Voxel-based correction of CT attenuations for accurate quantification of coronary artery calcification in low tube voltage scans with deep learning reconstruction

A novel voxel-based attenuation correction method, derived from phantom calibration, was developed to address overestimation bias in coronary artery calcium (CAC) quantification using 80 ​kV scans with deep learning reconstruction. In a prospective clinical study of 190 patients, this approach eliminated significant differences in Agatston score, calcium volume, and mass compared to standard 120 ​kV imaging (all P ​> ​0.05), while reducing risk category misclassification from 20.53 ​% to 5.79…

Read the full article on journalofcardiovascularct.com