arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1806.02562cs.CV
收藏

观察者间变异性对医学图像分割不确定性可靠估计的影响

On the Effect of Inter-observer Variability for a Reliable Estimation of Uncertainty of Medical Image Segmentation

Institute for Surgical Technologies and Biomechanics, University of Bern(伯尔尼大学外科技术与生物力学研究所);SCAN, Institute for Diagnostic and Interventional Neuroradiology(诊断与介入神经放射学研究所SCAN);University Clinic for Radio-oncology, Inselspital, Bern University Hospital, University of Bern(伯尔尼大学因塞尔医院放射肿瘤学大学诊所)

Alain Jungo, Raphael Meier, Ekin Ermis, Marcela Blatti-Moreno, Evelyn Herrmann, Roland Wiest, Mauricio Reyes

摘要:

期望不确定性估计方法改进对医学应用中使用的计算机辅助方法的理解和质量(例如,神经外科手术、放射治疗计划),其中自动医学图像分割至关重要。在有监督的机器学习中,生成地面实况标签数据的常见做法是合并观察者注释。然而,由于许多医学图像任务显示出由诸如图像质量、不同水平的用户专业知识和领域知识等因素引起的高观察者间变异性,因此很少有人知道观察者间变异性和常用的融合方法如何影响自动图像分割的不确定性的估计。本文分析了常用的图像标签融合技术对不确定性估计的影响,提出了对观测者之间的不确定性进行学习的方法。结果强调了在深度学习中应用融合方法的负面影响,以获得分割不确定性的可靠估计。此外,我们表明,学习观察员的不确定性,可以结合目前的标准蒙特卡洛脱落贝叶斯神经网络来表征模型的参数的不确定性。

英文摘要:

Uncertainty estimation methods are expected to improve the understanding and quality of computer-assisted methods used in medical applications (e.g., neurosurgical interventions, radiotherapy planning), where automated medical image segmentation is crucial. In supervised machine learning, a common practice to generate ground truth label data is to merge observer annotations. However, as many medical image tasks show a high inter-observer variability resulting from factors such as image quality, different levels of user expertise and domain knowledge, little is known as to how inter-observer variability and commonly used fusion methods affect the estimation of uncertainty of automated image segmentation. In this paper we analyze the effect of common image label fusion techniques on uncertainty estimation, and propose to learn the uncertainty among observers. The results highlight the negative effect of fusion methods applied in deep learning, to obtain reliable estimates of segmentation uncertainty. Additionally, we show that the learned observers' uncertainty can be combined with current standard Monte Carlo dropout Bayesian neural networks to characterize uncertainty of model's parameters.

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。

↑