Cardiovascular disease remains an integral field on which new research in both the biomedical and technological fields is based, as it remains the leading cause of mortality and morbidity worldwide. However, despite the progress of cardiac imaging techniques, the heart remains a challenging organ to study. Artificial intelligence (AI) has emerged as one of the major innovations in the field of diagnostic imaging, with a dramatic impact on cardiovascular magnetic resonance imaging (CMR). AI will be increasingly present in the medical world, with strong potential for greater diagnostic efficiency and accuracy. Regarding the use of AI in image acquisition and reconstruction, the main role was to reduce the time of image acquisition and analysis, one of the biggest challenges concerning magnetic resonance; moreover, it has been seen to play a role in the automatic correction of artifacts. The use of these techniques in image segmentation has allowed automatic and accurate quantification of the volumes and masses of the left and right ventricles, with occasional need for manual correction. Furthermore, AI can be a useful tool to directly help the clinician in the diagnosis and derivation of prognostic information of cardiovascular diseases. This review addresses the applications and future prospects of AI in CMR imaging, from image acquisition and reconstruction to image segmentation, tissue characterization, diagnostic evaluation, and prognostication.

Non-ischemic dilated cardiomyopathy (DCM) is a disease characterized by left ventricular dilation and systolic dysfunction. Patients with DCM are at higher risk for ventricular arrhythmias and sudden cardiac death (SCD). According to current international guidelines, left ventricular ejection fraction (LVEF) ≤ 35% represents the main indication for prophylactic implantable cardioverter defibrillator (ICD) implantation in patients with DCM. However, LVEF lacks sensitivity and specificity as a risk marker for SCD. It has been seen that the majority of patients with DCM do not actually benefit from the ICD implantation and, on the contrary, that many patients at risk of SCD are not identified as they have preserved or mildly depressed LVEF. Therefore, the use of LVEF as unique decision parameter does not maximize the benefit of ICD therapy. Multiple risk factors used in combination could likely predict SCD risk better than any single risk parameter. Several predictors have been proposed including genetic variants, electric indexes, and volumetric parameters of LV. Cardiac magnetic resonance (CMR) can improve risk stratification thanks to tissue characterization sequences such as LGE sequence, parametric mapping, and feature tracking. This review evaluates the role of CMR as a risk stratification tool in DCM patients referred for ICD.

Background: We report the case of a 93-year-old patient with normal left ventricular function and severe mitral annulus calcification, with mild mitral steno-insufficiency. Case Presentation: She had developed creeping drugs-induced renal toxicity that is generally totally overlooked, due mainly to statins, a proton pump inhibitor, and aspirin. The Na and fluid retention, along with hypertension that ensued, although not severe, caused acute heart failure (sub-pulmonary edema) by worsening the mitral insufficiency. This occurred due to a less efficient calcific mitral annulus contraction during systole and an increasing mitral transvalvular gradient, as the transvalvular mitral gradient has an exponential relation to flow. After the suspension of the nephrotoxic drugs and starting intravenous furosemide, she rapidly improved. At 6 months follow-up, she is stable, in an NYHA 1-2 functional class, despite the only partial recovery of the renal function. Conclusion: Progressive renal failure can functionally worsen even minimal mitral valvulopathy. Drug-induced nephrotoxicity can always be suspected in case of renal failure of unknown etiology. The suspension of the culprit drugs can improve renal function and dramatically improve the clinical symptoms even in a nonagenarian.

The aim of this study was to clarify the relative contribution of elevated left ventricle (LV) filling pressure (FP) estimated by pulmonary venous (PV) and mitral flow, transesophageal Doppler recording (TEE), and other extracardiac factors like obesity and renal insufficiency (KI) to exercise capacity (ExC) evaluated by cardiopulmonary exercise testing (CPX) in patients with dilated cardiomyopathy (DCM). During the CPX test, 119 patients (pts) with DCM underwent both peak VO₂ consumption and then TEE with color-guided pulsed-wave Doppler recording of PVF and transmitral flow. In 78 patients (65%), peak VO₂ was normal or mildly reduced (>14 mL/kg/min) (group 1) while it was markedly reduced (≤14 mL/kg/min) in 41 (group 2). In univariate analysis, systolic fraction (S Fract), a predictor of elevated pre-a LV diastolic FP, appeared to be the best diastolic parameter predicting a significantly reduced peak VO₂. Logistic regression analysis identified five parameters yielding a unique, statistically significant contribution in predicting reduced ExC: creatinine clearance < 52 mL/min (odds ratio (OR) = 7.4, p = 0.007); female gender (OR = 7.1, p = 0.004); BMI > 28 (OR = 5.8, p = 0.029), age > 62 years (OR = 5.5, p = 0.03), S Fract < 59% (OR = 4.9, p = 0.02). Conclusion: KI was the strongest predictor of reduced ExC. The other modifiable factors were obesity and severe LV diastolic dysfunction expressed by blunted systolic venous flow. Contrarily, LV ejection fraction was not predictive, confirming other previous studies. This has important clinical implications.