Clinical Evaluation of Automatic Coronary Artery Disease Reporting and Data System (CAD-RADS TM) in Coronary CT Angiography Using Convolutional Neural Networks

Background: The coronary artery disease reporting and data system (CAD-RADSTM) was recently introduced for standard reporting. We aimed to evaluate the utility of an automatic post-processing and reporting system based on CAD-RADS in suspected CAD patients.Methods: The clinical evaluation was encompassed 346 patients who underwent coronary computed tomography angiography (CCTA). We compared deep learning (DL)-based CCTA with Readers for classification of CAD-RADS with commercially-available automated segmentation and manual post-processing in a prospective validation cohort. Results: Compared with invasive coronary angiography (ICA), the sensitivity, specificity, positive predictive value, negative predictive value and accuracy of DL model for diagnosis of CAD were 79.02%, 86.52%, 89.50%, 73.94% and 82.08%, respectively. There was no significant difference between the DL-based and Readers-based CAD-RADS grading in CCTA. The consistency test showed that the Kappa value between the model and Readers was 0.775 (95% CI: 0.728-0.823, P < 0.001), 0.802 (95% CI: 0.756-0.847, P<0.001), and 0.796 (95% CI: 0.750-0.843, P < 0.001), respectively. This system reduces the time consumed from 14.97 ± 1.80 min to 5.02 ± 0.8 min (P < 0.001).Conclusion: The standardized report of DL-based CAD-RADS in CCTA can accurately evaluate suspected CAD patients with time-saving, and has good consistency with the radiologists.