Influence of computed tomography reconstruction algorithms on coronary artery calcium scores and reader agreement

Deep learning–based image reconstruction significantly improved the reproducibility of coronary artery calcium scoring compared with filtered back projection and iterative reconstruction. In 120 patients scored independently by two blinded readers, deep learning reconstruction demonstrated the highest inter- and intra-reader agreement, minimized reader-dependent bias, and yielded the greatest reader confidence. These advantages were consistent across patient characteristics and resulted in incre…

Read the full article on journalofcardiovascularct.com