DeepFat: Deep Learning Segmentation and Quantification Method for Assessing Epicardial Adipose Tissue in CT Calcium Score Scans
Abstract Epicardial adipose tissue volume (EAT) has been linked to coronary artery disease and the risk of major adverse cardiac events. As manual quantification of EAT is time-consuming, requires specialized training, and is prone to human error, we developed a method (DeepFat) for the automatic assessment of EAT on non-contrast low-dose CT calcium score images using deep learning. We segmented the tissue enclosed by the pericardial sac on axial slices, using two innovations. First, we applied a HU‑attention-window with a window/level 350/40-HU to draw attention to the sac and reduce numerical errors. Second, we applied look ahead slab-of-slices with bisection (“bisect”) in which we split the heart into halves and sequenced the lower half from bottom-to-middle and the upper half from top-to-middle, thereby presenting an always increasing curvature of the sac to the network. EAT volume was obtained by thresholding voxels within the sac in the fat window (-190/-30-HU). Compared to manual segmentation, our algorithm gave excellent results with volume Dice=88.52%±3.3, slice Dice=87.70%±7.5, EAT error=0.5%±8.1, and R=98.52%(p<0.001). HU-attention-window and bisect improved Dice volume scores by 0.49% and 3.2% absolute, respectively. Extensive augmentation improved results. Variability between analysts was comparable to variability with DeepFat. Results compared favorably to those of previous publications.