Automatic segmentation and quantification of epicardial adipose tissue from coronary computed tomography angiography.
- 作者列表："He X","Guo BJ","Lei Y","Wang T","Fu Y","Curran WJ","Zhang LJ","Liu T","Yang X
: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，以其与肥胖，糖尿病，年龄和高血压等因素相关而闻名。以快速和可重复的方式分割EAT对于解释其作为独立风险标志物的作用是重要的。然而，EAT具有可变分布，并且各种疾病可能影响EAT的体积，这可以增加已经耗时的手动分割工作的复杂性。我们提出了一种3D深度关注U-Net方法来自动分割冠状动脉计算机断层扫描血管造影 (CCTA) 中的EAT。通过对200名患者的回顾性调查，使用五倍交叉验证和保留实验来评估所提出的方法。将自动分割的EAT体积与医师批准的临床轮廓进行比较。使用的定量指标是Dice相似性系数 (DSC) 、灵敏度、特异性、Jaccard指数 (JAC) 、Hausdorff距离 (HD) 、平均表面距离 (MSD) 、剩余均方距离 (RMSD) 和质量中心距离 (CMD)。对于交叉验证，中值DSC、灵敏度和特异性分别为92.7% 、91.1% 和95.1%，JAC、HD、CMD、MSD和RMSD分别为82.9% ± 8.8% 、3.77 ± 1.86毫米、1.98 ± 1.50毫米、0.37 ± 0.24毫米和0.65 ± 0.37毫米。对于保持测试，所提出的方法的准确性仍然很高。我们开发了一种新颖的基于深度学习的方法，用于在CCTA图像上自动分割EAT。我们通过使用8个定量指标、Pearson相关性和Bland-Altman分析与200个临床患者病例的地面实况轮廓进行比较，证明了所提出的基于学习的分割方法的高准确性。我们的自动EAT分割结果显示了所提出的方法在临床环境中用于冠状动脉疾病 (CADs) 的计算机辅助诊断的潜力。
METHODS::We present the case of a 61-year-old woman with a large tumoral infiltration extending from the pelvis throughout the inferior vena cava inferior to the right atrium, protruding into the right ventricle and right ventricular outflow tract. She had been treated 10 years before for low-grade endometrial stromal sarcoma by hysterectomy and adnexectomy followed by hormone- and radio-therapy. Due to cancer recurrence, she underwent peritonectomy, appendectomy, and resection of terminal ileum.
METHODS:AIMS:Significant platelet activation after long stented coronary segments has been associated with periprocedural microvascular impairment and myonecrosis. In long lesions treated either with an everolimus-eluting bioresorbable vascular scaffold (BVS) or an everolimus-eluting stent (EES), we aimed to investigate (a) procedure-related microvascular impairment, and (b) the relationship of platelet activation with microvascular function and related myonecrosis. METHODS AND RESULTS:Patients (n=66) undergoing elective percutaneous coronary intervention (PCI) in long lesions were randomised 1:1 to either BVS or EES. The primary endpoint was the difference between groups in changes of pressure-derived corrected index of microvascular resistance (cIMR) after PCI. Periprocedural myonecrosis was assessed by high-sensitivity cardiac troponin T (hs-cTnT), platelet reactivity by high-sensitivity adenosine diphosphate (hs-ADP)-induced platelet reactivity with the Multiplate Analyzer. Post-dilatation was more frequent in the BVS group, with consequent longer procedure time. A significant difference was observed between the two groups in the primary endpoint of ΔcIMR (p=0.04). hs-ADP was not different between the groups at different time points. hs-cTnT significantly increased after PCI, without difference between the groups. CONCLUSIONS:In long lesions, BVS implantation is associated with significant acute reduction in IMR as compared with EES, with no significant interaction with platelet reactivity or periprocedural myonecrosis.
METHODS:BACKGROUND:Aortopulmonary window is an uncommon congenital heart disease, with untreated cases not surviving beyond childhood. However, very rarely it can present in adult patients with features of pulmonary hypertension. Clinically these patients cannot be differentiated from other more common conditions with left to right shunt. Transthoracic echocardiography if performed meticulously, can depict the defect in aortopulmonary septum. RESULTS:We report a case of large unrepaired aortopulmonary window in a 23 years old patient, diagnosed on transthoracic echocardiography.