Faculty, Staff and Student Publications

Publication Date

10-1-2023

Journal

UNSURE2025 Uncertainty for Safe Utilization of Machine Learning in Medical Imaging

DOI

10.1007/978-3-031-44336-7_15

PMID

40443712

PMCID

PMC12120689

PubMedCentral® Posted Date

5-29-2025

PubMedCentral® Full Text Version

Author MSS

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 do tend to perform well in most instances, which could exacerbate automation bias. Therefore, it is critical to detect out-of-distribution images at inference to warn the clinicians that the model likely failed. 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, images the model failed on were detected with high performance and minimal computational load. Specifically, the proposed technique achieved 92% area under the receiver operating characteristic curve and 94% area under the precision-recall curve and can run in seconds on a central processing unit.

Keywords

Out-of-distribution detection, Swin UNETR, Mahalanobis distance, Principal component analysis

Published Open-Access

yes

Share

COinS
 
 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.