Next Article in Journal
Utility of Field Tests for Predicting Cardiorespiratory Fitness and Prescribing Exercise Intensity in Cardiac Rehabilitation Programs: A Randomized Crossover Trial
Previous Article in Journal
Periprocedural Myocardial Infarction: Do We Need an Updated Definition?
Previous Article in Special Issue
The Key Role of 3D TEE in Assessing the Morphology of Degenerative Mitral Valve Regurgitation
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
JCDD
Volume 13
Issue 3
10.3390/jcdd13030113
jcdd-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

Radiomic Assessment of Epicardial Adipose Tissue for the Prediction of Non-Calcified Coronary Atherosclerotic Plaques

by
Carlo Di Donna
1,2,
Armando Ugo Cavallo
3,
Eliseo Picchi
1,*,
Mario Laudazi
1,
Massimo Federici
4,
Marcello Chiocchi
1 and
Francesco Garaci
1
1
Diagnostic Imaging Unit, Department of Biomedicine and Prevention, University of Rome Tor Vergata, 00133 Rome, Italy
2
Radiology Unit, Sant’ Andrea University Hospital, 00189 Rome, Italy
3
Department of Radiology, Istituto Dermopatico dell’Immacolata IDI-IRCCS, 00167 Rome, Italy
4
Department of Systems Medicine, University of Rome Tor Vergata, 00133 Rome, Italy
*
Author to whom correspondence should be addressed.
J. Cardiovasc. Dev. Dis. 2026, 13(3), 113; https://doi.org/10.3390/jcdd13030113
Submission received: 11 January 2026 / Revised: 8 February 2026 / Accepted: 14 February 2026 / Published: 2 March 2026
(This article belongs to the Special Issue Feature Papers in Imaging—Second Edition)
Browse Figures
Versions Notes

Abstract

Epicardial adipose tissue (EAT) has previously been associated with coronary artery calcium scores, an increased burden of coronary artery disease (CAD), and features of plaque instability. These associations are likely mediated by endocrine and paracrine signaling from bioactive molecules secreted by EAT, which may contribute to coronary atherosclerosis. EAT can be non-invasively quantified on images obtained during coronary computed tomography angiography (CCTA). This study aimed to evaluate the potential association between EAT and non-calcified coronary plaques with severe stenosis using radiomic methodology. Materials and Methods: A total of 128 consecutive patients undergoing CCTA—both with and without contrast—for known or suspected CAD were retrospectively analyzed. EAT features were extracted from contrast scans. Coronary artery plaque features were evaluated using Coronary Artery Disease-Reporting and Data System (CAD-RADS). Results: EAT features showed a statistically significant positive correlation with non-calcified coronary plaques with severe grades of stenosis (CAD-RADS > 4). The Ensemble Machine Learning (EML) model combined with coronary plaque data showed a sensitivity of 1.00 and a specificity of 0.93, with a negative predictive value of 1.00 and a positive predictive value of 0.85, and an accuracy of 0.95 (95% CI: 0.9221–1) in internal validation. Conclusions: EAT may represent a novel imaging biomarker associated with the presence of actionable coronary plaques. Radiomic texture analysis of EAT could enhance the non-invasive prediction of coronary stenoses. These preliminary findings support the clinical utility of EAT evaluation via CCTA in patients with low to intermediate cardiovascular risk.

Graphical Abstract

1. Introduction

1.1. Coronary Artery Disease

Coronary artery disease (CAD) is a chronic, often progressive condition caused by the buildup of atherosclerotic plaques in the coronary arteries, influenced by risk factors such as dyslipidemia, diabetes, hypertension, smoking, family history, and lifestyle [1]. While CAD can remain stable, it may suddenly become unstable due to acute atherothrombotic events [2]. Coronary computed tomography angiography (CCTA) plays a key role in diagnosing CAD in patients with low to intermediate risk, offering high sensitivity and specificity for detecting coronary stenosis and plaque vulnerability [3,4]. CCTA directly visualizes both stenosis and atherosclerotic plaque, making it more reliable than functional tests in ruling out CAD and reducing unnecessary invasive coronary angiography [5,6]. Advances such as CT-derived fractional flow reserve and CT perfusion enhance its diagnostic accuracy [7,8,9,10,11,12]. CCTA can assess plaque morphology, predict future cardiovascular events, and support preventive therapy decisions. With decreasing contrast and radiation burdens, CCTA is increasingly cost-effective and is now recommended as the first-line test for stable chest pain evaluation by guidelines like NICE [12].

1.2. Epicardial Adipose Tissue (EAT)

Epicardial adipose tissue (EAT) and its density (EAD) can be readily measured on CCTA scans [13,14]. Various studies have shown a correlation between EAT volume and EAD, as measured by CCTA, and factors such as coronary artery calcium score, coronary artery disease burden, and plaque vulnerability [15,16,17,18].
Epicardial adipose tissue primarily serves a protective role by providing mechanical support, supplying energy to the myocardium, and secreting anti-inflammatory adipokines. However, due to its potential for excessive lipid accumulation and expansion, EAT is currently considered a risk-enhancing factor for metabolic syndrome, similar to abdominal visceral adipose tissue [18].
Visceral obesity, or an increase in visceral adipose tissue (VAT), refers to fat tissue surrounding the organs, in contrast to subcutaneous adipose tissue. The accumulation of VAT plays a key role in the development of metabolic syndrome and is associated with an increased risk of cardiovascular diseases, including heart failure, coronary artery disease, pulmonary conditions, neurological disorders such as stroke, and cancer. Moreover, VAT is an independent predictor of mortality in men [18,19,20,21]. Patients with visceral fat accumulation have been shown to exhibit greater thickness of EAT compared to those with predominantly peripheral fat distribution [22,23].
EAT, as a manifestation of visceral fat, has itself been associated with an increased risk of atherosclerotic cardiovascular diseases, including coronary artery disease [24,25,26]. Several studies have identified EAT as a significant contributor to the development of atrial myopathy, atrial fibrillation, thromboembolic stroke, biventricular hypertrophy, and nervous system impairment, all of which are implicated in heart failure [23,27,28,29].
The characteristics of EAT have also been linked to major adverse cardiovascular events and elevated serum levels of inflammatory plaque markers. In fact, EAT has been shown to exert both paracrine and endocrine effects on other cardiac structures [30]. Notably, low-attenuation fat on CT—indicative of inflamed white adipose tissue—is more likely to influence the atherosclerotic process [28].

1.3. Radiomics and Texture Analysis

Radiomics using texture analysis (TA) is a promising approach that enables rapid extraction of specific features from biomedical images [31,32]. Machine learning and artificial intelligence algorithms can then be applied to derive insights into the underlying pathophysiology, diagnosis, and outcomes of many diseases [33,34,35,36].
TA involves identifying image features that are not detectable by the human eye and improving the diagnostic accuracy of radiological exams by using standardized mathematical formulas to calculate the relationships between neighboring voxels in terms of signal intensity. Radiomics has already shown promising results in the field of cardiac MRI, including distinguishing myocardial infarction from myocarditis, differentiating hypertrophic myocardium from normal myocardium and hypertrophic cardiomyopathy from hypertensive heart disease, predicting long-term outcomes in patients with Takotsubo syndrome, and detecting subtle cardiac changes related to ischemic processes [33,37,38,39]. There is growing interest, across multiple fields, in artificial intelligence systems that can predict structural abnormalities or the outcomes of pathological processes by analyzing intrinsic image features that are not detectable through conventional visual assessment.

1.4. Aim of the Study

The aim of the study is to investigate potential associations between EAT radiomics features and coronary artery non-calcified plaques with severe stenosis in patients with low to intermediate cardiovascular risk undergoing CCTA.

2. Materials and Methods

A retrospective study was carried out at University Hospital of Rome “Tor Vergata”, with approval from the ethics committee (R.S.71.21, protocol no. 5777).

2.1. Patients

The study was conducted on 128 patients with low to intermediate cardiovascular risk, according to the ESC 2021 Guidelines and the Heart Score, who had undergone CCTA with and without contrast agents for known or suspected coronary artery disease between September 2021 and May 2023. The patients provided written informed consent for the use of their demographic, clinical, and imaging data in anonymized form for research purposes. The inclusion and exclusion criteria for the study population are summarized in Table 1.

2.2. Coronary CT

CCTAs were performed with a 256-row wide-detector CT system (Revolution CT, GE HealthCare, Chicago, IL, USA) with 160 mm z-axis coverage and a gantry rotation time of 0.28 s, using retrospective gating in axial acquisition mode with ECG synchronization and high pitch, and images were reconstructed using ASiR. After baseline CT acquisition, a non-ionic low-osmolar contrast agent (Iomeprol 400 mgI/mL, Bracco Imaging S.p.A., Milan, Italy) was injected into an antecubital vein through a 20-gauge catheter, using a dual-head injector. All images were transferred to an external workstation (ADW version 4.7; GE HealthCare, Chicago, IL, USA) for post-processing analysis.

2.3. CT Image Processing

The CCT images were first screened using the Picture Archiving and Communication System provided by University Hospital of Rome “Tor Vergata”. The images were then classified based on the presence or absence of atherosclerotic plaques in the three main coronary arteries (left anterior descending artery, LAD; circumflex artery, Cx; right coronary artery, RCA). The classification considered the degree of stenosis and composition, with particular attention to the presence of low-density non-calcified plaques. For each plaque, the degree of stenosis was assessed using the CAD-RADS classification [40,41].
Using multiplanar reconstructions for each patient, a post-contrast injection four-chamber mesocardial view was obtained to enhance visualization of the epicardial adipose tissue. A single four-chamber view was selected to standardize the anatomical landmark and minimize z-axis motion artifacts common in volumetric EAT assessment. Each image was then segmented by a single expert operator with 6 years of experience in cardiovascular imaging using the open-source software MaZda version 4.6 (Institute of Electronics, University of Lodz, Lodz, Poland; accessed on 2 June 2025) [42], placing a region of interest (ROI) on the portions of EAT visible in the periventricular and pericoronary regions, as shown in Figure 1.
Grayscale was normalized by scaling the histogram data (mean ± 3 standard deviations) to reduce variations in contrast and intensity that could compromise the quantification of texture analysis features. A total of 337 features were extracted for each ROI. The extracted TA features included histogram analysis, gradient analysis, geometry, co-occurrence matrix features across five directions, run-length matrix features across four directions, autoregressive model features, and wavelet transformation. A detailed description of the radiomic features is freely available in the MaZda 4.6 online manual [42].

2.4. Processing of TA Data

Texture analysis data were normalized using an auto-scaling process (centered on the mean and divided by the standard deviation of each variable) and then processed using the Weka data mining platform (v3.8.5) [43], which, through preprocessing of the extracted radiomic features, helped reduce potential overfitting.
Features were selected to prioritize the highest correlation with the target variable and the lowest correlation among themselves. For the preliminary analysis, CfsSubsetEval was then used to identify a subset of features that were highly correlated with the presence of severe non-calcified plaque, while maintaining low inter-feature correlation.
Subsequently, the auto-scaled dataset was split 50:50 into a training set and a testing and validation set to ensure a robust size for the testing set. The former was used to train the classification models, and the latter to test and evaluate their performance. The classes were evenly balanced in each dataset.
Eleven classification models were formed: random forest (RF), neural network (Nnet), Naïve Bayes (NB), Extreme Gradient Boosting (XGB), Support Vector Machines (SVM), Support Vector Machines with linear kernel (svmLinear), k-nearest neighborhoods (knn), partial least squares (pls), decision tree (CART), logistic regression model (glm), and linear discriminant analysis (lda). An adaptive resampling cross-validation system (minimum number of resamples = 99, confidence level = 0.05) was used to prevent overfitting and ensure robust hyperparameter selection.

2.5. Ensemble Machine Learning

Models with a test set accuracy greater than 70% were selected and combined using an Ensemble Machine Learning (EML) model, which was based on averaging the obtained predictions.
To evaluate the EML’s ability to correctly classify the images, ROC curves were computed, along with sensitivity, specificity, positive and negative predictive values, and overall accuracy. The score that maximized Youden’s index (sensitivity + specificity − 1) was identified as the optimal threshold for distinguishing between the two classes.
To summarize the results, a confusion matrix was used to assess the overall diagnostic performance of the proposed scoring method.

2.6. Statistical Analysis

Statistical analysis was performed using R version 3.4.4 (R Core Team 2018. R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria. URL https://www.R-project.org/ accessed on 2 June 2025) [44]. The packages used were “caret,” “stat,” “pROC,” and “OptimalCutpoints.” Categorical variables were displayed as absolute numbers and percentages, while continuous variables were shown as mean ± standard deviation. Continuous variables were compared using the Wilcoxon test. The Area Under the Curve (AUC) and ROC curves were used to compare the diagnostic performance of the various ML/AI models applied to each analyzed image. The AUCs obtained were compared using the DeLong test. The optimal threshold value was determined using Youden’s index. Additionally, thresholds were established to achieve a Negative Predictive Value (NPV) of 90% and a Positive Predictive Value (PPV) of 99%. The results showed that some values had a p-value lower than 0.05, indicating statistical significance.

3. Results

3.1. Study Population

The study population comprised 128 patients with low to intermediate cardiovascular risk who had undergone CCTA between September 2021 and May 2023. Their characteristics are summarized in Table 2. The workflow of data analysis is illustrated in Scheme 1.

3.2. Image Analysis

A total of 128 images obtained from cardiac CT scans were analyzed. The observed plaque characteristics and CAD-RADS scores are summarized in Table 3.
For each CCT exam, a single four-chamber image was segmented and analyzed for the assessment of epicardial adipose tissue using freehand ROI placement in MaZda 4.6. The selected variables are summarized in Table 4, which compares the mean values of each feature between patients with non-calcified plaques and CAD-RADS ≥ 4 and those without.

3.3. ROC Curve Analysis

The RF model showed a sensitivity of 0.66 and a specificity of 0.00, with a negative predictive value (NPV) of 0.00 and a positive predictive value (PPV) of 0.78, and an accuracy of 0.76 (95% CI: 0.383–0.713).
The NB model showed a sensitivity of 0.74 and a specificity of 0.43, with an NPV of 0.85 and a PPV of 0.30, and an accuracy of 0.68 (95% CI: 0.5135–0.825).
The SVM model showed a sensitivity of 0.66 and a specificity of 0.17, with an NPV of 0.20 and a PPV of 0.63, and an accuracy of 0.50 (95% CI: 0.3338–0.6662).
The linear SVM (SVM_L) model showed a sensitivity of 0.64 and a specificity of 0.10, with an NPV of 0.01 and a PPV of 0.67, and an accuracy of 0.50 (95% CI: 0.3338–0.6662).
The CART model showed a sensitivity of 0.70 and a specificity of 0.00, with an NPV of 0.00 and a PPV of 0.96, and an accuracy of 0.68 (95% CI: 0.5135–0.825).
The KNN model showed a sensitivity of 0.73 and a specificity of 0.32, with an NPV of 0.55 and a PPV of 0.55, and an accuracy of 0.53 (95% CI: 0.3582–0.6902).
The GLM model showed a sensitivity of 0.71 and a specificity of 0.00, with an NPV of 0.00 and a PPV of 0.00, and an accuracy of 0.71 (95% CI: 0.541–0.8458).
The PLS model showed a sensitivity of 0.70 and a specificity of 0.00, with an NPV of 0.96 and a PPV of 0.00, and an accuracy of 0.68 (95% CI: 0.5135–0.825).
The LDA model showed a sensitivity of 0.71 and a specificity of 0.00, with an NPV of 0.00 and a PPV of 0.00, and an accuracy of 0.71 (95% CI: 0.541–0.8458).
The NNET model showed a sensitivity of 0.65 and a specificity of 0.00, with an NPV of 0.00 and a PPV of 0.00, and an accuracy of 0.55 (95% CI: 0.383–0.7138).
The XGB model showed a sensitivity of 0.66 and a specificity of 0.00, with an NPV of 0.00 and a PPV of 0.78, and an accuracy of 0.55 (95% CI: 0.383–0.7138).
The EML model combined with coronary plaque data showed a sensitivity of 1.00 and a specificity of 0.93, with an NPV of 1.00 and a PPV of 0.85, and an accuracy of 0.95 (95% CI: 0.9221–1). The ROC curve is shown in Figure 2.

4. Discussion

4.1. Epicardial Adipose Tissue

An increasing body of research shows that epicardial adipose tissue not only serves as a protective mechanical cushion for the myocardium but also exerts biohumoral effects on both adjacent and non-adjacent cardiac structures. Goeller et al. and Abazid et al. have reported a correlation between EAD, coronary calcification (coronary calcium score), and the subclinical prevalence of CAD. These are just a few of the many studies exploring how EAT contributes to inflammation and plaque vulnerability, thereby elevating cardiovascular risk [16,24,27].
Low EAD is associated with BMI and higher CCS, suggesting the presence of chronic inflammation driven by white EAT that may elevate cardiovascular risk. Subjects with a CCS greater than 100 have a significantly lower EAD compared to those with a CCS of 0. Franssens et al. also described a link between low EAD and more extensive coronary calcification [28].
Research has shown that excess lipid accumulation in diet-induced obesity and insulin-resistant states is linked to adipose tissue characterized by lower CT attenuation with adipocyte hypertrophy and hyperplasia [28,45]. This adipose tissue secretes numerous molecules, such as plasminogen activator inhibitor-1 and monocyte chemoattractant protein-1, which are associated with low-grade systemic inflammation and heightened risk of vascular inflammation and atherosclerosis progression. Moreover, low-density EAT is associated with reduced levels of adiponectin, a protective factor against inflammation and atherogenesis, and therefore increases the risk of acute coronary syndrome and atherosclerosis progression [20].
Many inflammatory patterns linked to heart failure are caused by conditions such as obesity, hypertension, autoimmunity, and aging. Inflammatory biomolecules not only cause coronary microvascular endothelial inflammation, oxidative stress, reduced nitric oxide availability, and cardiomyocyte loss, but also directly affect cardiac immune cells, leading to local chronic inflammation [28]. The relationship between coronary atheromatosis and chronic inflammation suggests the potential to target these mediators therapeutically.

4.2. Radiomics

To our knowledge, this is the first study to use radiomic analysis of epicardial adipose tissue not only around the coronary arteries but also in the periventricular region to predict severe non-calcified coronary artery disease using the corresponding CAD-RADS score. There is growing interest in artificial intelligence systems that can predict the presence of structural abnormalities or the outcome of a pathological process by analyzing intrinsic imaging features that are not detectable through simple visual inspection [46,47].
Notably, machine learning and artificial intelligence tools are increasingly being used in diagnostic imaging. These technologies can analyze large volumes of data, which may consist of the pixels that make up the image or of intrinsic characteristics (radiomic features) extracted from the image itself. Radiomic feature analysis usually relies on expert operators, who play an active role in the data extraction, which can be a time-consuming process [48,49].
Studying radiomic features, backed by appropriate statistical analysis, also makes it possible to identify and potentially validate novel biomarkers for the diseases under investigation, which can be used for both diagnosis and prognosis. In this regard, a few emerging studies have begun to explore EAT radiomics and their prognostic implications [50,51,52,53]. Our work found a statistically significant correlation between specific radiomic features of epicardial adipose tissue and the presence of severe non-calcified coronary artery disease with CAD-RADS ≥ 4 and proposed the same kind of clinical applications.

4.3. Clinical Applications

If the results of this study are confirmed by further prospective research on larger populations, epicardial adipose tissue could be considered a new imaging biomarker for cardiovascular risk. Assessing the characteristics of EAT in patients undergoing chest CT, even without contrast agents, would allow for risk stratification and help determine which patients should be prioritized for further diagnostic investigations due to their higher risk of having management-relevant coronary artery disease.
Additionally, there are cases where a cardiac CT exam reveals moderate coronary pathology, and the radiologist may face the dilemma of whether to refer the patient for invasive follow-up through coronary angiography. Evaluation of EAT could aid in clinical decision-making for patients in these potential borderline cases.

5. Limitations of the Study

The main limitations of this study are its retrospective design, limited patient population, and the single-operator manual segmentation of epicardial adipose tissue on post-contrast images, although this approach did allow for the secure exclusion of coronary arteries and their branches. The retrospective design of the study prevented the collection of specific physiological parameters. As a result, a formal clinical risk stratification (e.g., via risk scores) could not be performed. Manual segmentation of EAT may introduce operator-dependent errors, as opposed to automated or semi-automated methods. The reliance on single-operator manual segmentation without inter-observer variability assessment (ICC) limits the generalizability of the results. Future research should employ volumetric segmentation and automated tools to enhance radiomic stability. Furthermore, while we categorized disease severity according to the CAD-RADS system, our analysis did not include specific stenosis percentages or a differentiation between CAD-RADS subgroups, which may carry distinct prognostic implications; future studies with larger cohorts should explore whether radiomic features can further stratify risk within these specific obstructive categories. Given that a substantial proportion of cardiovascular events arise from plaques causing less than 50% stenosis [3], future research involving larger cohorts across all CAD-RADS categories is needed to evaluate the broader predictive value of EAT radiomics. Additionally, while feature selection was performed to reduce dimensionality, the high number of radiomic features relative to the sample size poses a risk of overfitting. Although internal validation was performed, future studies utilizing nested cross-validation and larger datasets are required to robustly validate the stability of these radiomic signatures.

6. Conclusions

The EML model demonstrated excellent diagnostic accuracy in predicting the presence of non-calcified atheromatous plaques in the coronary circulation that result in severe stenosis, as determined from EAT radiomics in internal validation. These preliminary findings suggest that EAT radiomic features show a potential association with severe non-calcified coronary stenosis. This study is hypothesis-generating, and further prospective research with outcome-based validation is required to determine the clinical utility of this approach. and to determine if EAT characteristics may serve as a novel imaging biomarker for patients with low to intermediate cardiovascular risk.

Author Contributions

Conceptualization, C.D.D., A.U.C. and M.C.; methodology, C.D.D. and M.C.; software, A.U.C. and C.D.D.; validation, E.P., M.F. and F.G.; formal analysis, A.U.C. and C.D.D.; investigation, C.D.D. and M.L.; resources, M.L., C.D.D. and E.P.; data curation, A.U.C. and C.D.D.; writing—original draft preparation, C.D.D. and E.P.; writing—review and editing, M.L., E.P. and M.C.; visualization, A.U.C. and C.D.D.; supervision, M.F., F.G. and M.C.; project administration, C.D.D., M.L. and E.P.; funding acquisition, F.G. and E.P. All authors have read and agreed to the published version of the manuscript.

Funding

This research is co-funded by the Italian Ministry of University and Research within the Complementary National Plan PNC-I.1 “Research initiative for innovative technologies and pathways in the health and welfare sector”. “DARE—Digital Lifelong Prevention” (project code: PNC0000002—CUP: B53C22006450001).

Institutional Review Board Statement

The study was conducted in accordance with the Declaration of Helsinki and approved by the Institutional Review Board (R.S.71.21, protocol no. 5777, 15 November 2022).

Informed Consent Statement

Informed consent was obtained from all subjects before cardiac-CT scan also for scientific purposes; patient consent for this specific study was waived due to retrospective analysis.

Data Availability Statement

Data are available under reasonable request to the corresponding author.

Conflicts of Interest

The authors declare no conflicts of interest.

Abbreviations

The following abbreviations are used in this manuscript:
EATEpicardial Adipose Tissue
TATexture Analysis
CADCoronary Artery Disease
CCTACoronary Computed Tomography Angiography
CCSCoronary Calcium Score
AUCArea Under the Curve
ROCReceiving Operator Curve
EMLEnsemble Machine Learning Model
RFRandom Forest
NNETNeural Network
NBNaïve Bayes
XGBExtreme Gradient Boosting
SVMSupport Vector Machines
SVMlSupport Vector Machines with linear kernel
CARTDecision Tree
GLMLogistic Regression Model
KNNK-Nearest Neighborhoods
LDALinear Discriminant Analysis

References

  1. Knuuti, J.; Wijns, W.; Saraste, A.; Capodanno, D.; Barbato, E.; Funck-Brentano, C.; Prescott, E.; Storey, R.F.; Deaton, C.; Cuisset, T.; et al. 2019 ESC Guidelines for the Diagnosis and Management of Chronic Coronary Syndromes. Eur. Heart J. 2020, 41, 407–477. [Google Scholar] [CrossRef]
  2. Kraler, S.; Mueller, C.; Libby, P.; Bhatt, D.L. Acute Coronary Syndromes: Mechanisms, Challenges, and New Opportunities. Eur. Heart J. 2025, 46, 2866–2889. [Google Scholar] [CrossRef]
  3. Hoffmann, U.; Ferencik, M.; Udelson, J.E.; Picard, M.H.; Truong, Q.A.; Patel, M.R.; Huang, M.; Pencina, M.; Mark, D.B.; Heitner, J.F.; et al. Prognostic Value of Noninvasive Cardiovascular Testing in Patients with Stable Chest Pain: Insights from the PROMISE Trial (Prospective Multicenter Imaging Study for Evaluation of Chest Pain). Circulation 2017, 135, 2320–2332. [Google Scholar] [CrossRef]
  4. Siontis, G.C.; Mavridis, D.; Greenwood, J.P.; Coles, B.; Nikolakopoulou, A.; Jüni, P.; Salanti, G.; Windecker, S. Outcomes of Non-Invasive Diagnostic Modalities for the Detection of Coronary Artery Disease: Network Meta-Analysis of Diagnostic Randomised Controlled Trials. BMJ 2018, 360, k504. [Google Scholar] [CrossRef] [PubMed]
  5. Abbara, S.; Blanke, P.; Maroules, C.D.; Cheezum, M.; Choi, A.D.; Han, B.K.; Marwan, M.; Naoum, C.; Norgaard, B.L.; Rubinshtein, R.; et al. SCCT Guidelines for the Performance and Acquisition of Coronary Computed Tomographic Angiography: A Report of the Society of Cardiovascular Computed Tomography Guidelines Committee. J. Cardiovasc. Comput. Tomogr. 2016, 10, 435–449. [Google Scholar] [CrossRef]
  6. Pontone, G.; Baggiano, A.; Andreini, D.; Guaricci, A.I.; Guglielmo, M.; Muscogiuri, G.; Fusini, L.; Fazzari, F.; Mushtaq, S.; Conte, E.; et al. Stress Computed Tomography Perfusion Versus Fractional Flow Reserve CT Derived in Suspected Coronary Artery Disease: The PERFECTION Study. JACC Cardiovasc. Imaging 2019, 12, 1487–1497. [Google Scholar] [CrossRef]
  7. Mushtaq, S.; Conte, E.; Pontone, G.; Baggiano, A.; Annoni, A.; Formenti, A.; Mancini, M.E.; Guglielmo, M.; Muscogiuri, G.; Tanzilli, A.; et al. State-of-the-Art- Myocardial Perfusion Stress Testing: Static CT Perfusion. J. Cardiovasc. Comput. Tomogr. 2020, 14, 294–302. [Google Scholar] [CrossRef]
  8. Choi, A.D. CT-FFR: Real-World Questions, and the New CAD Imaging Triple Aim. JACC Cardiovasc. Imaging 2023, 16, 1066–1068. [Google Scholar] [CrossRef] [PubMed]
  9. Mesnier, J.; Rodes-Cabau, J. CT-FFR in the TAVR Work-Up: Optimizing the Gatekeeper. JACC Cardiovasc. Interv. 2022, 15, 11. [Google Scholar] [CrossRef]
  10. Khav, N.; Ihdayhid, A.R.; Ko, B. CT-Derived Fractional Flow Reserve (CT-FFR) in the Evaluation of Coronary Artery Disease. Heart Lung Circ. 2020, 29, 1621–1632. [Google Scholar] [CrossRef] [PubMed]
  11. Soschynski, M.; Storelli, R.; Birkemeyer, C.; Hagar, M.T.; Faby, S.; Schwemmer, C.; Nous, F.M.A.; Pugliese, F.; Vliegenthart, R.; Schlett, C.L.; et al. CT Myocardial Perfusion and CT-FFR versus Invasive FFR for Hemodynamic Relevance of Coronary Artery Disease. Radiology 2024, 312, 2. [Google Scholar] [CrossRef] [PubMed]
  12. Moss, A.J.; Williams, M.C.; Newby, D.E.; Nicol, E.D. The Updated NICE Guidelines: Cardiac CT as the First-Line Test for Coronary Artery Disease. Curr. Cardiovasc. Imaging Rep. 2017, 10, 15. [Google Scholar] [CrossRef] [PubMed]
  13. Monti, C.B.; Capra, D.; Zanardo, M.; Guarnieri, G.; Schiaffino, S.; Secchi, F.; Sardanelli, F. CT-Derived Epicardial Adipose Tissue Density: Systematic Review and Meta-Analysis. Eur. J. Radiol. 2021, 143, 109902. [Google Scholar] [CrossRef] [PubMed]
  14. Park, J.-S.; Choi, S.-Y.; Zheng, M.; Yang, H.-M.; Lim, H.-S.; Choi, B.-J.; Yoon, M.-H.; Hwang, G.-S.; Tahk, S.-J.; Shin, J.-H. Epicardial Adipose Tissue Thickness Is a Predictor for Plaque Vulnerability in Patients with Significant Coronary Artery Disease. Atherosclerosis 2013, 226, 134–139. [Google Scholar] [CrossRef]
  15. Mancio, J.; Azevedo, D.; Saraiva, F.; Azevedo, A.I.; Pires-Morais, G.; Leite-Moreira, A.; Falcao-Pires, I.; Lunet, N.; Bettencourt, N. Epicardial Adipose Tissue Volume Assessed by Computed Tomography and Coronary Artery Disease: A Systematic Review and Meta-Analysis. Eur. Heart J.-Cardiovasc. Imaging 2018, 19, 490–497. [Google Scholar] [CrossRef]
  16. Bos, D.; Shahzad, R.; Van Walsum, T.; Van Vliet, L.J.; Franco, O.H.; Hofman, A.; Niessen, W.J.; Vernooij, M.W.; Van Der Lugt, A. Epicardial Fat Volume Is Related to Atherosclerotic Calcification in Multiple Vessel Beds. Eur. Heart J.-Cardiovasc. Imaging 2015, 16, 1264–1269. [Google Scholar] [CrossRef]
  17. Pugliese, L.; Spiritigliozzi, L.; Di Tosto, F.; Ricci, F.; Cavallo, A.U.; Di Donna, C.; De Stasio, V.; Presicce, M.; Benelli, L.; D’Errico, F.; et al. Association of Plaque Calcification Pattern and Attenuation with Instability Features and Coronary Stenosis and Calcification Grade. Atherosclerosis 2020, 311, 150–157. [Google Scholar] [CrossRef]
  18. Villasante Fricke, A.C.; Iacobellis, G. Epicardial Adipose Tissue: Clinical Biomarker of Cardio-Metabolic Risk. Int. J. Mol. Sci. 2019, 20, 5989. [Google Scholar] [CrossRef]
  19. Alberti, K.G.M.M.; Eckel, R.H.; Grundy, S.M.; Zimmet, P.Z.; Cleeman, J.I.; Donato, K.A.; Fruchart, J.-C.; James, W.P.T.; Loria, C.M.; Smith, S.C. Harmonizing the Metabolic Syndrome: A Joint Interim Statement of the International Diabetes Federation Task Force on Epidemiology and Prevention; National Heart, Lung, and Blood Institute; American Heart Association; World Heart Federation; International Atherosclerosis Society; and International Association for the Study of Obesity. Circulation 2009, 120, 1640–1645. [Google Scholar] [CrossRef]
  20. Akoumianakis, I.; Antoniades, C. The Interplay between Adipose Tissue and the Cardiovascular System: Is Fat Always Bad? Cardiovasc. Res. 2017, 113, 999–1008. [Google Scholar] [CrossRef]
  21. Ricci, F.; Benelli, L.; Pasqualetto, M.; Laudazi, M.; Pugliese, L.; Volpe, M.; Cerimele, C.; Di Donna, C.; Garaci, F.; Chiocchi, M. Beyond the Obesity Paradox: Analysis of New Prognostic Factors in Transcatheter Aortic Valve Implantation Procedure. J. Cardiovasc. Dev. Dis. 2024, 11, 368. [Google Scholar] [CrossRef] [PubMed]
  22. Iacobellis, G.; Assael, F.; Ribaudo, M.C.; Zappaterreno, A.; Alessi, G.; Di Mario, U.; Leonetti, F. Epicardial Fat from Echocardiography: A New Method for Visceral Adipose Tissue Prediction. Obes. Res. 2003, 11, 304–310. [Google Scholar] [CrossRef] [PubMed]
  23. Iacobellis, G.; Willens, H.J. Echocardiographic Epicardial Fat: A Review of Research and Clinical Applications. J. Am. Soc. Echocardiogr. 2009, 22, 1311–1319. [Google Scholar] [CrossRef]
  24. Goeller, M.; Achenbach, S.; Marwan, M.; Doris, M.K.; Cadet, S.; Commandeur, F.; Chen, X.; Slomka, P.J.; Gransar, H.; Cao, J.J.; et al. Epicardial Adipose Tissue Density and Volume Are Related to Subclinical Atherosclerosis, Inflammation and Major Adverse Cardiac Events in Asymptomatic Subjects. J. Cardiovasc. Comput. Tomogr. 2018, 12, 67–73. [Google Scholar] [CrossRef]
  25. Shimabukuro, M.; Hirata, Y.; Tabata, M.; Dagvasumberel, M.; Sato, H.; Kurobe, H.; Fukuda, D.; Soeki, T.; Kitagawa, T.; Takanashi, S.; et al. Epicardial Adipose Tissue Volume and Adipocytokine Imbalance Are Strongly Linked to Human Coronary Atherosclerosis. Arterioscler. Thromb. Vasc. Biol. 2013, 33, 1077–1084. [Google Scholar] [CrossRef]
  26. Aldiss, P.; Davies, G.; Woods, R.; Budge, H.; Sacks, H.S.; Symonds, M.E. ‘Browning’ the Cardiac and Peri-Vascular Adipose Tissues to Modulate Cardiovascular Risk. Int. J. Cardiol. 2017, 228, 265–274. [Google Scholar] [CrossRef]
  27. Abazid, R.M.; Smettei, O.A.; Kattea, M.O.; Sayed, S.; Saqqah, H.; Widyan, A.M.; Opolski, M.P. Relation Between Epicardial Fat and Subclinical Atherosclerosis in Asymptomatic Individuals. J. Thorac. Imaging 2017, 32, 378–382. [Google Scholar] [CrossRef]
  28. Franssens, B.T.; Nathoe, H.M.; Visseren, F.L.J.; Van Der Graaf, Y.; Leiner, T.; Algra, A.; Van Der Graaf, Y.; Grobbee, D.E.; Rutten, G.E.H.M.; Visseren, F.L.J.; et al. Relation of Epicardial Adipose Tissue Radiodensity to Coronary Artery Calcium on Cardiac Computed Tomography in Patients at High Risk for Cardiovascular Disease. Am. J. Cardiol. 2017, 119, 1359–1365. [Google Scholar] [CrossRef]
  29. Thanassoulis, G.; Massaro, J.M.; O’Donnell, C.J.; Hoffmann, U.; Levy, D.; Ellinor, P.T.; Wang, T.J.; Schnabel, R.B.; Vasan, R.S.; Fox, C.S.; et al. Pericardial Fat Is Associated With Prevalent Atrial Fibrillation: The Framingham Heart Study. Circ. Arrhythm. Electrophysiol. 2010, 3, 345–350. [Google Scholar] [CrossRef]
  30. Ernault, A.C.; Meijborg, V.M.F.; Coronel, R. Modulation of Cardiac Arrhythmogenesis by Epicardial Adipose Tissue. J. Am. Coll. Cardiol. 2021, 78, 1730–1745. [Google Scholar] [CrossRef] [PubMed]
  31. Gillies, R.J.; Kinahan, P.E.; Hricak, H. Radiomics: Images Are More than Pictures, They Are Data. Radiology 2016, 278, 563–577. [Google Scholar] [CrossRef]
  32. Lambin, P.; Leijenaar, R.T.H.; Deist, T.M.; Peerlings, J.; de Jong, E.E.C.; van Timmeren, J.; Sanduleanu, S.; Larue, R.T.H.M.; Even, A.J.G.; Jochems, A.; et al. Radiomics: The Bridge between Medical Imaging and Personalized Medicine. Nat. Rev. Clin. Oncol. 2017, 14, 749–762. [Google Scholar] [CrossRef]
  33. Hassani, C.; Saremi, F.; Varghese, B.A.; Duddalwar, V. Myocardial Radiomics in Cardiac MRI. Am. J. Roentgenol. 2020, 214, 536–545. [Google Scholar] [CrossRef] [PubMed]
  34. Frix, A.-N.; Cousin, F.; Refaee, T.; Bottari, F.; Vaidyanathan, A.; Desir, C.; Vos, W.; Walsh, S.; Occhipinti, M.; Lovinfosse, P.; et al. Radiomics in Lung Diseases Imaging: State-of-the-Art for Clinicians. J. Pers. Med. 2021, 11, 602. [Google Scholar] [CrossRef] [PubMed]
  35. van Griethuysen, J.J.; Fedorov, A.; Parmar, C.; Hosny, A.; Aucoin, N.; Narayan, V.; Beets-Tan, R.G.; Fillion-Robin, J.-C.; Pieper, S.; Aerts, H.J. Computational Radiomics System to Decode the Radiographic Phenotype. Cancer Res. 2017, 77, e104–e107. [Google Scholar] [CrossRef]
  36. Rafael-Palou, X.; Jimenez-Pastor, A.; Martí-Bonmatí, L.; Muñoz-Nuñez, C.F.; Laudazi, M.; Alberich-Bayarri, Á. Advancing Deep Learning-Based Segmentation for Multiple Lung Cancer Lesions in Real-World Multicenter CT Scans. Eur. Radiol. Exp. 2025, 9, 78. [Google Scholar] [CrossRef] [PubMed]
  37. Neisius, U.; El-Rewaidy, H.; Nakamori, S.; Rodriguez, J.; Manning, W.J.; Nezafat, R. Radiomic Analysis of Myocardial Native T1 Imaging Discriminates Between Hypertensive Heart Disease and Hypertrophic Cardiomyopathy. JACC Cardiovasc. Imaging 2019, 12, 1946–1954. [Google Scholar] [CrossRef]
  38. Mannil, M.; Kato, K.; Manka, R.; Von Spiczak, J.; Peters, B.; Cammann, V.L.; Kaiser, C.; Osswald, S.; Nguyen, T.H.; Horowitz, J.D.; et al. Prognostic Value of Texture Analysis from Cardiac Magnetic Resonance Imaging in Patients with Takotsubo Syndrome: A Machine Learning Based Proof-of-Principle Approach. Sci. Rep. 2020, 10, 20537. [Google Scholar] [CrossRef]
  39. Cavallo, A.U.; Ponsiglione, A.; Pereira, B.; Di Donna, C.; Koltsakis, E.; Vernuccio, F.; Laudazi, M.; Cannella, R.; Fanni, S.C.; D’Antonoli, T.A.; et al. CT and MRI Radiomics in Cardiovascular Risk Prediction: A Systematic Review and Meta-Analysis by the EuSoMII Radiomics Auditing Group. Eur. Radiol. 2025. epub ahead of print. [Google Scholar] [CrossRef] [PubMed]
  40. Cury, R.C.; Abbara, S.; Achenbach, S.; Agatston, A.; Berman, D.S.; Budoff, M.J.; Dill, K.E.; Jacobs, J.E.; Maroules, C.D.; Rubin, G.D.; et al. Coronary Artery Disease—Reporting and Data System (CAD-RADS). JACC Cardiovasc. Imaging 2016, 9, 1099–1113. [Google Scholar] [CrossRef]
  41. Cury, R.C.; Leipsic, J.; Abbara, S.; Achenbach, S.; Berman, D.; Bittencourt, M.; Budoff, M.; Chinnaiyan, K.; Choi, A.D.; Ghoshhajra, B.; et al. CAD-RADSTM 2.0—2022 Coronary Artery Disease—Reporting and Data System An Expert Consensus Document of the Society of Cardiovascular Computed Tomography (SCCT), the American College of Cardiology (ACC), the American College of Radiology (ACR) and the North America Society of Cardiovascular Imaging (NASCI). Radiol. Cardiothorac. Imaging 2022, 4, e220183. [Google Scholar] [CrossRef]
  42. Szczypiński, P.M.; Strzelecki, M.; Materka, A.; Klepaczko, A. MaZda—A Software Package for Image Texture Analysis. Comput. Methods Programs Biomed. 2009, 94, 66–76. [Google Scholar] [CrossRef]
  43. Frank, E.; Hall, M.A.; Witten, I.H. The WEKA Workbench. Online Appendix for “Data Mining: Practical Machine Learning Tools and Techniques”, 4th ed.; Morgan Kaufmann: San Mateo, CA, USA, 2016. [Google Scholar]
  44. López-Ratón, M.; Rodríguez-Álvarez, M.X.; Suárez, C.C.; Sampedro, F.G. OptimalCutpoints: An R Package for Selecting Optimal Cutpoints in Diagnostic Tests. J. Stat. Softw. 2014, 61, 1–36. [Google Scholar] [CrossRef]
  45. Antonopoulos, A.S.; Sanna, F.; Sabharwal, N.; Thomas, S.; Oikonomou, E.K.; Herdman, L.; Margaritis, M.; Shirodaria, C.; Kampoli, A.-M.; Akoumianakis, I.; et al. Detecting Human Coronary Inflammation by Imaging Perivascular Fat. Sci. Transl. Med. 2017, 9, eaal2658. [Google Scholar] [CrossRef]
  46. Sollini, M.; Antunovic, L.; Chiti, A.; Kirienko, M. Towards Clinical Application of Image Mining: A Systematic Review on Artificial Intelligence and Radiomics. Eur. J. Nucl. Med. Mol. Imaging 2019, 46, 2656–2672. [Google Scholar] [CrossRef]
  47. Tanos, V.; Neofytou, M.; Soliman, A.S.A.; Tanos, P.; Pattichis, C.S. Is Computer-Assisted Tissue Image Analysis the Future in Minimally Invasive Surgery? A Review on the Current Status of Its Applications. J. Clin. Med. 2021, 10, 5770. [Google Scholar] [CrossRef]
  48. van Timmeren, J.E.; Cester, D.; Tanadini-Lang, S.; Alkadhi, H.; Baeßler, B. Radiomics in Medical Imaging-“how-to” Guide and Critical Reflection. Insights Imaging 2020, 11, 91. [Google Scholar] [CrossRef] [PubMed]
  49. Chartrand, G.; Cheng, P.M.; Vorontsov, E.; Drozdzal, M.; Turcotte, S.; Pal, C.J.; Kadoury, S.; Tang, A. Deep Learning: A Primer for Radiologists. RadioGraphics 2017, 37, 2113–2131. [Google Scholar] [CrossRef] [PubMed]
  50. Yang, W.; Ding, X.; Yu, Y.; Lan, Z.; Yu, L.; Yuan, J.; Xu, Z.; Sun, J.; Wang, Y.; Zhang, J. Long-Term Prognostic Value of CT-Based High-Risk Coronary Lesion Attributes and Radiomic Features of Pericoronary Adipose Tissue in Diabetic Patients. Clin. Radiol. 2024, 79, 931–940. [Google Scholar] [CrossRef]
  51. Zhu, J.; Zhu, X.; Lv, S.; Guo, D.; Li, H.; Zhao, Z. Incremental Value of Pericoronary Adipose Tissue Radiomics Models in Identifying Vulnerable Plaques. J. Comput. Assist. Tomogr. 2025, 49, 422–430. [Google Scholar] [CrossRef] [PubMed]
  52. Chen, R.; Li, X.; Jia, H.; Feng, C.; Dong, S.; Liu, W.; Lin, S.; Zhu, X.; Xu, Y.; Zhu, Y. Radiomics Analysis of Pericoronary Adipose Tissue From Baseline Coronary Computed Tomography Angiography Enables Prediction of Coronary Plaque Progression. J. Thorac. Imaging 2024, 39, 359–366. [Google Scholar] [CrossRef] [PubMed]
  53. Zhou, K.; Shang, J.; Guo, Y.; Ma, S.; Lv, B.; Zhao, N.; Liu, H.; Zhang, J.; Xv, L.; Wang, Y.; et al. Incremental Diagnostic Value of Radiomics Signature of Pericoronary Adipose Tissue for Detecting Functional Myocardial Ischemia: A Multicenter Study. Eur. Radiol. 2023, 33, 3007–3019. [Google Scholar] [CrossRef]
Jcdd 13 00113 g001
Figure 1. Placement of ROI on epicardial adipose tissue for radiomic feature extraction.
Figure 1. Placement of ROI on epicardial adipose tissue for radiomic feature extraction.
Jcdd 13 00113 g001
Jcdd 13 00113 sch001
Scheme 1. Study Workflow illustrating the radiomic pipeline from image segmentation to machine learning analysis.
Scheme 1. Study Workflow illustrating the radiomic pipeline from image segmentation to machine learning analysis.
Jcdd 13 00113 sch001
Jcdd 13 00113 g002
Figure 2. ROC curve of the EML model.
Figure 2. ROC curve of the EML model.
Jcdd 13 00113 g002
Table 1. Study population inclusion and exclusion criteria.
Table 1. Study population inclusion and exclusion criteria.
Inclusion CriteriaExclusion Criteria
Low to moderate cardiovascular riskHistory of coronary stent implantation or coronary artery bypass surgery
No history of acute coronary syndromePresence of valve prostheses
No history of heart surgeryHigh cardiovascular risk
No history of valvular diseaseHistory of acute coronary syndrome
Presence of valvular disease
Table 2. Clinical characteristics of the study population.
Table 2. Clinical characteristics of the study population.
Clinical CharacteristicsMean ± DS/N (%)
Age52.3 ± 13.3
Gender [Female]52 (41%)
Hypertension75 (59%)
Smoking56 (44%)
Diabetes37 (29%)
Dyslipidemia64 (50%)
CAD-RADSN (%)
013 (10.2%)
113 (10.2%)
227 (21.1%)
333 (25.8%)
4 A/B36 (28.1%)
56 (4.7%)
Table 3. Plaque characteristics of the study population.
Table 3. Plaque characteristics of the study population.
Plaque CharacteristicsN (%)
CAD-RADS ≥ 4
Of which: non-calcified		42 (32.81%)
24 (18.74%)
Plaque in left anterior descending artery
Of which: non-calcified		110 (85.9%)
16 (12.49%)
Plaque in right coronary artery
Of which: non-calcified		87 (68.0%)
9 (7.03%)
Plaque in circumflex artery
Of which: non-calcified		86 (67.2%)
6 (4.69%)
Table 4. Variables (expressed as mean values) selected based on their inter-correlation and correlation with the target variable.
Table 4. Variables (expressed as mean values) selected based on their inter-correlation and correlation with the target variable.
CAD-RADS ≥ 4, Non-CalcifiedOther Patientsp-Value
GeoLminE57,233,67245,722,3310.0025
GeoRm17,398,47316,123,7910.82
S.0.2.Entropy28,376,18726,637,1870.0004
S.3..3.SumVarnc27,117,21828,181,7230.029
S.3..3.Entropy24,817,12321,239,8180.0003
X_Area_S.4.4.5387.2735123.98540.14
Vertl_LngREmph13,189,84714,983,4280.27
WavEnHL_s.158,778,52156,187,2310.0006
WavEnHH_s.144,328,81847,827,3410.015
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.

Share and Cite

MDPI and ACS Style

Di Donna, C.; Cavallo, A.U.; Picchi, E.; Laudazi, M.; Federici, M.; Chiocchi, M.; Garaci, F. Radiomic Assessment of Epicardial Adipose Tissue for the Prediction of Non-Calcified Coronary Atherosclerotic Plaques. J. Cardiovasc. Dev. Dis. 2026, 13, 113. https://doi.org/10.3390/jcdd13030113

AMA Style

Di Donna C, Cavallo AU, Picchi E, Laudazi M, Federici M, Chiocchi M, Garaci F. Radiomic Assessment of Epicardial Adipose Tissue for the Prediction of Non-Calcified Coronary Atherosclerotic Plaques. Journal of Cardiovascular Development and Disease. 2026; 13(3):113. https://doi.org/10.3390/jcdd13030113

Chicago/Turabian Style

Di Donna, Carlo, Armando Ugo Cavallo, Eliseo Picchi, Mario Laudazi, Massimo Federici, Marcello Chiocchi, and Francesco Garaci. 2026. "Radiomic Assessment of Epicardial Adipose Tissue for the Prediction of Non-Calcified Coronary Atherosclerotic Plaques" Journal of Cardiovascular Development and Disease 13, no. 3: 113. https://doi.org/10.3390/jcdd13030113

APA Style

Di Donna, C., Cavallo, A. U., Picchi, E., Laudazi, M., Federici, M., Chiocchi, M., & Garaci, F. (2026). Radiomic Assessment of Epicardial Adipose Tissue for the Prediction of Non-Calcified Coronary Atherosclerotic Plaques. Journal of Cardiovascular Development and Disease, 13(3), 113. https://doi.org/10.3390/jcdd13030113

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop