1. Deep learning-based workflow for automatic extraction of atria and epicardial adipose tissue on cardiac computed tomography in atrial fibrillation.
- Author
-
Kuo L, Wang GJ, Su PH, Chang SL, Lin YJ, Chung FP, Lo LW, Hu YF, Lin CY, Chang TY, Chen SA, and Lu CF
- Subjects
- Aged, Female, Humans, Male, Middle Aged, Tomography, X-Ray Computed, Workflow, Atrial Fibrillation diagnostic imaging, Atrial Fibrillation surgery, Deep Learning, Epicardial Adipose Tissue diagnostic imaging, Heart Atria diagnostic imaging, Pericardium diagnostic imaging
- Abstract
Background: Preoperative estimation of the volume of the left atrium (LA) and epicardial adipose tissue (EAT) on computed tomography (CT) images is associated with an increased risk of atrial fibrillation (AF) recurrence. We aimed to design a deep learning-based workflow to provide reliable automatic segmentation of the atria, pericardium, and EAT for future applications in the management of AF., Methods: This study enrolled 157 patients with AF who underwent first-time catheter ablation between January 2015 and December 2017 at Taipei Veterans General Hospital. Three-dimensional (3D) U-Net models of the LA, right atrium (RA), and pericardium were used to develop a pipeline for total, LA-EAT, and RA-EAT automatic segmentation. We defined fat within the pericardium as tissue with attenuation between -190 and -30 HU and quantified the total EAT. Regions between the dilated endocardial boundaries and endocardial walls of the LA or RA within the pericardium were used to detect voxels attributed to fat, thus estimating LA-EAT and RA-EAT., Results: The LA, RA, and pericardium segmentation models achieved Dice coefficients of 0.960 ± 0.010, 0.945 ± 0.013, and 0.967 ± 0.006, respectively. The 3D segmentation models correlated well with the ground truth for the LA, RA, and pericardium ( r = 0.99 and p < 0.001 for all). The Dice coefficients of our proposed method for EAT, LA-EAT, and RA-EAT were 0.870 ± 0.027, 0.846 ± 0.057, and 0.841 ± 0.071, respectively., Conclusion: Our proposed workflow for automatic LA, RA, and EAT segmentation using 3D U-Nets on CT images is reliable in patients with AF., Competing Interests: Conflicts of interest: Dr. Shih-Ann Chen, an editorial board member at Journal of the Chinese Medical Association , had no role in the peer review process of or decision to publish this article. The other authors declare that they have no conflicts of interest related to the subject matter or materials discussed in this article., (Copyright © 2024, the Chinese Medical Association.)
- Published
- 2024
- Full Text
- View/download PDF