Zhang Qiang, Qiao Huiyu, Dou Jiaqi, Sui Binbin, Zhao Xihai, Chen Zhensen, Wang Yishi, Chen Shuo, Lin Mingquan, Chiu Bernard, Yuan Chun, Li Rui, Chen Huijun
Center for Biomedical Imaging Research, Department of Biomedical Engineering, School of Medicine, Tsinghua University, Beijing, China.
Department of Radiology, Beijing TianTan Hospital, Capital Medical University, Beijing Neurosurgical Institute, Beijing, China.
Magn Reson Imaging. 2019 Jul;60:93-100. doi: 10.1016/j.mri.2019.04.001. Epub 2019 Apr 5.
This study sought to determine the feasibility of using Simultaneous Non-contrast Angiography and intraPlaque Hemorrhage (SNAP) to detect the lipid-rich/necrotic core (LRNC), and develop a machine learning based algorithm to segment plaque components on SNAP images.
Sixty-eight patients (age: 58±9 years, 24 males) with carotid artery atherosclerotic plaque were imaged on a 3 T MR scanner with both traditional multi-contrast vessel wall MR sequences (TOF, T1W, and T2W) and 3D SNAP sequence. The manual segmentations of carotid plaque components including LRNC, intraplaque hemorrhage (IPH), calcification (CA) and fibrous tissue (FT) on traditional multi-contrast images were used as reference. By utilizing the intensity and morphological information from SNAP, a machine learning based two steps algorithm was developed to firstly identify LRNC (with or without IPH), CA and FT, and then segmented IPH from LRNC. Ten-fold cross-validation was used to evaluate the performance of proposed method. The overall pixel-wise accuracy, the slice-wise sensitivity & specificity & Youden's index, and the Pearson's correlation coefficient of the component area between the proposed method and the manual segmentation were reported.
In the first step, all tested classifiers (Naive Bayes (NB), Support Vector Machine (SVM), Random Forest (RF), Gradient Boosting Decision Tree (GBDT) and Artificial Neural Network (ANN)) had overall pixel-wise accuracy higher than 0.88. For RF, GBDT and ANN classifiers, the correlation coefficients of areas were all higher than 0.82 (p < 0.001) for LRNC and 0.79 for CA (p < 0.001), and the Youden's indexes were all higher than 0.79 for LRNC and 0.76 for CA, which were better than that of NB and SVM. In the second step, the overall pixel-wise accuracy was higher than 0.78 for the five classifiers, and RF achieved the highest Youden's index (0.69) with the correlation coefficients as 0.63 (p < 0.001).
The RF is the overall best classifier for our proposed method, and the feasibility of using SNAP to identify plaque components, including LRNC, IPH, CA, and FT has been validated. The proposed segmentation method using a single SNAP sequence might be a promising tool for atherosclerotic plaque components assessment.
本研究旨在确定使用同步非对比血管造影和斑块内出血（SNAP）检测富含脂质/坏死核心（LRNC）的可行性，并开发一种基于机器学习的算法来分割SNAP图像上的斑块成分。
对68例（年龄：58±9岁，男性24例）患有颈动脉粥样硬化斑块的患者，在3T磁共振扫描仪上采用传统的多对比血管壁磁共振序列（TOF、T1W和T2W）以及3D SNAP序列进行成像。以传统多对比图像上颈动脉斑块成分（包括LRNC、斑块内出血（IPH）、钙化（CA）和纤维组织（FT））的手动分割作为参考。利用SNAP的强度和形态学信息，开发了一种基于机器学习的两步算法，首先识别LRNC（有无IPH）、CA和FT，然后从LRNC中分割出IPH。采用十折交叉验证来评估所提方法的性能。报告了所提方法与手动分割之间的总体像素准确率、逐切片敏感性、特异性、约登指数以及成分面积的皮尔逊相关系数。
在第一步中，所有测试的分类器（朴素贝叶斯（NB）、支持向量机（SVM）、随机森林（RF）、梯度提升决策树（GBDT）和人工神经网络（ANN））的总体像素准确率均高于0.88。对于RF、GBDT和ANN分类器，LRNC的面积相关系数均高于0.82（p<0.001），CA的面积相关系数高于0.79（p<0.001），LRNC的约登指数均高于0.79，CA的约登指数高于0.76，优于NB和SVM。在第二步中，五个分类器的总体像素准确率均高于0.78，RF的约登指数最高（0.69），相关系数为0.63（p<0.001）。
RF是我们所提方法总体上最佳的分类器，并且使用SNAP识别包括LRNC、IPH、CA和FT在内的斑块成分的可行性已得到验证。所提的使用单一SNAP序列的分割方法可能是评估动脉粥样硬化斑块成分的一种有前景的工具。
