Cine-cardiac magnetic resonance to distinguish between ischemic and non-ischemic cardiomyopathies: a machine learning approach.

OBJECTIVE: This work aimed to derive a machine learning (ML) model for the differentiation between ischemic cardiomyopathy (ICM) and non-ischemic cardiomyopathy (NICM) on non-contrast cardiovascular magnetic resonance (CMR). METHODS: This retrospective study evaluated CMR scans of 107 consecutive patients (49 ICM, 58 NICM), including atrial and ventricular strain parameters. We used these data to compare an explainable tree-based gradient boosting additive model with four traditional ML models for the differentiation of ICM and NICM. The models were trained and internally validated with repeated cross-validation according to discrimination and calibration. Furthermore, we examined important variables for distinguishing between ICM and NICM. RESULTS: A total of 107 patients and 38 variables were available for the analysis. Of those, 49 were ICM (34 males, mean age 60 ± 9 years) and 58 patients were NICM (38 males, mean age 56 ± 19 years). After 10 repetitions of the tenfold cross-validation, the proposed model achieved the highest area under curve (0.82, 95% CI [0.47-1.00]) and lowest Brier score (0.19, 95% CI [0.13-0.27]), showing competitive diagnostic accuracy and calibration. At the Youden's index, sensitivity was 0.72 (95% CI [0.68-0.76]), the highest of all. Analysis of predictions revealed that both atrial and ventricular strain CMR parameters were important for the identification of ICM patients. CONCLUSION: The current study demonstrated that using a ML model, multi chamber myocardial strain, and function on non-contrast CMR parameters enables the discrimination between ICM and NICM with competitive diagnostic accuracy. CLINICAL RELEVANCE STATEMENT: A machine learning model based on non-contrast cardiovascular magnetic resonance parameters may discriminate between ischemic and non-ischemic cardiomyopathy enabling wider access to cardiovascular magnetic resonance examinations with lower costs and faster imaging acquisition. KEY POINTS: • The exponential growth in cardiovascular magnetic resonance examinations may require faster and more cost-effective protocols. • Artificial intelligence models can be utilized to distinguish between ischemic and non-ischemic etiologies. • Machine learning using non-contrast CMR parameters can effectively distinguish between ischemic and non-ischemic cardiomyopathies.

Woven EndoBridge Device for Unruptured Wide-Neck Bifurcation Aneurysm: A Multicenter 5-Year Follow-up.

BACKGROUND AND OBJECTIVES: This multicenter study aimed to assess the safety and efficacy of the Woven EndoBridge (WEB) device for treating unruptured wide-neck intracranial bifurcation aneurysms (WIBAs) with short-, mid-, and long-term follow-ups (FUPs). METHODS: Consecutive patients with unruptured WIBAs treated with WEB between December 2014 and January 2018 were included. Patient, aneurysm, and device characteristics were collected and analyzed retrospectively. Morbidity and mortality rates were determined by collecting intraprocedural, periprocedural, and delayed complications. Aneurysm occlusion was assessed at 1, 3, and 5 years using a 3-grade scale: complete occlusion, neck remnant, and residual aneurysm. Complete occlusion and neck remnant were considered as adequate occlusion. Patients who received re-treatment were also evaluated. RESULTS: The study included 104 consecutive patients (55.8% female, mean age 58.6 ± 11.8 years). Aneurysm maximum size, neck, and dome-to-neck mean were, respectively, 6.9 ± 2.1 mm, 4.5 ± 1.2 mm, and 1.4 ± 0.3 mm. One-year FUP was collected for 95 patients, and 3- and 5-year FUPs were collected for 83 patients. Adequate occlusion was observed at 1-year FUP in 90.5% (86/95), 91.6% (76/83) was observed at 3-year FUP, and 92.8% (77/83) at 5-year FUP. None of the aneurysms bled after treatment. During FUP, 6/83 patients (7.2%) were re-treated for residual aneurysm. Morbidity and mortality rates closely related to aneurysm occlusion were 0% (0/104). CONCLUSION: The WEB device was safe and effective for treating unruptured WIBAs, both in short-term and long-term FUPs.

Base-to-apex Gradient Pattern Assessed by Cardiovascular Magnetic Resonance in Takotsubo Cardiomyopathy.

OBJECTIVES: The purpose of this study was to investigate the base-to-apex gradient strain pattern as a noncontrast cardiovascular magnetic resonance (CMR) parameter in patients with Takotsubo cardiomyopathy (TTC) and determine whether this pattern may help discriminate TTC from patients with anterior myocardial infarction (AMI). MATERIALS AND METHODS: A total of 80 patients were included in the analysis: 30 patients with apical ballooning TTC and 50 patients with AMI. Global and regional ventricular function, including longitudinal (LS), circumferential (CS), and radial strain (RS), were assessed using CMR. The base-to-apex LS, RS, and CS gradients, defined as the peak gradient difference between averaged basal and apical strain, were calculated. RESULTS: The base-to-apex RS gradient was impaired in TTC patients compared with the AMI group (14.04 ± 15.50 vs. -0.43 ± 11.59, P=0.001). Conversely, there were no significant differences in the base-to-apex LS and CS gradients between the AMI group and TTC patients (0.14 ± 2.71 vs. -1.5 ± 3.69, P=0.054: -0.99 ± 6.49 vs. ±1.4 ± 5.43, P=0.47, respectively). Beyond the presence and extension of LGE, base-to-apex RS gradient was the only independent discriminator between TTC and AMI (OR 1.28; 95% CI 1.08, 1.52, P=0.006) in multivariate logistic regression analysis. CONCLUSION: The findings of this study suggest that the pattern of regional myocardial strain impairment could serve as an additional noncontrast CMR tool to refine the diagnosis of TTC. A pronounced base-to-apex RS gradient may be a specific left ventricle strain pattern of TTC.

Obstructive and Nonobstructive Hypertrophic Cardiomyopathy: Differences in Global and Segmental Myocardial Strain by Cardiac Magnetic Resonance Feature Tracking.

PURPOSE: To evaluate any significant differences in myocardial strain between hypertrophic obstructive cardiomyopathy (HOCM) and nonobstructive ones (HNCM), as assessed by cardiac magnetic resonance feature tracking (CMR-FT). MATERIALS AND METHODS: A total of 17 patients (mean age: 54±14 y) with echocardiographic diagnosis of HOCM (left ventricular outflow tract obstruction peak gradient ≥30 mm Hg), 19 patients (mean age: 49±16 y) with HNCM (peak gradient <30 mm Hg), and 18 age-matched and gender-matched healthy controls (mean age: 42±14 y). All patients underwent cardiac MRI with SSFP-cine to assess left ventricular global and segmental strain analysis by CMR-FT. Late gadolinium enhancement (LGE) sequences were used for semiautomatic quantification of LGE volume, mass, and percentage. RESULTS: The magnitude of global radial, circumferential, and longitudinal strain as well as strain rate were significantly lower in all patients in comparison to controls (P<0.001), except for radial and circumferential strain between HOCM and controls (P=0.270; P=0.154). The latter strain parameters were significantly higher in HOCM than HNCM (radial strain: 31.67±7.55 vs. 21.26±7.10, P<0.001; circumferential strain: -17.94±2.78 vs. -13.46±3.42, P<0.001). Radial and circumferential strain and circumferential diastolic strain rate were higher in mid-anterior (P<0.001), mid-anteroseptal (P<0.001), and all apical segments (P<0.005) between the 2 groups of patients. Moreover, longitudinal strain was higher only in apical segments in HOCM (P<0.02). CONCLUSIONS: HOCM patients showed higher left ventricular apical, mid-anterior, and mid-anteroseptal strain parameters compared with HNCM. These differences were independent of corresponding segmental thickness and LGE amount.

Early diagnosis of chemotherapy-induced cardiotoxicity by cardiac MRI.

Survival rate in cancer patients has improved over the course of the years. In cancer survivors, cardiovascular disease is the second leading cause of mortality and early detection and serial monitoring of cardiotoxicity are key factors towards the improvement of patients' outcomes. This review article will provide an overview of the existing literature regarding the tools that MRI can offer in the early diagnosis of myocardial damage.

Sequential Strategy Including FFRCT Plus Stress-CTP Impacts on Management of Patients with Stable Chest Pain: The Stress-CTP RIPCORD Study.

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.

Performance of a deep learning algorithm for the evaluation of CAD-RADS classification with CCTA.

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.

[Non-invasive functional assessment of coronary stenosis by cardiac computed tomography]. / Valutazione funzionale non invasiva della stenosi coronarica mediante tomografia computerizzata cardiaca.

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.