-Distribution Detection in Medical Image Segmentation
This addresses a critical safety issue for clinicians using automated segmentation models in medical imaging, though it is incremental as it adapts existing methods to a specific domain.
The paper tackled the problem of detecting out-of-distribution images in medical image segmentation to prevent model failures, achieving high performance with minimal computational load by applying Mahalanobis distance to reduced bottleneck features.
Clinically deployed segmentation models are known to fail on data outside of their training distribution. As these models perform well on most cases, it is imperative to detect out-of-distribution (OOD) images at inference to protect against automation bias. This work applies the Mahalanobis distance post hoc to the bottleneck features of a Swin UNETR model that segments the liver on T1-weighted magnetic resonance imaging. By reducing the dimensions of the bottleneck features with principal component analysis, OOD images were detected with high performance and minimal computational load.