This review surveys automated segmentation of epicardial adipose tissue (EAT) and pericardial adipose tissue (PAT) in computed tomography, covering both AI and non-AI methods. It highlights that automation can reduce the time and inter-observer variability associated with manual quantification. The review reports that existing approaches can achieve segmentation quality comparable to human annotation, supporting potential clinical use for biomarker discovery and patient assessment. It also identifies unresolved issues, especially the shortage of large public annotated datasets and the need to optimize attenuation thresholds for contrast-enhanced CT.
No heat snapshots are available in the last 24 hours.