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

Ankit B. Patel; Joshua P. Yung; Kristy K. Brock; Mais Al Taie; McKell Woodland; Nihil Patel; Tucker J. Netherton

REVIEW

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2308.03723 v2 pith:3Y2Q34AS submitted 2023-08-07 cs.LG cs.AIcs.CV

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

McKell Woodland , Nihil Patel , Mais Al Taie , Joshua P. Yung , Tucker J. Netherton , Ankit B. Patel , Kristy K. Brock This is my paper

classification cs.LG cs.AIcs.CV

keywords bottleneckfeaturesimagesmodelsout-of-distributionsegmentationanalysisapplies

verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved

0 comments

read the original abstract

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.

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

discussion (0)