Machine learning-based prediction of insufficient contrast enhancement in coronary computed tomography angiography.

OBJECTIVES: Patient-tailored contrast delivery protocols strongly reduce the total iodine load and in general improve image quality in CT coronary angiography (CTCA). We aim to use machine learning to predict cases with insufficient contrast enhancement and to identify parameters with the highest predictive value. METHODS: Machine learning models were developed using data from 1,447 CTs. We included patient features, imaging settings, and test bolus features. The models were trained to predict CTCA images with a mean attenuation value in the ascending aorta below 400 HU. The accuracy was assessed by the area under the receiver operating characteristic (AUROC) and precision-recall curves (AUPRC). Shapley Additive exPlanations was used to assess the impact of features on the prediction of insufficient contrast enhancement. RESULTS: A total of 399 out of 1,447 scans revealed attenuation values in the ascending aorta below 400 HU. The best model trained using only patient features and CT settings achieved an AUROC of 0.78 (95% CI: 0.73-0.83) and AUPRC of 0.65 (95% CI: 0.58-0.71). With the inclusion of the test bolus features, it achieved an AUROC of 0.84 (95% CI: 0.81-0.87), an AUPRC of 0.71 (95% CI: 0.66-0.76), and a sensitivity of 0.66 and specificity of 0.88. The test bolus' peak height was the feature that impacted low attenuation prediction most. CONCLUSION: Prediction of insufficient contrast enhancement in CT coronary angiography scans can be achieved using machine learning models. Our experiments suggest that test bolus features are strongly predictive of low attenuation values and can be used to further improve patient-specific contrast delivery protocols. KEY POINTS: • Prediction of insufficient contrast enhancement in CT coronary angiography scans can be achieved using machine learning models. • The peak height of the test bolus curve is the most impacting feature for the best performing model.

The impact and challenges of implementing CTCA according to the 2019 ESC guidelines on chronic coronary syndromes: a survey and projection of CTCA services in the Netherlands.

BACKGROUND: The 2019 ESC-guidelines on chronic coronary syndromes (ESC-CCS) recommend computed tomographic coronary angiography (CTCA) or non-invasive functional imaging instead of exercise ECG as initial test to diagnose obstructive coronary artery disease. Since impact and challenges of these guidelines are unknown, we studied the current utilisation of CTCA-services, status of CTCA-protocols and modeled the expected impact of these guidelines in the Netherlands. METHODS AND RESULTS: A survey on current practice and CTCA utilisation was disseminated to every Dutch hospital organisation providing outpatient cardiology care and modeled the required CTCA capacity for implementation of the ESC guideline, based on these national figures and expert consensus. Survey response rate was 100% (68/68 hospital organisations). In 2019, 63 hospital organisations provided CTCA-services (93%), CTCA was performed on 99 CTCA-capable CT-scanners, and 37,283 CTCA-examinations were performed. Between the hospital organisations, we found substantial variation considering CTCA indications, CTCA equipment and acquisition and reporting standards. To fully implement the new ESC guideline, our model suggests that 70,000 additional CTCA-examinations would have to be performed in the Netherlands. CONCLUSIONS: Despite high national CTCA-services coverage in the Netherlands, a substantial increase in CTCA capacity is expected to be able to implement the 2019 ESC-CCS recommendations on the use of CTCA. Furthermore, the results of this survey highlight the importance to address variations in image acquisition and to standardise the interpretation and reporting of CTCA, as well as to establish interdisciplinary collaboration and organisational alignment.

CTCA for detection of significant coronary artery disease in routine TAVI work-up : A systematic review and meta-analysis.

Transcatheter aortic valve implantation (TAVI) has evolved to standard treatment of severe aortic stenosis in patients with an intermediate to high surgical risk. Computed tomography coronary angiography (CTCA) could partially replace invasive coronary angiography to diagnose significant coronary artery disease in the work-up for TAVI. A literature search was performed in MEDLINE and EMBASE for papers comparing CTCA and coronary angiography in TAVI candidates. The primary endpoint was the diagnostic accuracy of CTCA, compared to coronary angiography, for detection of significant (>50% diameter stenosis) coronary artery disease, measured as sensitivity, specificity, positive-(PPV) and negative predictive value (NPV). Seven studies were included, with a cumulative sample size of 1,275 patients. The patient-based pooled sensitivity, specificity, PPV and NPV were 95, 65, 71 and 94% respectively. Quality assessment revealed excellent and good quality in terms of applicability and risk of bias respectively, with the main concern being patient selection. In conclusion, on the basis of a significance cut-off value of 50% diameter stenosis, CTCA provides acceptable diagnostic accuracy for the exclusion of coronary artery disease in patients referred for TAVI. Using the routinely performed preoperative computed tomography scans as a gatekeeper for coronary angiography could decrease additional coronary angiographies by 37% in this high-risk and fragile population.