Related Experiment Videos
Analysis of epicardial adipose tissue in relation to arterial hypertension using radiomics in photon-counting CT
Felix Waßmer1, Jannik Barz1, Dominik Nörenberg1
1Department of Radiology and Nuclear Medicine, University Medical Center Mannheim, Heidelberg University, Mannheim, Germany.
Insights
Photon-counting CT reveals lower epicardial adipose tissue attenuation in patients with arterial hypertension. This finding may aid in cardiac risk stratification beyond traditional stenosis detection.
Area of Science:
- Cardiovascular Imaging
- Radiology
- Artificial Intelligence in Medicine
Background:
- Cardiac CT is integral to clinical practice, moving beyond stenosis detection.
- Individual risk stratification using cardiac structure textural analysis is gaining importance.
- Photon-counting CT (PCCT) enables advanced radiomic analysis.
Purpose of the Study:
- To explore radiomic features of epicardial adipose tissue (EAT) for risk stratification.
- To investigate the association between EAT radiomics and arterial hypertension.
- To evaluate machine learning models for hypertension prediction using EAT features.
Main Methods:
- Retrospective analysis of 114 patients without coronary artery disease undergoing PCCT.
- Manual segmentation of EAT and extraction of 1,015 radiomic features.
- Machine learning models (logistic regression) evaluated with cross-validation and a test set.
Main Results:
- Logistic regression showed moderate performance (AUC 0.65/0.59).
- The most significant finding was lower mean EAT attenuation in hypertensive patients.
- Feature selection involved univariate analysis, RFE, and random forest importance.
Conclusions:
- Lower mean EAT attenuation is a potential imaging biomarker for arterial hypertension.
- Radiomic analysis of EAT shows promise for cardiac risk stratification.
- Findings are exploratory and require validation in larger cohorts.
Abstract:
Cardiac CT is increasingly integrated into clinical routine. However, looking beyond the diagnostic aspect of identifying hemodynamically significant stenosis, individual risk stratification through interpretation of textural alterations of cardiac structures influenced by clinical risk factors, such as arterial hypertension, becomes increasingly relevant after the implementation of photon-counting CT. In this retrospective, single-center, IRB-approved study, 114 patients without coronary artery disease underwent PCCT. Epicardial adipose tissue (EAT) was manually segmented, and 1,015 radiomic features were extracted using PyRadiomics. Patients were divided into two groups defined by the presence or absence of arterial hypertension. Feature selection combined univariate analysis, recursive feature elimination, and random forest importance. Three machine-learning models were evaluated using a leakage-free protocol with repeated stratified cross-validation and a separately held-out test set. Logistic regression achieved the best but only moderate performance (cross-validated AUC 0.65; held-out test AUC 0.59). The most robust quantitative finding was a lower mean EAT attenuation in the hypertension group. These exploratory findings should be regarded as hypothesis-generating and require validation in larger cohorts.
Related Concept Videos
01:20Imaging Studies for Cardiovascular System III: X-Ray
Definition and Purpose
An X-ray, or radiograph, is a non-invasive method that uses ionizing radiation to take images of internal structures. It is mainly used in cardiac imaging to examine the heart, lungs, and major blood vessels, aiming to identify abnormalities in the heart's size, shape, and position, such as heart failure, congenital defects, and vascular...
01:28Imaging Studies for Cardiovascular System V: CT
01:25Imaging Studies for Cardiovascular System VI: Calcium -Scoring CT
01:30Acute Coronary Syndrome III: Diagnostic Studies