Epicardial Adipose Tissue
Epicardial adipose tissue (EAT), the fat surrounding the heart, is increasingly recognized as a significant predictor of cardiovascular disease risk, independent of overall obesity. Current research focuses on developing accurate and efficient methods for EAT quantification, primarily using deep learning models like U-Net and SwinUNETR, often incorporating techniques such as radiomics analysis and uncertainty modeling to improve segmentation accuracy from medical images (CT, MRI). These advancements aim to improve cardiovascular risk assessment and potentially personalize preventative strategies by providing more precise and readily available measurements of EAT volume and characteristics.
Papers
Machine learning in the prediction of cardiac epicardial and mediastinal fat volumes
É. O. Rodrigues, V. H. A. Pinheiro, P. Liatsis, A. Conci
On the Automated Segmentation of Epicardial and Mediastinal Cardiac Adipose Tissues Using Classification Algorithms
Érick Oliveira Rodrigues, Felipe Fernandes Cordeiro de Morais, Aura Conci