Search

Background Scar burden with late gadolinium enhancement (LGE) cardiac MRI (CMR) predicts arrhythmic events in patients with postinfarction in single-center studies. However, LGE analysis requires experienced human observers, is time consuming, and introduces variability. Purpose To test whether postinfarct scar with LGE CMR can be quantified fully automatically by machines and to compare the ability of LGE CMR scar analyzed by humans and machines to predict arrhythmic events. Materials and Methods This study is a retrospective analysis of the multicenter, multivendor CarDiac MagnEtic Resonance for Primary Prevention Implantable CardioVerter DebrillAtor ThErapy (DERIVATE) registry. Patients with chronic heart failure, echocardiographic left ventricular ejection fraction (LVEF) of less than 50%, and LGE CMR were recruited (from January 2015 through December 2020). In the current study, only patients with ischemic cardiomyopathy were included. Quantification of total, dense, and nondense scars was carried out by two experienced readers or a Ternaus network, trained and tested with LGE images of 515 and 246 patients, respectively. Univariable and multivariable Cox analyses were used to assess patient and cardiac characteristics associated with a major adverse cardiac event (MACE). Area under the receiver operating characteristic curve (AUC) was used to compare model performances. Results In 761 patients (mean age, 65 years ± 11, 671 men), 83 MACEs occurred. With use of the testing group, univariable Cox-analysis found New York Heart Association class, left ventricle volume and/or function parameters (by echocardiography or CMR), guideline criterion (LVEF of ≤35% and New York Heart Association class II or III), and LGE scar analyzed by humans or the machine-learning algorithm as predictors of MACE. Machine-based dense or total scar conferred incremental value over the guideline criterion for the association with MACE (AUC: 0.68 vs 0.63, P = .02 and AUC: 0.67 vs 0.63, P = .01, respectively). Modeling with competing risks yielded for dense and total scar (AUC: 0.67 vs 0.61, P = .01 and AUC: 0.66 vs 0.61, P = .005, respectively). Conclusion In this analysis of the multicenter CarDiac MagnEtic Resonance for Primary Prevention Implantable CardioVerter DebrillAtor ThErapy (DERIVATE) registry, fully automatic machine learning-based late gadolinium enhancement analysis reliably quantifies myocardial scar mass and improves the current prediction model that uses guideline-based risk criteria for implantable cardioverter defibrillator implantation. ClinicalTrials.gov registration no.: NCT03352648 Published under a CC BY 4.0 license. Supplemental material is available for this article. ispartof: Radiology vol:307 issue:3 pages:e222239- ispartof: location:United States status: published

Aims Right ventricular systolic dysfunction (RVSD) is an important determinant of outcomes in heart failure (HF) cohorts. While the quantitative assessment of RV function is challenging using 2D-echocardiography, cardiac magnetic resonance (CMR) is the gold standard with its high spatial resolution and precise anatomical definition. We sought to investigate the prognostic value of CMR-derived RV systolic function in a large cohort of HF with reduced ejection fraction (HFrEF). Methods and results Study cohort comprised of patients enrolled in the CarDiac MagnEtic Resonance for Primary Prevention Implantable CardioVerter DefibrillAtor ThErapy registry who had HFrEF and had simultaneous baseline CMR and echocardiography (n = 2449). RVSD was defined as RV ejection fraction (RVEF) Conclusion RV systolic dysfunction is an independent predictor of ACM in HFrEF, with a more pronounced prognostic value in select subgroups, likely reflecting the importance of RVSD in the early stages of HF progression.

Background and aims Artificial intelligence (AI) is increasing its role in diagnosis of patients with suspicious coronary artery disease. The aim of this manuscript is to develop a deep convolutional neural network (CNN) to classify coronary computed tomography angiography (CCTA) in the correct Coronary Artery Disease Reporting and Data System (CAD-RADS) category. Methods Two hundred eighty eight patients who underwent clinically indicated CCTA were included in this single-center retrospective study. The CCTAs were stratified by CAD-RADS scores by expert readers and considered as reference standard. A deep CNN was designed and tested on the CCTA dataset and compared to on-site reading. The deep CNN analyzed the diagnostic accuracy of the following three Models based on CAD-RADS classification: Model A (CAD-RADS 0 vs CAD-RADS 1–2 vs CAD-RADS 3,4,5), Model 1 (CAD-RADS 0 vs CAD-RADS>0), Model 2 (CAD-RADS 0–2 vs CAD-RADS 3–5). Time of analysis for both physicians and CNN were recorded. Results Model A showed a sensitivity, specificity, negative predictive value, positive predictive value and accuracy of 47%, 74%, 77%, 46% and 60%, respectively. Model 1 showed a sensitivity, specificity, negative predictive value, positive predictive value and accuracy of 66%, 91%, 92%, 63%, 86%, respectively. Conversely, Model 2 demonstrated the following sensitivity, specificity, negative predictive value, positive predictive value and accuracy: 82%, 58%, 74%, 69%, 71%, respectively. Time of analysis was significantly lower using CNN as compared to on-site reading (530.5 ± 179.1 vs 104.3 ± 1.4 sec, p=0.01) Conclusions Deep CNN yielded accurate automated classification of patients with CAD-RADS.

Cardiac magnetic resonance (CMR) is the best-suited cardiac imaging modality to provide reliable and reproducible information regarding cardiac volumes, function, and tissue characterization. In clinical practice, artificial intelligence (AI) in CMR can be applied to the whole process, ranging from sequence reconstruction, image analysis, and reporting of findings. In sequence reconstruction, the application of AI is mainly focused on the speed of reconstruction, while in image analysis and reporting AI is primarily aimed at automating the process of segmentation of both ventricles as well as fibrotic tissue. Within the realm of tissue characterization, AI can also be helpful in the depiction of tissue abnormalities from noncontrast images. Finally, AI can be useful for prognostic stratification.

Stress computed tomography perfusion (Stress-CTP) and computed tomography-derived fractional flow reserve (FFRCT) are functional techniques that can be added to coronary computed tomography angiography (cCTA) to improve the management of patients with suspected coronary artery disease (CAD). This retrospective analysis from the PERFECTION study aims to assess the impact of their availability on the management of patients with suspected CAD scheduled for invasive coronary angiography (ICA) and invasive FFR. The management plan was defined as optimal medical therapy (OMT) or revascularization and was recorded for the following strategies: cCTA alone, cCTA+FFRCT, cCTA+Stress-CTP and cCTA+FFRCT+Stress-CTP. In 291 prospectively enrolled patients, cCTA+FFRCT, cCTA+Stress-CTP and cCTA+FFRCT+Stress-CTP showed a similar rate of reclassification of cCTA findings when FFRCT and Stress-CTP were added to cCTA. cCTA, cCTA+FFRCT, cCTA+Stress-CTP and cCTA+FFRCT+Stress-CTP showed a rate of agreement versus the final therapeutic decision of 63%, 71%, 89%, 84% (cCTA+Stress-CTP and cCTA+FFRCT+Stress-CTP vs cCTA and cCTA+FFRCT: p &lt, 0.01), respectively, and a rate of agreement in terms of the vessels to be revascularized of 57%, 64%, 74%, 71% (cCTA+Stress-CTP and cCTA+FFRCT+Stress-CTP vs cCTA and cCTA+FFRCT: p &lt, 0.01), respectively, with an effective radiation dose (ED) of 2.9 &plusmn, 1.3 mSv, 2.9 &plusmn, 1.3 mSv, 5.9 &plusmn, 2.7 mSv, and 3.1 &plusmn, 2.1 mSv. The addition of FFRCT and Stress-CTP improved therapeutic decision-making compared to cCTA alone, and a sequential strategy with cCTA+FFRCT+Stress-CTP represents the best compromise in terms of clinical impact and radiation exposure.

Stress computed tomography perfusion (Stress-CTP) and computed tomography-derived fractional flow reserve (FFRCT) are functional techniques that can be added to coronary computed tomography angiography (cCTA) to improve the management of patients with suspected coronary artery disease (CAD). This retrospective analysis from the PERFECTION study aims to assess the impact of their availability on the management of patients with suspected CAD scheduled for invasive coronary angiography (ICA) and invasive FFR. The management plan was defined as optimal medical therapy (OMT) or revascularization and was recorded for the following strategies: cCTA alone, cCTA+FFRCT, cCTA+Stress-CTP and cCTA+FFRCT+Stress-CTP. In 291 prospectively enrolled patients, cCTA+FFRCT, cCTA+Stress-CTP and cCTA+FFRCT+Stress-CTP showed a similar rate of reclassification of cCTA findings when FFRCT and Stress-CTP were added to cCTA. cCTA, cCTA+FFRCT, cCTA+Stress-CTP and cCTA+FFRCT+Stress-CTP showed a rate of agreement versus the final therapeutic decision of 63%, 71%, 89%, 84% (cCTA+Stress-CTP and cCTA+FFRCT+Stress-CTP vs cCTA and cCTA+FFRCT: p < 0.01), respectively, and a rate of agreement in terms of the vessels to be revascularized of 57%, 64%, 74%, 71% (cCTA+Stress-CTP and cCTA+FFRCT+Stress-CTP vs cCTA and cCTA+FFRCT: p < 0.01), respectively, with an effective radiation dose (ED) of 2.9 ± 1.3 mSv, 2.9 ± 1.3 mSv, 5.9 ± 2.7 mSv, and 3.1 ± 2.1 mSv. The addition of FFRCT and Stress-CTP improved therapeutic decision-making compared to cCTA alone, and a sequential strategy with cCTA+FFRCT+Stress-CTP represents the best compromise in terms of clinical impact and radiation exposure.

The increased number of patients with coronary artery disease (CAD) is of great clinical relevance and involves a large burden of the healthcare system. The management of these patients is focused on relieving symptoms and improving clinical outcomes. Therefore, the ideal test would provide the correct diagnosis and actionable information. To this aim, several non-invasive functional imaging modalities are usually used as gatekeeper to invasive coronary angiography, but their diagnostic performance remains low with limited accuracy when compared to obstructive CAD at the time of invasive coronary angiography or invasive fractional flow reserve (FFR) assessment. For these reasons, an urgent need for non-invasive techniques that evaluate both the functional and morphological severity of CAD is growing. Coronary computed tomography angiography (CCTA) has emerged as a unique non-invasive technique providing coronary artery anatomic imaging. More recently, the evaluation of FFR with CCTA (FFRCT) has demonstrated high diagnostic performance compared to invasive FFR. Moreover, this tool has been proven to be more cost-effective than standard diagnostic pathways in large prospective multicenter trials, and to have a prognostic role. Additionally, stress myocardial computed tomography perfusion (stress CTP) represents a novel tool for the diagnosis of ischemia with high diagnostic accuracy. With advances in technical development, both static and dynamic computed tomography myocardial perfusion protocols offer functional assessment with an acceptable increase in radiation exposure. Compared to other imaging techniques, both FFRCT and stress CTP allow the combination of the anatomical evaluation of coronary arteries and the functional relevance of coronary artery lesions, having the potential to revolutionize the diagnostic paradigm of suspected CAD. FFRCT and stress CTP should be integrated in diagnostic pathways of patients with stable CAD and will likely result in a decrease of invasive diagnostic procedures and costs.