Radiomics signature of epicardial adipose tissue for predicting postoperative atrial fibrillation after pulmonary endarterectomy

Abstract

PurposeThis study aimed to construct a radiomics signature of epicardial adipose tissue for predicting postoperative atrial fibrillation (POAF) after pulmonary endarterectomy (PEA) in patients with chronic thromboembolic pulmonary hypertension (CTEPH).MethodsWe reviewed the preoperative computed tomography pulmonary angiography images of CTEPH patients who underwent PEA at our institution between December 2016 and May 2022. Patients were divided into training/validation and testing cohorts by stratified random sampling in a ratio of 7:3. Radiomics features were selected by using intra- and inter-class correlation coefficient, redundancy analysis, and Least Absolute Shrinkage and Selection Operator algorithm to construct the radiomics signature. The area under the receiver operating characteristic curve (AUC), calibration curve, and decision curve analysis (DCA) were used to evaluate the discrimination, calibration, and clinical practicability of the radiomics signature. Two hundred-times stratified five-fold cross-validation was applied to assess the reliability and robustness of the radiomics signature.ResultsA total of 93 patients with CTEPH were included in this study, including 23 patients with POAF and 70 patients without POAF. Five of the 1,218 radiomics features were finally selected to construct the radiomics signature. The radiomics signature showed good discrimination with an AUC of 0.804 (95%CI: 0.664–0.943) in the training/validation cohort and 0.728 (95% CI: 0.503–0.953) in the testing cohorts. The average AUC of 200 times stratified five-fold cross-validation was 0.804 (95%CI: 0.801–0.806) and 0.807 (95%CI: 0.798–0.816) in the training and validation cohorts, respectively. The calibration curve showed good agreement between the predicted and actual observations. Based on the DCA, the radiomics signature was found to be clinically significant and useful.ConclusionThe radiomics signature achieved good discrimination, calibration, and clinical practicability. As a potential imaging biomarker, the radiomics signature of epicardial adipose tissue (EAT) may provide a reference for the risk assessment and individualized treatment of CTEPH patients at high risk of developing POAF after PEA.

Epicardial Adipose Tissue Changes during Statin Administration in Relation to the Body Mass Index: A Longitudinal Cardiac CT Study

“…However, a similar response to statin administration was observed in normal-BMI and in overweight/obese patients. A variation in fat quality during statin therapy could in part explain statins' pleiotropic effects; in the future, advanced texture analyses [34] and radiomic-based applications [35,36] customized for EAT analysis could better investigate such effects.…”

Radiomics Signature of Epicardial Adipose Tissue for Predicting Postoperative Atrial Fibrillation after Off-Pump Coronary Artery Bypass Surgery

“…The VOI image normalization and resampling were performed using the Pyradiomics package of Python Software (version 3.7, Python Software Foundation, DE, USA) as mentioned in our prior study [ 17 ]. In order to address the curse of dimensionality, which is particularly evident in high-dimensional data, we employed feature extraction techniques such as laplacian of gaussian (LoG) filters (sigma value of 1.0, 2.0, 3.0, 4.0, and 5.0) and wavelet transformation [ 18 ].…”

Epicardial adipose tissue, metabolic disorders, and cardiovascular diseases: recent advances classified by research methodologies

“…In addition, recent studies have demonstrated a significant difference in the radiomics phenotype of EAT between patients with lone AF and the control group, and even between different AF subtypes 107,108 . Furthermore, some specific radiomics features, such as Gray‐Level Size Zone Matrix, can act as an independent predictor of AF recurrence, which might be of practical clinical value in AF management 108,109 …”

“… 107 , 108 Furthermore, some specific radiomics features, such as Gray‐Level Size Zone Matrix, can act as an independent predictor of AF recurrence, which might be of practical clinical value in AF management. 108 , 109 …”