Automated Cardiac Adipose Tissue Segmentation in Computed Tomography: A Literature Review
Computer Vision and Pattern RecognitionArtificial Intelligence
Summary
The authors review recent progress in using computers to automatically identify two types of fat around the heart in CT scans, which is important because these fats are linked to heart diseases. Manual measurement is slow and varies between doctors, so automated methods help make this process faster and more reliable. They look at both AI-based and traditional techniques and note challenges like needing bigger shared datasets and better settings for certain CT scans. Their findings show that these automated methods can match the accuracy of human experts, making them promising tools for heart health research and care.
Authors
Andreas W. Aspe, Jonas Jalili Pedersen, Andreas Ohrt Johansen, Klaus Fuglsang Kofoed, Kristine Aavild Sørensen, Rasmus Reinhold Paulsen, Josefine Vilsbøll Sundgaard
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.