000			03959nam a22004337a 4500
008			240117s20242024 xxu||||| |||| 00| 0 eng d
022			_a1530-6550
024			_aPMC11270472 [pmc]
024			_aS1530-6550(22)00747-5 [pii]
040			_aOvid MEDLINE(R)
099			_a39076659
245			_aQuantification of Epicardial Adipose Tissue Volume and Attenuation for Cardiac CT Scans Using Deep Learning in a Single Multi-Task Framework.
251			_aReviews in Cardiovascular Medicine. 23(12):412, 2022 Dec.
252			_aRev Cardiovasc Med. 23(12):412, 2022 Dec.
253			_aReviews in cardiovascular medicine
260			_c2022
260			_fFY2023
260			_p2022 Dec
265			_sepublish
265			_tPubMed-not-MEDLINE
266			_z2024/07/30 04:59
520			_aBackground: Recent studies have shown that epicardial adipose tissue (EAT) is an independent atrial fibrillation (AF) prognostic marker and has influence on the myocardial function. In computed tomography (CT), EAT volume (EATv) and density (EATd) are parameters that are often used to quantify EAT. While increased EATv has been found to correlate with the prevalence and the recurrence of AF after ablation therapy, higher EATd correlates with inflammation due to arrest of lipid maturation and with high risk of plaque presence and plaque progression. Automation of the quantification task diminishes the variability in readings introduced by different observers in manual quantification and results in high reproducibility of studies and less time-consuming analysis. Our objective is to develop a fully automated quantification of EATv and EATd using a deep learning (DL) framework.
520			_aConclusions: We proposed a framework that provides a fast and robust strategy for accurate EAT segmentation, and volume (EATv) and attenuation (EATd) quantification tasks. The framework will be useful to clinicians and other practitioners for carrying out reproducible EAT quantification at patient level or for large cohorts and high-throughput projects. Copyright: © 2022 The Author(s). Published by IMR Press.
520			_aMethods: We proposed a framework that consists of image classification and segmentation DL models and performs the task of selecting images with EAT from all the CT images acquired for a patient, and the task of segmenting the EAT from the output images of the preceding task. EATv and EATd are estimated using the segmentation masks to define the region of interest. For our experiments, a 300-patient dataset was divided into two subsets, each consisting of 150 patients: Dataset 1 (41,979 CT slices) for training the DL models, and Dataset 2 (36,428 CT slices) for evaluating the quantification of EATv and EATd.
520			_aResults: The classification model achieved accuracies of 98% for precision, recall and F1 scores, and the segmentation model achieved accuracies in terms of mean ( +/- std.) and median dice similarity coefficient scores of 0.844 ( +/- 0.19) and 0.84, respectively. Using the evaluation set (Dataset 2), our approach resulted in a Pearson correlation coefficient of 0.971 ( R2 = 0.943) between the label and predicted EATv, and the correlation coefficient of 0.972 ( R2 = 0.945) between the label and predicted EATd.
546			_aEnglish
650			_zAutomated
651			_aMedStar Heart & Vascular Institute
651			_aMedStar Washington Hospital Center
656			_aElectrophysiology
656			_aMedstar Heart & Vascular Institute
657			_aJournal Article
700			_a#z#Bergquist, Peter J _bMHVI
700			_aSrichai, Monvadi B _bMHVI
700			_aThomaides, Athanasios _bMWHC
790			_aAbdulkareem M , Brahier MS , Zou F , Rauseo E , Uchegbu I , Taylor A , Thomaides A , Bergquist PJ , Srichai MB , Lee AM , Vargas JD , Petersen SE
856			_uhttps://dx.doi.org/10.31083/j.rcm2312412 _zhttps://dx.doi.org/10.31083/j.rcm2312412
942			_cART _dArticle
999			_c14643 _d14643