3D texture analysis for classification of second harmonic generation images of human ovarian cancer.
3D texture analysis for classification of second harmonic generation images of human ovarian cancer.
复制标题
DOI：
10.1038/srep35734
复制
发表时间：
2016-10-21
影响因子：
4.6
通讯作者：
Campagnola PJ
中科院分区：
文献类型：
--
作者：
Wen B;Campbell KR;Tilbury K;Nadiarnykh O;Brewer MA;Patankar M;Singh V;Eliceiri KW;Campagnola PJ
细胞外基质（ECM）中胶原结构的重塑与卵巢癌有关。为了量化这些改变，我们实施了一种形式的3D纹理分析，以描绘在正常（1）和高风险（2）卵巢基质、良性卵巢肿瘤（3）、低级别（4）和高级别（5）浆液性肿瘤和类卵巢肿瘤（6）的3D二次谐波发生（SHG）显微镜图像数据中观察到的纤维形态。我们开发了一组量身定制的3D过滤器，其提取3D图像集中的纹理特征以构建（或学习）每个组织类的统计模型。通过使用这些学习到的模型应用k最近邻分类，我们对六个类别实现了83-91%的准确率。在相同的组织上，3D方法优于类似的2D分类，我们认为这是由于增加了信息量。这种基于ECM结构变化的分类将补充基于遗传谱的常规分类，并可作为额外的生物标志物。此外，纹理分析算法是相当通用的，因为它不依赖于单一的形态度量，如纤维对齐，长度和宽度，而是它们与可定制的基集的组合卷积。
Remodeling of the collagen architecture in the extracellular matrix (ECM) has been implicated in ovarian cancer. To quantify these alterations we implemented a form of 3D texture analysis to delineate the fibrillar morphology observed in 3D Second Harmonic Generation (SHG) microscopy image data of normal (1) and high risk (2) ovarian stroma, benign ovarian tumors (3), low grade (4) and high grade (5) serous tumors, and endometrioid tumors (6). We developed a tailored set of 3D filters which extract textural features in the 3D image sets to build (or learn) statistical models of each tissue class. By applying k-nearest neighbor classification using these learned models, we achieved 83–91% accuracies for the six classes. The 3D method outperformed the analogous 2D classification on the same tissues, where we suggest this is due the increased information content. This classification based on ECM structural changes will complement conventional classification based on genetic profiles and can serve as an additional biomarker. Moreover, the texture analysis algorithm is quite general, as it does not rely on single morphological metrics such as fiber alignment, length, and width but their combined convolution with a customizable basis set.
登录
查看更多内容
影响因子：
5
作者：
Vikram, Raghunandan;Yeung, Henry D. W.;Iyer, Revathy B.
通讯作者：
Iyer, Revathy B.
影响因子：
13.5
作者：
Théret, N;Musso, O;Clément, B
通讯作者：
Clément, B
影响因子：
6
作者：
Conklin, Matthew W.;Eickhoff, Jens C.;Keely, Patricia J.
通讯作者：
Keely, Patricia J.
DOI：
10.1046/j.1525-1438.2003.t01-1-13050.x
发表时间：
2003-09-01
影响因子：
4.8
作者：
Skates, S;Troiano, R;Knapp, RC
通讯作者：
Knapp, RC
影响因子：
50.5
作者：
Prat, J.
通讯作者：
Prat, J.