降维用于改进医学图像分割中的分布外检测
机器学习
2023-10-23 v2 人工智能
计算机视觉与模式识别
摘要
临床部署的分割模型已知在训练分布之外的数据上失效。由于这些模型在大多数病例上表现良好，必须在推理时检测分布外（OOD）图像以防自动化偏倚。本工作将马氏距离事后应用于在 T1 加权磁共振成像上分割肝脏的 Swin UNETR 模型的瓶颈特征。通过主成分分析降低瓶颈特征的维度，得以高性能和最小计算负载检测 OOD 图像。
引用
@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}
}
备注
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