Epicardial and paracardial adipose tissue quantification in short-axis cardiac cine MRI using deep learning
- 23 August 2025
- journal article
- research article
- Published by Springer Nature in Magnetic Resonance Materials in Physics, Biology and Medicine
- Vol. 39 (1) , 97-108
Abstract
Objective Epicardial and paracardial adipose tissues (EAT and PAT) are two types of fat depots around the heart and they have important roles in cardiac physiology. Manual quantification of EAT and PAT from cardiac MR (CMR) is time-consuming and prone to human bias. Leveraging the cardiac motion, we aimed to develop deep learning neural networks for automated segmentation and quantification of EAT and PAT in short-axis cine CMR. Materials and methods A modified U-Net equipped with modules of multi-resolution convolution, motion information extraction, feature fusion, and dual attention mechanisms, was developed. Multiple steps of ablation studies were performed to verify the efficacy of each module. The performance of different networks was also compared. Results The final network incorporating all modules achieved segmentation Dice indices of 77.72% ± 2.53% and 77.18% ± 3.54% for EAT and PAT, respectively, which were significantly higher than the baseline U-Net. It also achieved the highest performance compared to other networks. With our model, the determination coefficients of EAT and PAT volumes to the reference were 0.8550 and 0.8025, respectively. Conclusion Our proposed network can provide accurate and quick quantification of EAT and PAT on routine short-axis cine CMR, which can potentially aid cardiologists in clinical settings.Keywords
Funding Information
- National Natural Science Foundation of China (82250610232)
- National Natural Science Foundation of China (82302295)
- Science and Technology Commission of Shanghai Municipality (23010503200)
This publication has 43 references indexed in Scilit:
- Segmentation and volume quantification of epicardial adipose tissue in computed tomography imagesMedical Physics, 2022
- ExFuse: Enhancing Feature Fusion for Semantic Segmentation2018
- CBAM: Convolutional Block Attention Module2018
- Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation2018
- 3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation2016
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Fundamentals of balanced steady state free precession MRIJournal of Magnetic Resonance Imaging, 2013
- Myocardial Fat ImagingCurrent Cardiovascular Imaging Reports, 2010
- Generalized autocalibrating partially parallel acquisitions (GRAPPA)Magnetic Resonance in Medicine, 2002
- Appearance of the Normal Pericardium on Coronary MR AngiogramsJournal of Magnetic Resonance Imaging, 1995