The correlation of deep learning-based CAD-RADS evaluated by coronary computed tomography angiography with breast arterial calcification on mammography

Zhang

Jin

et al. 2021

BMC Cardiovasc Disord

Self Cite

Background The study sought to compare Coronary Artery Disease Reporting and Data System (CAD-RADS) classification with traditional coronary artery disease (CAD) classifications and Duke Prognostic CAD Index for predicting the risk of all-cause mortality in patients with suspected CAD. Methods 9625 consecutive suspected CAD patients were assessed by coronary CTA for CAD-RADS classification, traditional CAD classifications and Duke Prognostic CAD Index. Kaplan–Meier and multivariable Cox models were used to estimate all-cause mortality. Discriminatory ability of classifications was assessed using time dependent receiver-operating characteristic (ROC) curves and The Hosmer–Lemeshow goodness-of-fit test was employed to evaluate calibration. Results A total of 540 patients died from all causes with a median follow-up of 4.3 ± 2.1 years. Kaplan–Meier survival curves showed the cumulative events increased significantly associated with CAD-RADS, three traditional CAD classifications and Duke Prognostic CAD Index. In multivariate Cox regressions, the risk for the all-cause death increased from HR 0.861 (95% CI 0.420–1.764) for CAD-RADS 1 to HR 2.761 (95% CI 1.961–3.887) for CAD-RADS 4B&5, using CAD-RADS 0 as the reference group. The relative HRs for all-cause death increased proportionally with the grades of the three traditional CAD classifications and Duke Prognostic CAD Index. The area under the time dependent ROC curve for prediction of all-cause death was 0.7917, 0.7805, 0.7991for CAD-RADS in 1 year, 3 year, 5 year, respectively, which was non-inferior to the traditional CAD classifications and Duke Prognostic CAD Index. Conclusions The CAD-RADS classification provided important prognostic information for patients with suspected CAD with noninvasive evaluation, which was non-inferior than Duke Prognostic CAD Index and traditional stenosis-based grading schemes in prognostic value of all-cause mortality. Traditional and simplest CAD classification should be preferable, given the more number of groups and complexity of CAD-RADS and Duke prognostic index, without using more time consuming classification.

Section: Discussionmentioning

confidence: 99%

Prognostic value of CAD-RADS classification by coronary CTA in patients with suspected CAD

Zhang

Jin

et al. 2021

BMC Cardiovasc Disord

Self Cite

“…However, compared with the Duke Prognostic CAD Index, CAD-RADS classi cation is more concise and thus is more conducive to enhance communication between interpreting and referring clinicians. Moreover, automated classi cation of CAD-RADS based on structured reporting systems may improve data quality and then establishing standard databases with education, patient care and research purposes [21][22][23].…”

Section: Discussionmentioning

confidence: 99%

Prognostic Value of CAD-RADS Classification by Coronary CTA in Patients With Suspected CAD

Zhang

et al. 2021

Preprint

Self Cite

Background: The study sought to compare Coronary Artery Disease Reporting and Data System (CAD-RADS) classification with traditional coronary artery disease (CAD) classifications and Duke Prognostic CAD Index for predicting the risk of all-cause mortality in patients with suspected CAD.Methods: 9625 consecutive suspected CAD patients were assessed by coronary CTA for CAD-RADS classification, traditional CAD classifications and Duke Prognostic CAD Index. Kaplan-Meier and multivariable Cox models were used to estimate all-cause mortality. Discriminatory ability of classifications was assessed using receiver-operating characteristic (ROC) curves and the Hosmer-Lemeshow goodness-of-fit test.Results: A total of 540 patients died from all causes with a median follow-up of 4.3 ±2.1 years. Kaplan-Meier survival curves showed the cumulative events increased significantly associated with CAD-RADS, three traditional CAD classifications and Duke Prognostic CAD Index. In multivariate Cox regressions, the risk for the all-cause death increased from HR 0.861 (95% CI: 0.420 to 1.764) for CAD-RADS 1 to HR 2.761 (95% CI: 1.961 to 3.887) for CAD-RADS 4B&5, using CAD-RADS 0 as the reference group. The relative HR s for all-cause death increased proportionally with the grades of the three traditional CAD classifications and Duke Prognostic CAD Index. The ROC curve for prediction of all cause death was 0.7927 for CAD-RADS, which was non-inferior to the traditional CAD classifications and Duke Prognostic CAD Index.Conclusions: CAD-RADS classification provided important prognostic information for patients with suspected CAD with noninvasive evaluation, which was non-inferior than Duke Prognostic CAD Index and traditional stenosis-based grading schemes.

“…The patients in the test set were under ICA examination with an interval of less than 30 days after CCTA procedure. We have previously reported the validation of our deep learning system [13,14]. Before training, the aorta, coronary artery and plaques were labeled on each image by a multi-layer manually annotation system consisting of multiple layers of trained graders.…”

Section: Deep Learningmentioning

confidence: 99%

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

Xiao

et al. 2021

Preprint

Self Cite

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.