Repeatability of Radiomic Features of Brown Adipose Tissue.

Abstract

The aim of this study was to assess the repeatability of activated brown adipose tissue (BAT) radiomic features. To decipher radiomic features that may provide useful information on BAT, the impact of reconstruction methods and imaging modality choice was also evaluated. <b>Methods:</b> Twenty-seven healthy adults enrolled in this study. After a cooling procedure to activate BAT, volunteers underwent ¹⁸F-FDG imaging. Participants underwent repeat imaging using the same imaging protocols and a similar ¹⁸F-FDG dose within 14 d. Active BAT was segmented using the BARCIST 1.0 methods. Radiomic features were extracted from each region of interest on high-definition PET (HD PET), non-HD PET, and CT images. Lin's concordance correlation coefficient was used to estimate the repeatability of the extracted radiomic features. To determine whether BAT radiomic feature repeatability correlates with BAT SUV_max repeatability, participants were stratified based on the relative difference in SUV_max between sessions. Non-HD PET repeatable features were clustered together using hierarchical clustering, and the normalized dynamic range of each feature was computed to identify the most informative feature within each cluster. <b>Results:</b> Eighteen of the 27 volunteers had sufficient BAT activity for radiomic analysis. Sixty-six HD PET, 66 non-HD PET, and 6 CT features showed high repeatability (concordance correlation coefficient ≥ 0.80). Feature repeatability was significantly higher for PET than for CT, but there was no statistically significant difference between HD and non-HD PET in radiomic feature repeatability. The repeatability of radiomic features extracted from each modality and reconstruction method type followed the trend in SUV_max, as participants with lower relative differences in SUV_max between initial and repeated imaging sessions had higher radiomic feature repeatability. Hierarchical clustering of the high-repeatability PET features resulted in 10 highly correlated clusters (<i>R</i>² ≥ 0.95). Seven features, including SUV_max, did not cluster with any other features. <b>Conclusion:</b> Several clusters of highly repeatable BAT radiomic features derived from ¹⁸F-FDG PET/CT appear to provide information regarding BAT activity distinct from SUV_max These features might be explored as quantitative imaging biomarkers of BAT activity in future studies.