Radiomic features based on Hessian index for prediction of prognosis in head-and-neck cancer patients.
Radiomic features based on Hessian index for prediction of prognosis in head-and-neck cancer patients.
复制标题
DOI：
10.1038/s41598-020-78338-7
复制
发表时间：
2020-12-04
影响因子：
4.6
通讯作者：
Kabata Y
中科院分区：
文献类型：
--
作者：
Le QC;Arimura H;Ninomiya K;Kabata Y
这项研究证明了基于差异拓扑学的Hessian指数的放射学特征在头颈部癌症患者治疗前预测预后的有效性。Hessian指数用CT图像上每个体素的Hessian矩阵的负特征值的个数来计算，该指数可以指示肿瘤在凸点、凹点和其他点(鞍点)的异质性。在训练队列(n = 126)中构建了三种类型的签名，每种签名来自CT常规特征、海森索引特征以及来自常规和索引特征集的组合特征。比较低危和高危人群的生存曲线，用统计学上的显著差异(p值，对数列检验)来评估这些信号的预后价值。在一个测试队列(n = 68)中，用常规变量、指数变量、组合特征变量和临床变量建立的模型的p值分别为2.9510-2、1.8510-2、3.1710-2和1.8710-3。当结合临床变量时，常规特征、指数特征和联合特征的p值分别为3.53×10~(-3)、1.28×10~(-3)和1.45×10~(-3)。这一结果表明，指数特征可以提供比常规特征更多的预后信息，并进一步增加临床变量对HN癌症患者的预后价值。
This study demonstrated the usefulness of radiomic features based on the Hessian index of differential topology for the prediction of prognosis prior to treatment in head-and-neck (HN) cancer patients. The Hessian index, which can indicate tumor heterogeneity with convex, concave, and other points (saddle points), was calculated as the number of negative eigenvalues of the Hessian matrix at each voxel on computed tomography (CT) images. Three types of signatures were constructed in a training cohort (n = 126), one type each from CT conventional features, Hessian index features, and combined features from the conventional and index feature sets. The prognostic value of the signatures were evaluated using statistically significant difference (p value, log-rank test) to compare the survival curves of low- and high-risk groups. In a test cohort (n = 68), the p values of the models built with conventional, index, combined features, and clinical variables were 2.95 10–2, 1.85 10–2, 3.17 10–2, and 1.87 10–3, respectively. When the features were integrated with clinical variables, the p values of conventional, index, and combined features were 3.53 10–3, 1.28 10–3, and 1.45 10–3, respectively. This result indicates that index features could provide more prognostic information than conventional features and further increase the prognostic value of clinical variables in HN cancer patients.
登录
查看更多内容
影响因子：
9.3
作者：
Hatt, Mathieu;Majdoub, Mohamed;Visvikis, Dimitris
通讯作者：
Visvikis, Dimitris
影响因子：
3.5
作者：
Buch, K.;Li, B.;Sakai, O.
通讯作者：
Sakai, O.
影响因子：
4.4
作者：
Clark, Kenneth;Vendt, Bruce;Prior, Fred
通讯作者：
Prior, Fred
通过口咽头和颈癌患者中的原发性肿瘤纹理分析来研究用于局部复发的放射素特征。
影响因子：
4.6
作者：
M. D. Anderson Cancer Center Head and Neck Quantitative Imaging Working Group
通讯作者：
M. D. Anderson Cancer Center Head and Neck Quantitative Imaging Working Group
影响因子：
5.9
作者：
Ganeshan, Balaji;Panayiotou, Elleny;Miles, Ken
通讯作者：
Miles, Ken