Use of uncertainty quantification as a surrogate for layer segmentation error in Stargardt disease retinal OCT images

D. Alonso-Caneiro, J. Kugelman, Janelle Tong, M. Kalloniatis, F. Chen, Scott A. Read, M. Collins
{"title":"Use of uncertainty quantification as a surrogate for layer segmentation error in Stargardt disease retinal OCT images","authors":"D. Alonso-Caneiro, J. Kugelman, Janelle Tong, M. Kalloniatis, F. Chen, Scott A. Read, M. Collins","doi":"10.1109/DICTA52665.2021.9647154","DOIUrl":null,"url":null,"abstract":"Semantic segmentation methods based on deep learning techniques have transformed the analysis of many medical imaging modalities, including the extraction of retinal layers from ocular optical coherence tomography images. Despite the high accuracy of these methods, the automatic techniques are not free of labelling errors, which means that a clinician may need to engage in the time-consuming process of reviewing the outcome of the segmentation method. Given this shortcoming, having access to segmentation techniques that can provide a confidence metric associated with the output (probability class map) are desirable. In this study, the use of Monte-Carlo dropout combined with a residual U-net architecture is explored as a way to provide segmentation pixel-wise prediction maps as well as corresponding uncertainty maps. While assessing the proposed network on a dataset of subjects with a retinal pathology (Stargardt disease), the uncertainty map exhibited a high correlation with the boundary error metric. Thus, confirming the potential of the technique to extract metrics that are a surrogate of the segmentation error. While the Monte-Carlo dropout seems to have no detrimental effect on performance, the uncertainty metric derived from this technique has potential for a range of important clinical (i.e. ranking of scans to be reviewed by a human expert) and research (i.e. network fine-tuning with a focus on high uncertainty/high error regions) applications.","PeriodicalId":424950,"journal":{"name":"2021 Digital Image Computing: Techniques and Applications (DICTA)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 Digital Image Computing: Techniques and Applications (DICTA)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/DICTA52665.2021.9647154","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1

Abstract

Semantic segmentation methods based on deep learning techniques have transformed the analysis of many medical imaging modalities, including the extraction of retinal layers from ocular optical coherence tomography images. Despite the high accuracy of these methods, the automatic techniques are not free of labelling errors, which means that a clinician may need to engage in the time-consuming process of reviewing the outcome of the segmentation method. Given this shortcoming, having access to segmentation techniques that can provide a confidence metric associated with the output (probability class map) are desirable. In this study, the use of Monte-Carlo dropout combined with a residual U-net architecture is explored as a way to provide segmentation pixel-wise prediction maps as well as corresponding uncertainty maps. While assessing the proposed network on a dataset of subjects with a retinal pathology (Stargardt disease), the uncertainty map exhibited a high correlation with the boundary error metric. Thus, confirming the potential of the technique to extract metrics that are a surrogate of the segmentation error. While the Monte-Carlo dropout seems to have no detrimental effect on performance, the uncertainty metric derived from this technique has potential for a range of important clinical (i.e. ranking of scans to be reviewed by a human expert) and research (i.e. network fine-tuning with a focus on high uncertainty/high error regions) applications.
利用不确定度量化替代Stargardt病视网膜OCT图像的层分割误差
基于深度学习技术的语义分割方法已经改变了许多医学成像模式的分析,包括从眼部光学相干断层扫描图像中提取视网膜层。尽管这些方法具有很高的准确性,但自动技术并非没有标记错误,这意味着临床医生可能需要参与耗时的过程来审查分割方法的结果。考虑到这一缺点,最好使用能够提供与输出(概率类映射)相关联的置信度度量的分割技术。在本研究中,将蒙特卡罗dropout与残差U-net架构相结合,作为一种提供分割像素预测图以及相应的不确定性图的方法进行了探索。在视网膜病变(Stargardt病)受试者数据集上评估所提出的网络时,不确定性图与边界误差度量显示出高度相关性。因此,确认了该技术在提取分割误差替代指标方面的潜力。虽然蒙特卡罗辍学似乎对性能没有不利影响,但从该技术衍生的不确定性度量在一系列重要的临床(即由人类专家审查的扫描排序)和研究(即关注高不确定性/高误差区域的网络微调)应用中具有潜力。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信