Department of Radiation Oncology and Winship Cancer Institute, Emory University, Atlanta, GA 30322, United States of America. Co-first author.
Phys Med Biol. 2020 May 11;65(9):095012. doi: 10.1088/1361-6560/ab8077.
Epicardial adipose tissue (EAT) is a visceral fat deposit, that's known for its association with factors, such as obesity, diabetes mellitus, age, and hypertension. Segmentation of the EAT in a fast and reproducible way is important for the interpretation of its role as an independent risk marker intricate. However, EAT has a variable distribution, and various diseases may affect the volume of the EAT, which can increase the complexity of the already time-consuming manual segmentation work. We propose a 3D deep attention U-Net method to automatically segment the EAT from coronary computed tomography angiography (CCTA). Five-fold cross-validation and hold-out experiments were used to evaluate the proposed method through a retrospective investigation of 200 patients. The automatically segmented EAT volume was compared with physician-approved clinical contours. Quantitative metrics used were the Dice similarity coefficient (DSC), sensitivity, specificity, Jaccard index (JAC), Hausdorff distance (HD), mean surface distance (MSD), residual mean square distance (RMSD), and the center of mass distance (CMD). For cross-validation, the median DSC, sensitivity, and specificity were 92.7%, 91.1%, and 95.1%, respectively, with JAC, HD, CMD, MSD, and RMSD are 82.9% ± 8.8%, 3.77 ± 1.86 mm, 1.98 ± 1.50 mm, 0.37 ± 0.24 mm, and 0.65 ± 0.37 mm, respectively. For the hold-out test, the accuracy of the proposed method remained high. We developed a novel deep learning-based approach for the automated segmentation of the EAT on CCTA images. We demonstrated the high accuracy of the proposed learning-based segmentation method through comparison with ground truth contour of 200 clinical patient cases using 8 quantitative metrics, Pearson correlation, and Bland-Altman analysis. Our automatic EAT segmentation results show the potential of the proposed method to be used in computer-aided diagnosis of coronary artery diseases (CADs) in clinical settings.
心外膜脂肪组织 (EAT) 是一种内脏脂肪沉积，已知与肥胖、糖尿病、年龄和高血压等因素有关。快速且可重复地分割 EAT 对于解释其作为独立风险标志物的作用至关重要。然而，EAT 的分布具有可变性，各种疾病可能会影响 EAT 的体积，从而增加了已经耗时的手动分割工作的复杂性。我们提出了一种 3D 深度注意 U-Net 方法，用于从冠状动脉 CT 血管造影 (CCTA) 自动分割 EAT。通过对 200 例患者的回顾性研究，采用五折交叉验证和保留实验来评估所提出的方法。自动分割的 EAT 体积与医师批准的临床轮廓进行了比较。使用的定量指标包括 Dice 相似系数 (DSC)、敏感性、特异性、Jaccard 指数 (JAC)、Hausdorff 距离 (HD)、平均表面距离 (MSD)、残差均方距离 (RMSD) 和质心距离 (CMD)。对于交叉验证，中位数 DSC、敏感性和特异性分别为 92.7%、91.1%和 95.1%，JAC、HD、CMD、MSD 和 RMSD 分别为 82.9%±8.8%、3.77±1.86mm、1.98±1.50mm、0.37±0.24mm 和 0.65±0.37mm。对于保留测试，所提出方法的准确性仍然很高。我们开发了一种新的基于深度学习的方法，用于 CCTA 图像上心外膜脂肪组织的自动分割。我们通过与 200 例临床患者病例的地面真实轮廓进行比较，使用 8 种定量指标、Pearson 相关和 Bland-Altman 分析，证明了所提出的基于学习的分割方法的高精度。我们的自动 EAT 分割结果表明，该方法有可能在临床环境中用于冠状动脉疾病 (CAD) 的计算机辅助诊断。
