Automatic epicardial fat segmentation and volume quantification on non-contrast cardiac Computed Tomography

Epicardial Fat Volume (EFV) represents a valuable predictor of cardio- and cerebrovascular events. However, the manual procedures for EFV calculation, diffused in clinical practice, are highly time-consuming technicians or physicians often involve significant intra- inter-observer variances. To reduce processing time improve results repeatability, we propose computer-assisted tool that automatically performs epicardial fat segmentation volume quantification on non-contrast cardiac Computed Tomography (CT). The proposed algorithm prioritizes use basic image techniques, promoting lower computational complexity. heart region is selected using Otsu's Method, Template Matching Connected Component Analysis. Then, to refine pericardium delineation, convex hull applied. Lastly, segmented by thresholding. In addition algorithm, an intuitive software (HARTA) was developed use, allowing human intervention adjustments. A set 878 CT images used validate method. Using HARTA, average segment 15.5 ± 2.42 s, while manually 10 26 min were required. evaluated obtaining accuracy 98.83% Dice Similarity Coefficient 0.7730. automatic presents Pearson Spearman correlation coefficients 0.9366 0.8773, respectively. potential be contexts, assisting cardiologists achieve faster accurate EFV, leading towards personalized diagnosis therapy. component can also insure credibility this diagnostic support system. hereby presented available public access at GitHub.