A 3-D Riesz-Covariance Texture Model for Prediction of Nodule Recurrence in Lung CT
A 3-D Riesz-Covariance Texture Model for Prediction of Nodule Recurrence in Lung CT
复制标题
DOI：
10.1109/tmi.2016.2591921
复制
发表时间：
2016-12-01
影响因子：
10.6
通讯作者：
Depeursinge, Adrien
中科院分区：
文献类型：
--
作者：
Cirujeda, Pol;Cid, Yashin Dicente;Depeursinge, Adrien
本文提出了一种新的成像生物标志物的肺癌复发的三维纹理分析的CT图像。三维形态结节组织的属性描述的3-D Riesz小波。后者的响应聚集在结节区域内的功能协方差，利用丰富的内部和内部变化的特征空间尺寸。当与经典的使用平均值进行特征聚合相比时，特征协方差保留了特征之间的空间协变。得到的Riesz-协方差描述符位于黎曼几何允许测地线测量和微分流形。后一个属性被合并到支持向量机（SVM）和流形感知稀疏正则化分类器的内核。在110例非小细胞肺癌（NSCLC）患者和癌症复发信息的数据集上评估了所提出模型的有效性。12个月内疾病复发的预测准确率为81.3- 82.7%。复发的解剖位置可以区分为局部、区域和远处失败，准确率为78.3- 93.3%。通过揭示用于建立预测模型的结节区域的重要性，所获得的结果打开了新的研究视角。
This paper proposes a novel imaging biomarker of lung cancer relapse from 3-D texture analysis of CT images. Three-dimensional morphological nodular tissue properties are described in terms of 3-D Riesz-wavelets. The responses of the latter are aggregated within nodular regions by means of feature covariances, which leverage rich intra-and inter-variations of the feature space dimensions. When compared to the classical use of the average for feature aggregation, feature covariances preserve spatial co-variations between features. The obtained Riesz-covariance descriptors lie on a manifold governed by Riemannian geometry allowing geodesic measurements and differentiations. The latter property is incorporated both into a kernel for support vector machines (SVM) and a manifold-aware sparse regularized classifier. The effectiveness of the presented models is evaluated on a dataset of 110 patients with non-small cell lung carcinoma (NSCLC) and cancer recurrence information. Disease recurrence within a timeframe of 12 months could be predicted with an accuracy of 81.3-82.7%. The anatomical location of recurrence could be discriminated between local, regional and distant failure with an accuracy of 78.3-93.3%. The obtained results open novel research perspectives by revealing the importance of the nodular regions used to build the predictive models.