Department of Radiology, General Hospital of Northern Theater Command, Shenyang, 110016, China.
College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, 110169, China.
Med Phys. 2021 Aug;48(8):4279-4290. doi: 10.1002/mp.15012. Epub 2021 Jun 29.
Epicardial fat is the adipose tissue between the serosal pericardial wall layer and the visceral layer. It is distributed mainly around the atrioventricular groove, atrial septum, ventricular septum and coronary arteries. Studies have shown that the density, thickness, volume and other characteristics of epicardial adipose tissue (EAT) are independently correlated with a variety of cardiovascular diseases. Given this association, the accurate determination of EAT volume is an essential aim of future research. Therefore, the purpose of this study was to establish a framework for fully automatic EAT segmentation and quantification in coronary computed tomography angiography (CCTA) scans.
A set of 103 scans are randomly selected from our medical center. An automatic pipeline has been developed to segment and quantify the volume of EAT. First, a multi-slice deep neural network is used to simultaneously segment the pericardium in multiple adjacent slices. Then a deformable model is employed to reduce false positive and negative regions in the segmented binary pericardial images. Finally, the pericardium mask is used to define the region of interest (ROI) and the threshold method is utilized to extract the pixels ranging from -175 Hounsfield units (HU) to -15 HU for the segmentation of EAT.
The Dice indices of the pericardial segmentation using the proposed method with respect to the manual delineation results of two radiology experts were 97.1% 0.7% and 96.9% 0.6%, respectively. The inter-observer variability was also assessed, resulting in a Dice index of 97.0% 0.7%. For the EAT segmentation results, the Dice indices between the proposed method and the two radiology experts were 93.4% 1.5% and 93.3% 1.3%, respectively, and the same measurement between the experts themselves was 93.6% 1.9%. The Pearson's correlation coefficients between the EAT volumes computed from the results of the proposed method and the manual delineation by the two experts were 1.00 and 0.99 and the same coefficients between the experts was 0.99.
This work describes the development of a fully automatic EAT segmentation and quantification method from CCTA scans and the results compare favorably with the assessments of two independent experts. The proposed method is also packaged with a graphical user interface which can be found at https://github.com/MountainAndMorning/EATSeg.
心外膜脂肪是心外膜壁层和内脏层之间的脂肪组织。它主要分布于心房沟、房间隔、室间隔和冠状动脉周围。研究表明，心外膜脂肪（EAT）的密度、厚度、体积等特征与多种心血管疾病独立相关。鉴于这种相关性，准确确定 EAT 体积是未来研究的重要目标。因此，本研究旨在建立一种用于冠状动脉计算机断层血管造影（CCTA）扫描中全自动 EAT 分割和定量的框架。
从我们的医疗中心随机选择了 103 例扫描。已经开发了一个自动流水线来分割和量化 EAT 的体积。首先，使用多层深度神经网络同时分割多个相邻切片的心包膜。然后使用可变形模型减少分割的心包二值图像中的假阳性和假阴性区域。最后，使用心包掩模定义感兴趣区域（ROI），并使用阈值方法提取从-175 亨氏单位（HU）到-15 HU 的像素用于 EAT 分割。
使用所提出的方法对两位放射科专家的手动勾画结果进行心包分割的 Dice 指数分别为 97.1% ± 0.7%和 96.9% ± 0.6%。还评估了观察者间的可变性，得到的 Dice 指数为 97.0% ± 0.7%。对于 EAT 分割结果，所提出的方法与两位放射科专家的 Dice 指数分别为 93.4% ± 1.5%和 93.3% ± 1.3%，专家之间的相同测量值为 93.6% ± 1.9%。从所提出的方法的结果计算得出的 EAT 体积与两位专家的手动勾画结果之间的 Pearson 相关系数分别为 1.00 和 0.99，专家之间的相同系数为 0.99。
本工作描述了一种从 CCTA 扫描中全自动 EAT 分割和定量的方法的开发，其结果与两位独立专家的评估相比表现良好。所提出的方法还带有图形用户界面，可以在 https://github.com/MountainAndMorning/EATSeg 上找到。
