Dimensionality Reduction and Nearest Neighbors for Improving Out-of-Distribution Detection in Medical Image Segmentation

TL;DR

This paper proposes a dimensionality reduction and nearest neighbor-based method to improve out-of-distribution detection in medical image segmentation models, enhancing reliability and clinician awareness.

Contribution

It introduces a scalable out-of-distribution detection approach using PCA or UMAP with Mahalanobis and KNN distances for medical image segmentation models.

Findings

KNN outperforms Mahalanobis distance in detection accuracy

Dimensionality reduction reduces computational load

Method effectively detects out-of-distribution images in medical imaging

Abstract

Clinically deployed deep learning-based segmentation models are known to fail on data outside of their training distributions. While clinicians review the segmentations, these models tend to perform well in most instances, which could exacerbate automation bias. Therefore, detecting out-of-distribution images at inference is critical to warn the clinicians that the model likely failed. This work applied the Mahalanobis distance (MD) post hoc to the bottleneck features of four Swin UNETR and nnU-net models that segmented the liver on T1-weighted magnetic resonance imaging and computed tomography. By reducing the dimensions of the bottleneck features with either principal component analysis or uniform manifold approximation and projection, images the models failed on were detected with high performance and minimal computational load. In addition, this work explored a non-parametric alternative to the MD, a k-th nearest neighbors distance (KNN). KNN drastically improved scalability and performance over MD when both were applied to raw and average-pooled bottleneck features.