Kazerooni Anahita Fathi, Malek Mahrooz, Haghighatkhah Hamidreza, Parviz Sara, Nabil Mahnaz, Torbati Leila, Assili Sanam, Saligheh Rad Hamidreza, Gity Masoumeh
Quantitative MR Imaging and Spectroscopy Group (QMISG), Research Center for Molecular and Cellular Imaging (RCMCI), Tehran University of Medical Sciences, Iran.
Department of Medical Physics and Biomedical Engineering, School of Medicine, Tehran University of Medical Sciences, Iran.
J Magn Reson Imaging. 2017 Feb;45(2):418-427. doi: 10.1002/jmri.25359. Epub 2016 Jul 1.
To identify the best dynamic contrast-enhanced (DCE) magnetic resonance imaging (MRI) descriptive parameters in predicting malignancy of complex ovarian masses, and develop an optimal decision tree for accurate classification of benign and malignant complex ovarian masses.
Preoperative DCE-MR images of 55 sonographically indeterminate ovarian masses (27 benign and 28 malignant) were analyzed prospectively. Four descriptive parameters of the dynamic curve, namely, time-to-peak (TTP), wash-in-rate (WIR), relative signal intensity (SI ), and the initial area under the curve (IAUC ) were calculated on the normalized curves of specified regions-of-interest (ROIs). A two-tailed Student's t-test and two automated classifiers, linear discriminant analysis (LDA) and support vector machines (SVMs), were used to compare the performance of the mentioned parameters individually and in combination with each other.
TTP (P = 6.15E-8) and WIR (P = 5.65E-5) parameters induced the highest sensitivity (89% for LDA, and 97% for SVM) and specificity (93% for LDA, and 100% for SVM), respectively. Regarding the high sensitivity of TTP and high specificity of WIR and through their combination, an accurate and simple decision-tree classifier was designed using the line equation obtained by LDA classification model. The proposed classifier achieved an accuracy of 89% and area under the ROC curve of 93%.
In this study an accurate decision-tree classifier based on a combination of TTP and WIR parameters was proposed, which provides a clinically flexible framework to aid radiologists/clinicians to reach a conclusive preoperative diagnosis and patient-specific therapy plan for distinguishing malignant from benign complex ovarian masses.
2 J. Magn. Reson. Imaging 2017;45:418-427.
确定在预测复杂卵巢肿块恶性程度方面最佳的动态对比增强（DCE）磁共振成像（MRI）描述参数，并开发一种用于准确分类良性和恶性复杂卵巢肿块的最优决策树。
前瞻性分析55个超声检查结果不确定的卵巢肿块（27个良性和28个恶性）的术前DCE-MR图像。在指定感兴趣区域（ROI）的归一化曲线上计算动态曲线的四个描述参数，即达峰时间（TTP）、流入率（WIR）、相对信号强度（SI）和曲线下初始面积（IAUC）。使用双尾Student t检验以及两种自动分类器，即线性判别分析（LDA）和支持向量机（SVM），分别比较上述参数单独及相互组合时的性能。
TTP（P = 6.15E - 8）和WIR（P = 5.65E - 5）参数分别具有最高的敏感性（LDA为89%，SVM为97%）和特异性（LDA为93%，SVM为100%）。鉴于TTP的高敏感性和WIR的高特异性及其组合，利用LDA分类模型得到的线性方程设计了一个准确且简单的决策树分类器。所提出的分类器准确率达89%，ROC曲线下面积为93%。
本研究提出了一种基于TTP和WIR参数组合的准确决策树分类器，为放射科医生/临床医生提供了一个临床灵活的框架，以辅助其做出确定性的术前诊断和针对患者的治疗方案，用于区分良性和恶性复杂卵巢肿块。
2 J. Magn. Reson. Imaging 2017;45:418 - 427。
