Problem
Research questions and friction points this paper is trying to address.
Cardiac Adipose Tissue
Epicardial Adipose Tissue
Pericardial Adipose Tissue
CT Segmentation
Inter-observer Variability
Automated Cardiac Adipose Tissue Segmentation in Computed Tomography: A Literature Review
🤖 AI Summary
Manual segmentation of epicardial adipose tissue (EAT) and pericardial adipose tissue (PAT) is time-consuming and suffers from substantial inter-observer variability, hindering efficient and consistent clinical quantification. This study systematically reviews and presents the first comprehensive comparison of artificial intelligence–based approaches—particularly deep learning—and non-AI methods, including conventional image processing and traditional machine learning, for automated segmentation of EAT and PAT in both non-contrast and contrast-enhanced CT scans. The findings indicate that current automated techniques achieve accuracy approaching that of manual annotations, demonstrating strong potential for clinical deployment. However, key limitations remain, notably the scarcity of publicly available datasets and suboptimal optimization of CT attenuation thresholds, which this work identifies as critical directions for future research.
📝 Abstract
This review provides an overview of recent advancements in automated segmentation methods on Computed Tomography (CT) for two types of cardiac fat: Epicardial adipose Tissue (EAT) and Pericardial Adipose Tissue (PAT). These fat deposits, separated by the pericardium, have been linked to various cardiovascular diseases, with EAT receiving the most research attention. Their complex anatomical context makes manual quantification highly time-consuming and prone to considerable inter-observer variability. Automated methods effectively address these complications, offering a more efficient and consistent solution. This study encompasses a broad range of methods, spanning AI as well as non-AI approaches. Additionally, it presents the remaining challenges, including the need for larger annotated public datasets and optimized attenuation thresholds for contrast-enhanced CT. It is demonstrated that automated methods are able to achieve segmentation results comparable to the quality of human annotation, proving their potential as a clinical tool for discovering new biomarkers and enhancing patient outcomes.
Innovation
Methods, ideas, or system contributions that make the work stand out.
automated segmentation
cardiac adipose tissue
computed tomography
epicardial adipose tissue
AI in medical imaging
🔎 Similar Papers
No similar papers found.
💼 Related Jobs
