Cardiac fat segmentation using computed tomography and an image-to-image conditional generative adversarial neural network

2026-05-19

AI Summary

This study addresses the clinical need for efficient and accurate automated segmentation of cardiac adipose tissue—specifically epicardial and mediastinal fat—from non-contrast CT scans, a task traditionally hindered by the high cost and low efficiency of manual annotation. The authors propose the first application of the pix2pix conditional generative adversarial network (cGAN), an image-to-image translation framework, to enable end-to-end automatic segmentation and quantitative analysis of fat depots directly from CT images. Without requiring task-specific model redesign, the method achieves real-time, high-precision segmentation: 99.08% accuracy (F1 = 98.73) for epicardial fat and 97.90% accuracy (F1 = 98.40) for mediastinal fat, outperforming existing approaches and substantially enhancing clinical workflow efficiency.

Abstract

In recent years, research has highlighted the association between increased adipose tissue surrounding the human heart and elevated susceptibility to cardiovascular diseases such as atrial fibrillation and coronary heart disease. However, the manual segmentation of these fat deposits has not been widely implemented in clinical practice due to the substantial workload it entails for medical professionals and the associated costs. Consequently, the demand for more precise and time-efficient quantitative analysis has driven the emergence of novel computational methods for fat segmentation. This study presents a novel deep learning-based methodology that offers autonomous segmentation and quantification of two distinct types of cardiac fat deposits. The proposed approach leverages the pix2pix network, a generative conditional adversarial network primarily designed for image-to-image translation tasks. By applying this network architecture, we aim to investigate its efficacy in tackling the specific challenge of cardiac fat segmentation, despite not being originally tailored for this purpose. The two types of fat deposits of interest in this study are referred to as epicardial and mediastinal fats, which are spatially separated by the pericardium. The experimental results demonstrated an average accuracy of 99.08% and f1-score 98.73 for the segmentation of the epicardial fat and 97.90% of accuracy and f1-score of 98.40 for the mediastinal fat. These findings represent the high precision and overlap agreement achieved by the proposed methodology. In comparison to existing studies, our approach exhibited superior performance in terms of f1-score and run time, enabling the images to be segmented in real time.

Problem

• cardiac fat segmentation
• epicardial fat
• mediastinal fat
• computed tomography
• quantitative analysis

Innovation

• cardiac fat segmentation
• pix2pix
• conditional generative adversarial network
• epicardial fat
• mediastinal fat