Principal component analysis of breast DCE-MRI adjusted with a model-based method.
Principal component analysis of breast DCE-MRI adjusted with a model-based method.
复制标题
DOI：
10.1002/jmri.21950
复制
发表时间：
2009-11
影响因子：
4.4
通讯作者：
Degani, Hadassa
中科院分区：
文献类型：
--
作者：
Eyal, Erez;Badikhi, Daria;Furman-Haran, Edna;Kelcz, Fredrick;Kirshenbaum, Kevin J.;Degani, Hadassa
应用基于模型调整的主成分分析方法，探索一种快速、客观、标准化的乳腺DCE-MRI分析方法。采用主成分分析(PCA)和基于模型的三时间点(3TP)方法，对在1.5T扫描仪上采集的31个恶性病变和38个良性病变的三维梯度回波动态增强扫描图像进行了回顾性分析。通过主成分分析减少强度缩放(IS)和增强缩放(ES)数据集，得到第一个IS-特征向量，捕获脂肪和纤维腺组织之间的信号变化；两个IS-特征向量和两个第一个ES-特征向量，捕获对比增强后的变化，而其余特征向量捕获主要是噪声变化。两个对比度相关的特征向量的旋转导致了投影系数与3TP参数之间的高度一致性。ES特征向量和旋转角度在恶性病变中具有很高的重复性，因此可以计算出一般旋转的特征向量库。两个特征向量投影系数的ROC曲线分析表明，第一个旋转特征向量检测病变的灵敏度高(AUC>；0.97)，第二个旋转特征向量鉴别良恶性病变的灵敏度高(AUC=0.87)。经模型校正的主成分分析为乳腺DCE-MRI提供了一种快速、客观的计算机辅助诊断工具。
To investigate a fast, objective and standardized method for analyzing breast DCE-MRI applying principal component analysis (PCA) adjusted with a model based method. 3D gradient-echo dynamic contrast-enhanced breast images of 31 malignant and 38 benign lesions, recorded on a 1.5 Tesla scanner were retrospectively analyzed by PCA and by the model based three-time-point (3TP) method. Intensity scaled (IS) and enhancement scaled (ES) datasets were reduced by PCA yielding a 1st IS-eigenvector that captured the signal variation between fat and fibroglandular tissue; two IS-eigenvectors and the two first ES-eigenvectors that captured contrast-enhanced changes, whereas the remaining eigenvectors captured predominantly noise changes. Rotation of the two contrast related eigenvectors led to a high congruence between the projection coefficients and the 3TP parameters. The ES-eigenvectors and the rotation angle were highly reproducible across malignant lesions enabling calculation of a general rotated eigenvector base. ROC curve analysis of the projection coefficients of the two eigenvectors indicated high sensitivity of the 1st rotated eigenvector to detect lesions (AUC>0.97) and of the 2nd rotated eigenvector to differentiate malignancy from benignancy (AUC=0.87). PCA adjusted with a model-based method provided a fast and objective computer-aided diagnostic tool for breast DCE-MRI.
登录
查看更多内容
影响因子：
2.5
作者：
Lucht, REA;Knopp, MV;Brix, G
通讯作者：
Brix, G
影响因子：
4.1
作者：
Martinez, I.;Jimenez, J.;Artus, L.
通讯作者：
Artus, L.
影响因子：
6.2
作者：
Furman-Haran, E;Schechtman, E;Degani, H
通讯作者：
Degani, H
影响因子：
3.9
作者：
Kneeshaw, PJ;Lowry, M;Turnbull, LW
通讯作者：
Turnbull, LW
影响因子：
3.3
作者：
Helbich, TH
通讯作者：
Helbich, TH