Supervised two-dimensional functional principal component analysis with time-to-event outcomes and mammogram imaging data.
Supervised two-dimensional functional principal component analysis with time-to-event outcomes and mammogram imaging data.
复制标题
利用事件发生时间结果和乳房 X 光成像数据进行监督二维功能主成分分析。
DOI：
10.1111/biom.13611
复制
发表时间：
2023-06
期刊：
影响因子：
1.9
通讯作者：
Colditz, Graham A.
中科院分区：
文献类型：
--
作者：
Jiang, Shu;Cao, Jiguo;Rosner, Bernard;Colditz, Graham A.
关键词：
筛查性乳房X光检查旨在早期发现乳腺癌，其次测量乳腺密度，以将妇女分类为高于或低于一般人群中未来乳腺癌的平均风险。尽管个体乳房X线摄影特征与乳腺癌风险有很强的相关性，但关于乳房X线摄影成像数据的统计文献有限。虽然在文献中已经研究了用于提取基于图像的特征的功能主成分分析（FPCA），但是其独立于时间-事件响应变量进行。考虑到建立一个预测模型的精度预防，我们提出了一套灵活的方法，监督FPCA（sFPCA）和功能偏最小二乘（FPLS），提取基于图像的故障时间相关的功能，同时容纳右删失增加的复杂性。在整个论文中，我们希望证明在不同的临床设置下，一种方法优于另一种方法。所提出的方法被应用到激励数据集从乔安妮骑士乳房健康队列在Siteman癌症中心。与基准模型相比，我们的方法不仅获得了最佳的预测性能，而且还揭示了乳房X线照片中不同的风险模式。
Screening mammography aims to identify breast cancer early and secondarily measures breast density to classify women at higher or lower than average risk for future breast cancer in the general population. Despite the strong association of individual mammography features to breast cancer risk, the statistical literature on mammogram imaging data is limited. While functional principal component analysis (FPCA) has been studied in the literature for extracting image-based features, it is conducted independently of the time-to-event response variable. With the consideration of building a prognostic model for precision prevention, we present a set of flexible methods, supervised FPCA (sFPCA) and functional partial least squares (FPLS), to extract image-based features associated with the failure time while accommodating the added complication from right censoring. Throughout the paper, we hope to demonstrate that one method is favored over the other under different clinical setups. The proposed methods are applied to the motivating dataset from the Joanne Knight Breast Health cohort at Siteman Cancer Center. Our approaches not only obtain the best prediction performance compared to the benchmark model, but also reveal different risk patterns within the mammograms.
登录
查看更多内容
影响因子：
3.7
作者：
Huang, Jianhua Z.;Shen, Haipeng;Buja, Andreas
通讯作者：
Buja, Andreas
影响因子：
45.3
作者：
Freedman, Andrew N.;Yu, Binbing;McCaskill-Stevens, Worta
通讯作者：
McCaskill-Stevens, Worta
影响因子：
10.9
作者：
Ou, Yangming;Sotiras, Aristeidis;Paragios, Nikos;Davatzikos, Christos
通讯作者：
Davatzikos, Christos
影响因子：
10.6
作者：
Brandt, Sami S.;Karemore, Gopal;Nielsen, Mads
通讯作者：
Nielsen, Mads
DOI：
10.1093/annonc/mdv590
发表时间：
2016-04
期刊：
Annals of oncology : official journal of the European Society for Medical Oncology
影响因子：
--
作者：
Smith SG;Sestak I;Forster A;Partridge A;Side L;Wolf MS;Horne R;Wardle J;Cuzick J
通讯作者：
Cuzick J