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.
@article{arxiv.2308.03723,
title = {Dimensionality Reduction for Improving Out-of-Distribution Detection in Medical Image Segmentation},
author = {McKell Woodland and Nihil Patel and Mais Al Taie and Joshua P. Yung and Tucker J. Netherton and Ankit B. Patel and Kristy K. Brock},
journal= {arXiv preprint arXiv:2308.03723},
year = {2023}
}
Comments
This preprint has not undergone peer review or any post-submission improvements or corrections. The Version of Record of this contribution is published in the proceedings of UNSURE 2023, Lecture Notes in Computer Science, vol 14291, and is available online at https://doi.org/10.1007/978-3-031-44336-7_15