Periaortic adipose radiomics texture features associated with increased coronary calcium score—first results on a photon-counting-CT

Abstract

Background Cardiovascular diseases remain the world’s primary cause of death. The identification and treatment of patients at risk of cardiovascular events thus are as important as ever. Adipose tissue is a classic risk factor for cardiovascular diseases, has been linked to systemic inflammation, and is suspected to contribute to vascular calcification. To further investigate this issue, the use of texture analysis of adipose tissue using radiomics features could prove a feasible option. Methods In this retrospective single-center study, 55 patients (mean age 56, 34 male, 21 female) were scanned on a first-generation photon-counting CT. On axial unenhanced images, periaortic adipose tissue surrounding the thoracic descending aorta was segmented manually. For feature extraction, patients were divided into three groups, depending on coronary artery calcification (Agatston Score 0, Agatston Score 1–99, Agatston Score ≥ 100). 106 features were extracted using pyradiomics. R statistics was used for statistical analysis, calculating mean and standard deviation with Pearson correlation coefficient for feature correlation. Random Forest classification was carried out for feature selection and Boxplots and heatmaps were used for visualization. Additionally, monovariable logistic regression predicting an Agatston Score > 0 was performed, selected features were tested for multicollinearity and a 10-fold cross-validation investigated the stability of the leading feature. Results Two higher-order radiomics features, namely “glcm_ClusterProminence” and “glcm_ClusterTendency” were found to differ between patients without coronary artery calcification and those with coronary artery calcification (Agatston Score ≥ 100) through Random Forest classification. As the leading differentiating feature “glcm_ClusterProminence” was identified. Conclusion Changes in periaortic adipose tissue texture seem to correlate with coronary artery calcium score, supporting a possible influence of inflammatory or fibrotic activity in perivascular adipose tissue. Radiomics features may potentially aid as corresponding biomarkers in the future.

Analysis of Epicardial Adipose Tissue Texture in Relation to Coronary Artery Calcification in PCCT: The EAT Signature!

“…Radiomics features for differentiation based on the periaortic adipose tissue textures were identified using Random Forest-based feature selection on the Groups of Agatston score 0 and ≥100 and investigated in the Group of 1-99 for internal validation. It was found that two radiomics features differed between the groups, one of them significantly [17]. While the investigated adipose tissues as well as the identified radiomics features differ from our study, it nevertheless supports our findings, as it underlines the feasibility of distinguishing between patients with and without CAC using radiomics texture features of adipose tissues, indicating a potential underlying diffuse fibrotic or inflammatory reaction, which can be detected by texture analysis.…”

“…To find ways to extend the diagnostics of such patients at risk, research on EAT properties with potential diagnostic use has increased over the last few years. While these studies have often been based on the volume [14,15] of the adipose tissue, more recent studies have conducted radiomics examinations of perivascular intrathoracic adipose tissue with first promising results [16,17].…”

Next generation phenotyping for diagnosis and phenotype–genotype correlations in Kabuki syndrome

“…Gray-Level Co-occurrence Matrix (GLCM) methods, as proposed by Haralick 39 , are based on the estimation of the second-order joint conditional probability density functions, which characterize the spatial relationships between pixels. GLCM is commonly used in texture analysis 40 , 41 , for instance in radiomics on CT-scan or MRI images 42 – 44 or for skin texture assessment 45 . In GLCM, the co-occurrence matrix contains information on entropy, homogeneity, contrast, energy and correlation between pixels.…”