Papers › Dimensionality Reduction and Nearest Neighbors for Improving Out-of-Distribution...

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

5 Aug 2024arXiv:2408.02761archive 2025-07-28

McKell Woodland, Nihil Patel, Austin Castelo, Mais Al Taie, Mohamed Eltaher, Joshua P. Yung, Tucker J. Netherton, Tiffany L. Calderone, Jessica I. Sanchez, Darrel W. Cleere, Ahmed Elsaiey, Nakul Gupta, David Victor, Laura Beretta, Ankit B. Patel, Kristy K. Brock

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.

Paper PDF Code

Code

mckellwoodland/dimen_reduce_mahal officialmentioned in papermentioned on GitHubpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Dimensionality Reduction Image Segmentation Medical Image Segmentation Out-of-Distribution Detection Semantic Segmentation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

1x1 Convolution Attention Batch Normalization Concatenated Skip Connection Convolution Dense Connections HOC Linear Layer Max Pooling Multi-Head Attention Position-Wise Feed-Forward Layer ReLU Residual Connection Softmax U-Net UNETR

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections