Automatic quantification of epicardial adipose tissue volume

Abstract

Purpose 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. Methods 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. Results 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. Conclusions 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.

Relationship between epicardial fat volume on cardiac CT and atherosclerosis severity in three-vessel coronary artery disease: a single-center cross-sectional study

“…A semi-automatic method was developed for segmenting the pericardium and measuring the amount of EFV. Briefly, the pericardial contour was automatically delineated by a U-net framework, details of which are described in a previous report from our group [ 12 ]. The segmentation results were further checked and modified by two experienced cardiac imaging physicians (J.H.…”

Segmentation and volume quantification of epicardial adipose tissue in computed tomography images

“…As a traditional image segmentation method, threshold segmentation is widely welcomed in image segmentation due to its slight computational complexity, simple implementation, and stable performance. As a kind of human body fat, the threshold range of EAT is roughly determined as −175, −15, 32 −250, −50, 33 −200, −30, 34 and −190, −30 HU 35–40 . Among the many pieces of literature on EAT quantification research, more literature use −190, −30 HU as the upper and lower limits of EAT threshold.…”

Epicardial adipose tissue, metabolic disorders, and cardiovascular diseases: recent advances classified by research methodologies

“…Since 2015, researchers have been exploring the application of computer algorithms for fully automated EAT segmentation and quantification 53–56 . After numerous upgrades and iterations, the related algorithms have matured substantially over the past decade and have been put into actual use in clinical studies exploring the role of EAT 57–59 . The success of fully automated algorithms for EAT segmentation and quantification not only substantially reduced the workload required for EAT volume measurement (from more than 1 h to less than 1 min), but also improved accuracy in comparison with manual measurements.…”