arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2407.16367cs.CVcs.LG
收藏

医学图像分割中的不确定性导航

Navigating Uncertainty in Medical Image Segmentation

Technical University of Denmark(丹麦技术大学)

Kilian Zepf, Jes Frellsen, Aasa Feragen

AI总结:

本文探讨了医学图像分割中不确定方法的选择与评估,通过前列腺和肺部分割案例研究,提出了整合偶然与认知成分的不确定分割模型开发与选择指导原则。

摘要:

我们探讨了医学成像中不确定分割方法的选择与评估,并提出了两个案例研究:前列腺分割表明,对于极小的标注者差异,简单的确定性模型即可满足需求;肺部分割则突出了Generalized Energy Distance (GED)在模型选择中的局限性。我们的发现为准确选择和开发整合了偶然和认知成分的不确定分割模型提供了指导原则。这些指导原则旨在帮助研究人员和从业者更好地开发、选择和评估不确定分割方法,从而促进分割不确定性在实践中的增强采用和有效应用。

英文摘要:

We address the selection and evaluation of uncertain segmentation methods in medical imaging and present two case studies: prostate segmentation, illustrating that for minimal annotator variation simple deterministic models can suffice, and lung lesion segmentation, highlighting the limitations of the Generalized Energy Distance (GED) in model selection. Our findings lead to guidelines for accurately choosing and developing uncertain segmentation models, that integrate aleatoric and epistemic components. These guidelines are designed to aid researchers and practitioners in better developing, selecting, and evaluating uncertain segmentation methods, thereby facilitating enhanced adoption and effective application of segmentation uncertainty in practice.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑