Codari Marina, Scarabello Marco, Secchi Francesco, Sforza Chiarella, Baselli Giuseppe, Sardanelli Francesco
Unit of Radiology, IRCCS Policlinico San Donato, Via Morandi 30, San Donato Milanese, 20097 Milan, Italy.
Postgraduate School in Radiodiagnostics, Università degli Studi di Milano, Via Festa del Perdono 7, 20122 Milan, Italy.
Magn Reson Imaging. 2018 Apr;47:77-82. doi: 10.1016/j.mri.2017.11.010. Epub 2017 Nov 26.
In this study we proposed a fully automated method for localizing and segmenting the ascending aortic lumen with phase-contrast magnetic resonance imaging (PC-MRI).
Twenty-five phase-contrast series were randomly selected out of a large population dataset of patients whose cardiac MRI examination, performed from September 2008 to October 2013, was unremarkable. The local Ethical Committee approved this retrospective study. The ascending aorta was automatically identified on each phase of the cardiac cycle using a priori knowledge of aortic geometry. The frame that maximized the area, eccentricity, and solidity parameters was chosen for unsupervised initialization. Aortic segmentation was performed on each frame using active contouring without edges techniques. The entire algorithm was developed using Matlab R2016b. To validate the proposed method, the manual segmentation performed by a highly experienced operator was used. Dice similarity coefficient, Bland-Altman analysis, and Pearson's correlation coefficient were used as performance metrics.
Comparing automated and manual segmentation of the aortic lumen on 714 images, Bland-Altman analysis showed a bias of -6.68mm, a coefficient of repeatability of 91.22mm, a mean area measurement of 581.40mm, and a reproducibility of 85%. Automated and manual segmentation were highly correlated (R=0.98). The Dice similarity coefficient versus the manual reference standard was 94.6±2.1% (mean±standard deviation).
A fully automated and robust method for identification and segmentation of ascending aorta on PC-MRI was developed. Its application on patients with a variety of pathologic conditions is advisable.
在本研究中，我们提出了一种利用相位对比磁共振成像（PC-MRI）对升主动脉管腔进行定位和分割的全自动方法。
从2008年9月至2013年10月进行心脏MRI检查且结果无异常的大量患者数据集中随机选取25个相位对比序列。当地伦理委员会批准了这项回顾性研究。利用主动脉几何形状的先验知识在心动周期的每个阶段自动识别升主动脉。选择使面积、偏心率和紧实度参数最大化的帧进行无监督初始化。使用无边缘主动轮廓技术对每个帧进行主动脉分割。整个算法使用Matlab R2016b开发。为验证所提出的方法，使用了由经验丰富的操作员进行的手动分割。采用Dice相似系数、Bland-Altman分析和Pearson相关系数作为性能指标。
在714幅图像上比较主动脉管腔的自动分割和手动分割，Bland-Altman分析显示偏差为-6.68mm，重复性系数为91.22mm，平均面积测量值为581.40mm，再现性为85%。自动分割和手动分割高度相关（R=0.98）。与手动参考标准相比，Dice相似系数为94.6±2.1%（平均值±标准差）。
开发了一种用于在PC-MRI上识别和分割升主动脉的全自动且稳健的方法。建议将其应用于各种病理状况的患者。
