Myocardial bridging in obstructive hypertrophic cardiomyopathy: a risk factor for myocardial fibrosis.

BACKGROUND: Myocardial bridging (MB) is common in patients with hypertrophic cardiomyopathy (HCM). There are sparse data on the impact of MB on myocardial fibrosis in HCM. This study was designed to evaluate the relationship between MB and myocardial fibrosis in patients with obstructive HCM. METHODS: In this cohort study, retrospective data were collected from a high-volume HCM center. Patients with obstructive HCM who underwent septal myectomy and preoperative cardiac magnetic resonance (CMR) were screened from 2011 to 2018. RESULTS: Finally, 492 patients were included in this study, with an average age of 45.7 years. Of these patients, 76 patients had MB. MB occurred mostly in the left anterior descending artery (73/76). The global extent of late gadolinium enhancement (LGE) was correlated with the degree of systolic compression (r = 0.33, p = 0.003). Multivariable linear regression analysis revealed that the degree of systolic compression was an independent risk factor for LGE (ß = 0.292, p = 0.007). The LGE fraction of basal and mid anteroseptal segments in patients with severe MB (compression ratio ≥ 80%) was significantly greater than that in patients with mild to moderate MB (compression ratio < 80%). During a median follow-up of 28 (IQR: 15-52) months, 15 patients died. Kaplan-Meier analysis did not identify differences in all-cause death (log-rank p = 0.63) or cardiovascular death (log-rank p = 0.72) between patients undergoing MB-related surgery and those without MB. CONCLUSIONS: MB with severe systolic compression was significantly associated with a high extent of fibrosis in patients with obstructive HCM. Concomitant myotomy or coronary artery bypass grafting might provide excellent survival similar to that of patients without MB. Identification of patients with severe MB and providing comprehensive management might help improve the prognosis of patients with HCM.

Early detection of anthracycline-induced cardiotoxicity using [68 Ga]Ga-FAPI-04 imaging.

PURPOSE: Anthracycline-induced cardiotoxicity (AIC), whose major manifestation is diffuse myocardial fibrosis, is an important clinical problem in cancer therapy. Therefore, early identification and treatment are clinically important. This study aims to explore the feasibility of using 68 Ga-labelled fibroblast activation protein (FAP) inhibitor ([68 Ga]Ga-FAPI) positron emission tomography/computed tomography (PET/CT) for the early identification of the fibrotic process and guidance of antifibrosis therapy in AIC. METHODS: An AIC rat model was induced by the intravascular administration of doxorubicin (DOX) once per week for 1, 2, 3 and 6 weeks (2.5 mg/kg/injection, groups 1-4), whereas intravascular saline was administered to control rats. Experimental and control groups (n = 4) underwent [68 Ga]Ga-FAPI PET/CT following disease induction. Groups 5 and 6 received DOX injections for 3 and 6 weeks, treated with angiotensin-converting enzyme (ACE) inhibitor starting at 3 weeks, treated with enalapril (20 mg/kg, gastric gavage) daily and underwent echocardiography and [68 Ga]Ga-FAPI PET/CT at 3 weeks after treatment. Rat hearts were subjected to haematoxylin and eosin staining, FAP immunohistochemistry, Sirius red staining and Masson's trichrome staining to investigate the pathological changes and deposition of collagen fibres. Rat blood was sampled weekly for the enzyme-linked immunosorbent assay of various markers of myocardial injury, such as plasma cardiac troponin I, B-type natriuretic peptide and angiotensin II. RESULTS: [68 Ga]Ga-FAPI-04 uptake by the heart was significantly higher in the cardiotoxicity group than in the control group at weeks 3 (SUVmax: 1.21 ± 0.23 vs 0.67 ± 0.01, P < 0.05) and 6 (SUVmax: 1.48 ± 0.28 vs 0.67 ± 0.08, P < 0.001), whereas left ventricle ejection fraction (LVEF) did not significantly differ between normal and AIC rats at week 3. FAP+ expression began to increase starting at week 3, before irreversible fibrotic changes were detected, until week 6. After 3 weeks of enalapril treatment, [68 Ga]Ga-FAPI-04 accumulation decreased in groups 5 and 6 (SUVmax decreased from 1.21 ± 0.23 to 0.77 ± 0.08 and 1.48 ± 0.28 to 1.09 ± 1.06, P < 0.05). Cardiac function was preserved (LVEF was 75.7% ± 7.38% in group 3 vs 74.5% ± 2.45% in group 5, P > 0.05) and improved (LVEF increased from 51.6% ± 9.03% in group 4 to 65.2% ± 4.27% in group 6, P < 0.05), and myocardial fibrosis attenuated (from 6.5% ± 1.2% in group 4 to 4.31% ± 0.37% in group 6, P < 0.01). CONCLUSION: [68 Ga]Ga-FAPI PET/CT can be used for the early detection of active myocardial fibrosis in AIC and the evaluation of the efficacy of therapeutic interventions. Early treatment guided by [68 Ga]Ga-FAPI PET/CT may reduce anthracycline-induced myocardial injury and improve heart function.

Long-term outcomes prediction in diabetic heart failure with preserved ejection fraction by cardiac MRI.

OBJECTIVES: We aimed to explore imaging features including tissue characterization and myocardial deformation in diabetic heart failure with preserved ejection fraction (HFpEF) patients by magnetic resonance imaging (MRI) and investigate its prognostic value for adverse outcomes. MATERIALS AND METHODS: Patients with HFpEF who underwent cardiac MRI between January 2010 and December 2016 were enrolled. Feature-tracking (FT) analysis and myocardial fibrosis were assessed by cardiac MRI. Cox proportional regression analysis was performed to determine the association between MRI variables and primary outcomes. Primary outcomes were all-cause death or heart failure hospitalization during the follow-up period. RESULTS: Of the 335 enrolled patients with HFpEF, 191 had diabetes mellitus (DM) (mean age: 58.7 years ± 10.8; 137 men). During a median follow-up of 10.2 years, 91 diabetic HFpEF and 56 non-diabetic HFpEF patients experienced primary outcomes. DM was a significant predictor of worse prognosis in HFpEF. In diabetic HFpEF, the addition of conventional imaging variables (left ventricular ejection fraction, left atrial volume index, extent of late gadolinium enhancement (LGE)) and global longitudinal strain (GLS) resulted in a significant increase in the area under the receiver operating characteristic curve (from 0.693 to 0.760, p < 0.05). After adjustment for multiple clinical and imaging variables, each 1% worsening in GLS was associated with a 9.8% increased risk of adverse events (p = 0.004). CONCLUSIONS: Diabetic HFpEF is characterized by more severely impaired strains and myocardial fibrosis, which is identified as a high-risk HFpEF phenotype. In diabetic HFpEF, comprehensive cardiac MRI provides incremental value in predicting prognosis. Particularly, MRI-FT measurement of GLS is an independent predictor of adverse outcome in diabetic HFpEF. CLINICAL RELEVANCE STATEMENT: Our findings suggested that MRI-derived variables, especially global longitudinal strain, played a crucial role in risk stratification and predicting worse prognosis in diabetic heart failure with preserved ejection fraction, which could assist in identifying high-risk patients and guiding therapeutic decision-making. KEY POINTS: • Limited data are available on the cardiac MRI features of diabetic heart failure with preserved ejection fraction, including myocardial deformation and tissue characterization, as well as their incremental prognostic value. • Diabetic heart failure with preserved ejection fraction patients was characterized by more impaired strains and myocardial fibrosis. Comprehensive MRI, including tissue characterization and global longitudinal strain, provided incremental value for risk prediction. • MRI served as a valuable tool for identifying high-risk patients and guiding clinical management in diabetic heart failure with preserved ejection fraction.

Incremental value of myocardial global longitudinal strain in predicting major adverse cardiac events among patients with hypertrophic cardiomyopathy.

OBJECTIVES: Endocardial global longitudinal strain (endo-GLS) measured with echocardiography (echo) has been demonstrated to be associated with myocardial fibrosis (MF) and is a prognostic predictor in patients with hypertrophic cardiomyopathy (HCM). Late gadolinium enhancement cardiac magnetic resonance (LGE-CMR) imaging showed that MF is primarily located in the myocardial layer of the extremely hypertrophic septal or ventricular wall. We hypothesized that GLS of the myocardial layer (myo-GLS) is more strongly correlated with the extent of LGE (%LGE) and is a more powerful prognostic factor than endo-GLS. METHODS: A total of 177 inpatients (54.0 [IQR: 43.0, 64.0] years, female 37.3%) with HCM were retrospectively included from May 2019 to April 2021. Among them, 162 patients underwent echocardiographic examination and contrast-enhanced CMR within 7 days. Myo-GLS and %LGE were blindly assessed in a core laboratory. All the patients were followed after they were discharged. RESULTS: During a mean follow-up of 33.77 [IQR 30.05, 35.40] months, 14 participants (7.91%) experienced major adverse cardiac events (MACE). The MACE (+) group showed lower absolute endo-GLS and myo-GLS than the MACE (-) group. Myo-GLS was more associated with %LGE (r = -.68, P < .001) than endo-GLS (r = -.64, P < .001). Cox multivariable analysis indicated that absolute myo-GLS was independently associated with MACE (adjusted hazard ratio = .75, P < .05). Myo-GLS was better than endo-GLS at detecting MACE (+) patients (-8.64%, AUC .939 vs. - 16.375%, AUC .898, P < .05). CONCLUSIONS: Myo-GLS is a stronger predictor of MACE than endo-GLS in patients with HCM and is highly correlated with %LGE.

Fucoidan MF4 from Fucus vesiculosus inhibits Lewis lung cancer via STING-TBK1-IRF3 pathway.

Fucoidan, a sulfated polysaccharide of marine origin found in brown algae and sea cucumbers, has been identified as a neuroprotective compound. In this study, a novel fucoidan MF4 was extracted from Fucus vesiculosus and isolated using Q-Sepharose fast-flow ion-exchange chromatography. The physicochemical properties of MF4 were characterized. MF4 is primarily composed of fucose, xylose, galactose, glucose, and mannose in a molar ratio of 12.3: 4.9: 1.1: 1.0: 1.1, with an average molecular weight of 67.7 kDa. Notably, MF4 demonstrated suppression of LLC tumor growth in vivo. RNA-sequencing analysis revealed that MF4 enhanced the expression of type I interferon-associated downstream genes in macrophages. Furthermore, MF4 increased the levels of phosphorylated TBK1 and IRF3 proteins in vitro. By activating the STING-TBK1-IRF3 signaling pathway, MF4 may enhance the antitumor activity of macrophages. Taken together, MF4 has promising potential as an antitumor and immunomodulatory agent.

Right Ventricular Strain Derived from Cardiac MRI Feature Tracking for the Diagnosis and Prognosis of Arrhythmogenic Right Ventricular Cardiomyopathy.

Purpose To demonstrate the myocardial strain characteristics of patients with arrhythmogenic right ventricular cardiomyopathy (ARVC), based on revised Task Force Criteria (rTFC), and to explore the prognostic value of strain analysis in ARVC. Materials and Methods This retrospective study included 247 patients (median age, 38 years [IQR, 28-48 years]; 167 male, 80 female) diagnosed with ARVC, based on rTFC, between 2014 and 2018. Patients were divided into "possible" (n =25), "borderline" (n = 40), and "definite" (n = 182) ARVC groups following rTFC. Biventricular global strain parameters were calculated using cardiac MRI feature tracking (FT). The primary outcome was defined as a composite of cardiovascular events, including cardiovascular death, heart transplantation, and appropriate implantable cardioverter defibrillator discharge. Univariable and multivariable cumulative logistic regression and Cox proportional hazards regression analysis were used to evaluate the diagnostic and prognostic value of right ventricle (RV) strain parameters. Results Patients with definite ARVC had significantly reduced RV global strain in all three directions compared with possible or borderline groups (all P < .001). RV global longitudinal strain (GLS) was an independent predictor for disease (odds ratio, 1.09 [95% CI: 1.02, 1.16]; P = .009). During a median follow-up of 3.4 years (IQR, 2.0-4.9 years), 55 patients developed primary end point events. Multivariable analysis showed that RV GLS was independently associated with the occurrence of cardiovascular events (hazard ratio, 1.15 [95% CI: 1.07, 1.24]; P < .001). Kaplan-Meier analysis showed that patients with RV GLS worse than median had a higher risk of combined cardiovascular events (log-rank P < .001). Conclusion RV GLS derived from cardiac MRI FT demonstrated good diagnostic and prognostic value in ARVC. Keywords: MR Imaging, Image Postprocessing, Cardiac, Right Ventricle, Cardiomyopathies, Arrhythmogenic Right Ventricular Cardiomyopathy, Revised Task Force Criteria, Cardiovascular MR, Feature Tracking, Cardiovascular Events Supplemental material is available for this article. © RSNA, 2024.

A Comparison of the Association of Septal Scar Burden on Responses to LBBAP-CRT and BVP-CRT.

BACKGROUND: Left bundle branch area pacing (LBBAP) is an alternative to biventricular pacing (BVP) for cardiac resynchronization therapy (CRT). However, despite the presence of left bundle branch block, whether cardiac substrate may influence the effect between the 2 strategies is unclear. OBJECTIVES: This study aims to assess the association of septal scar on reverse remodeling and clinical outcomes of LBBAP compared with BVP. METHODS: We analyzed patients with nonischemic cardiomyopathy who had CRT indications undergoing preprocedure cardiac magnetic resonance examination. Changes in left ventricular ejection fraction (LVEF) and echocardiographic response (ER) (≥5% absolute LVEF increase) were assessed at 6 months. The clinical outcome was the composite of all-cause mortality, heart failure hospitalization, or major ventricular arrhythmia. RESULTS: There were 147 patients included (51 LBBAP and 96 BVP). Among patients with low septal scar burden (below median 5.7%, range: 0% to 5.3%), LVEF improvement was higher in the LBBAP than the BVP group (17.5% ± 10.9% vs 12.3% ± 11.8%; P = 0.037), with more than 3-fold increased odds of ER (OR: 4.35; P = 0.033). In high sepal scar subgroups (≥5.7%, range: 5.7%-65.9%), BVP trended towards higher LVEF improvement (9.2% ± 9.4% vs 6.4% ± 12.4%; P = 0.085). Interaction between septal scar burden and pacing strategy was significant for ER (P = 0.002) and LVEF improvement (P = 0.011) after propensity score adjustment. During median follow-up of 33.7 (Q1-Q3: 19.8-42.1) months, the composite clinical outcome occurred in 34.7% (n = 51) of patients. The high-burden subgroups had worse clinical outcomes independent of CRT method. CONCLUSIONS: Remodeling response to LBBAP and BVP among nonischemic cardiomyopathy patients is modified by septal scar burden. High septal scar burden was associated with poor clinical prognosis independent of CRT methods.

Heart Failure with Normal Natriuretic Peptide Levels and Preserved Ejection Fraction: A Prospective Clinical and Cardiac MRI Study.

Purpose To describe the clinical presentation, comprehensive cardiac MRI characteristics, and prognosis of individuals with predisposed heart failure with preserved ejection fraction (HFpEF). Materials and Methods This prospective cohort study (part of MISSION-HFpEF [Multimodality Imaging in the Screening, Diagnosis, and Risk Stratification of HFpEF]; NCT04603404) was conducted from January 1, 2019, to September 30, 2021, and included individuals with suspected HFpEF who underwent cardiac MRI. Participants who had primary cardiomyopathy and primary valvular heart disease were excluded. Participants were split into a predisposed HFpEF group, defined as HFpEF with normal natriuretic peptide levels based on an HFA-PEFF (Heart Failure Association Pretest Assessment, Echocardiography and Natriuretic Peptide, Functional Testing, and Final Etiology) score of 4 from the latest European Society of Cardiology guidelines, and an HFpEF group (HFA-PEFF score of ≥ 5). An asymptomatic control group without heart failure was also included. Clinical and cardiac MRI-based characteristics and outcomes were compared between groups. The primary end points were death, heart failure hospitalization, or stroke. Results A total of 213 participants with HFpEF, 151 participants with predisposed HFpEF, and 100 participants in the control group were analyzed. Compared with the control group, participants with predisposed HFpEF had worse left ventricular remodeling and function and higher systemic inflammation. Compared with participants with HFpEF, those with predisposed HFpEF, whether obese or not, were younger and had higher plasma volume, lower prevalence of atrial fibrillation, lower left atrial volume index, and less impaired left ventricular global longitudinal strain (-12.2% ± 2.8 vs -13.9% ± 3.1; P < .001) and early-diastolic global longitudinal strain rate (eGLSR, 0.52/sec ± 0.20 vs 0.57/sec ± 0.15; P = .03) but similar prognosis. Atrial fibrillation occurrence (hazard ratio [HR] = 3.90; P = .009), hemoglobin level (HR = 0.94; P = .001), and eGLSR (per 0.2-per-second increase, HR = 0.28; P = .002) were independently associated with occurrence of primary end points in participants with predisposed HFpEF. Conclusion Participants with predisposed HFpEF showed relatively unique clinical and cardiac MRI features, warranting greater clinical attention. eGLSR should be considered as a prognostic factor in participants with predisposed HFpEF. Keywords: Heart Failure with Preserved Ejection Fraction, Normal Natriuretic Peptide Levels, Cardiovascular Magnetic Resonance, Myocardial Strain, Prognosis Clinical trial registration no. NCT04603404 Supplemental material is available for this article. © RSNA, 2024.

Incremental Diagnostic Value of Right Ventricular Strain Analysis in Arrhythmogenic Right Ventricular Cardiomyopathy.

BACKGROUND: Strain analysis is a sensitive method for the assessment of ventricular structural or functional alterations. The authors aimed to determine whether right ventricular (RV) strain parameters can discriminate patients with revised Task Force Criteria-diagnosed arrhythmogenic RV cardiomyopathy (ARVC) incremental to the existing cardiovascular magnetic resonance (CMR) criteria, thus improving the diagnostic yield of CMR in ARVC. METHODS AND RESULTS: A total of 74 patients with revised Task Force Criteria-diagnosed ARVC (37 borderline and 37 definite) and 37 controls were retrospectively enrolled for analysis. Using CMR feature tracking, RV global longitudinal (GLS), circumferential, and radial strain of all participants were evaluated. Compared with controls, the study patients demonstrated significantly impaired global biventricular strain in all 3 directions (all P<0.001). Receiver operating characteristic curve analysis indicated that RV GLS was the strongest discriminator among all RV strain parameters for the identification of patients with ARVC (area under the curve, 0.92). Using the Youden index, the authors determined RV GLS ≥-19.95% as the diagnostic criterion of ARVC. In patients diagnosed with borderline ARVC according to revised Task Force Criteria but with no or only minor CMR criteria, there were >50% presenting with impaired RV GLS. When both conventional criteria and RV GLS were considered together, this new diagnostic method demonstrated an overall diagnostic accuracy of 90%. The likelihood ratio test showed a significant incremental diagnostic value of RV GLS (P=0.02) over the existing CMR major criteria. CONCLUSIONS: The current study showed an improved diagnostic accuracy when both RV GLS and the existing CMR criteria were considered together, especially for patients with borderline diagnosis, suggesting the incremental value of strain analysis to the initial assessment of ARVC.

CMR feature tracking-based left atrial mechanics predicts response to cardiac resynchronization therapy and adverse outcomes.

BACKGROUND: Cardiac resynchronization therapy (CRT) is an established therapy for advanced heart failure (HF) with prolonged QRS duration. However, 30% of patients have shown no benefit from the treatment. OBJECTIVE: This study aimed to examine the value of left atrial (LA) mechanics by cardiac magnetic resonance (CMR) to predict response to CRT and clinical outcomes. METHODS: A total of 163 CRT recipients with preimplantation CMR examination were retrospectively recruited. CMR feature tracking was used to evaluate LA size and function. The end points include (1) improvement of at least 5% in left ventricular ejection fraction combined with a reduction of at least 1 New York Heart Association functional class at 6-month follow-up and (2) any all-cause death or HF hospitalization during follow-up. RESULTS: Overall, 82 (50.3%) were CRT responders. CRT nonresponders had larger LA and worse LA reservoir and booster pump function than did responders (P < .001 for all). LA structural (maximum volume index < 47 mL/m2) and functional (booster pump strain > 8.5%) criteria were incremental to traditional indicators in detecting CRT response (χ2, 40.83 vs 9.98; P < .001). During follow-up (median 41 months), survival free from death or HF hospitalization increased with the number of positive LA criteria (log-rank, P < .001). After adjustment for clinical confounders, the absence of the 2 criteria remained associated with a considerably increased risk of death or HF hospitalization (adjusted hazard ratio 6.2; 95% confidence interval 2.15-17.88; P = .001). CONCLUSION: The preprocedure LA mechanics evaluated using CMR may be useful to predict response to CRT and improve risk stratification in CRT recipients.

Comparative prognostic importance of measures of left atrial structure and function in non-ischaemic dilated cardiomyopathy.

AIMS: To compare the association between measures of left atrial (LA) structure and function, derived from cardiovascular magnetic resonance (CMR), with cardiovascular (CV) death or non-fatal heart failure (HF) events in patients with non-ischaemic dilated cardiomyopathy (DCM). METHODS AND RESULTS: CMR studies of 580 prospectively recruited patients with DCM in sinus rhythm (median age 54 [interquartile range 44-64] years, 61% men, median LVEF 42% [30-51%]) were analysed for measures of LA structure (left atrial maximum volume index [LAVImax], left atrial minimum volume index [LAVImin]) and function (left atrial emptying fraction [LAEF], left atrial reservoir strain [LARS], left atrial conduit strain [LACS] and left atrial booster strain [LABS]). Over median follow-up of 7.4 years, 103 patients (18%) met the primary endpoint. Apart from LACS, each measure of LA structure and function was associated with the primary endpoint after adjusting for other important prognostic variables. The addition of each LA metric to a baseline model containing the same important prognostic covariates improved model discrimination, with LAVImin providing the greatest improvement (C-statistic improvement: 0.702 to 0.738; χ2 test comparing likelihood ratio p < 0.0001; categorical net reclassification index: 0.210 (95% CI 0.023-0.392)). Patients in the highest tercile of LAVImin had similar event rates to those with persistent atrial fibrillation. Measures of LA strain did not enhance model discrimination above LA volumetric measures. CONCLUSION: Measure of left atrial structure and function offer important prognostic information in patients with DCM and enhance prediction of adverse outcomes. LA strain was not incremental to volumetric analysis for risk prediction.

Machine Learning in Hypertrophic Cardiomyopathy: Nonlinear Model From Clinical and CMR Features Predicting Cardiovascular Events.

BACKGROUND: The cumulative burden of hypertrophic cardiomyopathy (HCM) is significant, with a noteworthy percentage (10%-15%) of patients with HCM per year experiencing major adverse cardiovascular events (MACEs). A current risk stratification scheme for HCM had only limited accuracy in predicting sudden cardiac death (SCD) and failed to account for a broader spectrum of adverse cardiovascular events and cardiac magnetic resonance (CMR) parameters. OBJECTIVES: This study sought to develop and evaluate a machine learning (ML) framework that integrates CMR imaging and clinical characteristics to predict MACEs in patients with HCM. METHODS: A total of 758 patients with HCM (67% male; age 49 ± 14 years) who were admitted between 2010 and 2017 from 4 medical centers were included. The ML model was built on the internal discovery cohort (533 patients with HCM, admitted to Fuwai Hospital, Beijing, China) by using the light gradient-boosting machine and internally evaluated using cross-validation. The external test cohort consisted of 225 patients with HCM from 3 medical centers. A total of 14 CMR imaging features (strain and late gadolinium enhancement [LGE]) and 23 clinical variables were evaluated and used to inform the ML model. MACEs included a composite of arrhythmic events, SCD, heart failure, and atrial fibrillation-related stroke. RESULTS: MACEs occurred in 191 (25%) patients over a median follow-up period of 109.0 months (Q1-Q3: 73.0-118.8 months). Our ML model achieved areas under the curve (AUCs) of 0.830 and 0.812 (internally and externally, respectively). The model outperformed the classic HCM Risk-SCD model, with significant improvement (P < 0.001) of 22.7% in the AUC. Using the cubic spline analysis, the study showed that the extent of LGE and the impairment of global radial strain (GRS) and global circumferential strain (GCS) were nonlinearly correlated with MACEs: an elevated risk of adverse cardiovascular events was observed when these parameters reached the high enough second tertiles (11.6% for LGE, 25.8% for GRS, -17.3% for GCS). CONCLUSIONS: ML-empowered risk stratification using CMR and clinical features enabled accurate MACE prediction beyond the classic HCM Risk-SCD model. In addition, the nonlinear correlation between CMR features (LGE and left ventricular pressure gradient) and MACEs uncovered in this study provides valuable insights for the clinical assessment and management of HCM.

Screening and diagnosis of cardiovascular disease using artificial intelligence-enabled cardiac magnetic resonance imaging.

Cardiac magnetic resonance imaging (CMR) is the gold standard for cardiac function assessment and plays a crucial role in diagnosing cardiovascular disease (CVD). However, its widespread application has been limited by the heavy resource burden of CMR interpretation. Here, to address this challenge, we developed and validated computerized CMR interpretation for screening and diagnosis of 11 types of CVD in 9,719 patients. We propose a two-stage paradigm consisting of noninvasive cine-based CVD screening followed by cine and late gadolinium enhancement-based diagnosis. The screening and diagnostic models achieved high performance (area under the curve of 0.988 ± 0.3% and 0.991 ± 0.0%, respectively) in both internal and external datasets. Furthermore, the diagnostic model outperformed cardiologists in diagnosing pulmonary arterial hypertension, demonstrating the ability of artificial intelligence-enabled CMR to detect previously unidentified CMR features. This proof-of-concept study holds the potential to substantially advance the efficiency and scalability of CMR interpretation, thereby improving CVD screening and diagnosis.

Precision prediction of heart failure events in patients with dilated cardiomyopathy and mildly reduced ejection fraction using multi-parametric cardiovascular magnetic resonance.

AIMS: To assess whether left ventricular (LV) global longitudinal strain (GLS), derived from cardiovascular magnetic resonance (CMR), is associated with (i) progressive heart failure (HF), and (ii) sudden cardiac death (SCD) in patients with dilated cardiomyopathy with mildly reduced ejection fraction (DCMmrEF). METHODS AND RESULTS: We conducted a prospective observational cohort study of patients with DCM and LV ejection fraction (LVEF) ≥40% assessed by CMR, including feature-tracking to assess LV GLS and late gadolinium enhancement (LGE). Long-term adjudicated follow-up included (i) HF hospitalization, LV assist device implantation or HF death, and (ii) SCD or aborted SCD (aSCD). Of 355 patients with DCMmrEF (median age 54 years [interquartile range 43-64], 216 men [60.8%], median LVEF 49% [46-54]) followed up for a median 7.8 years (5.2-9.4), 32 patients (9%) experienced HF events and 19 (5%) died suddenly or experienced aSCD. LV GLS was associated with HF events in a multivariable model when considered as either a continuous (per % hazard ratio [HR] 1.10, 95% confidence interval [CI] 1.00-1.21, p = 0.045) or dichotomized variable (LV GLS > -15.4%: HR 2.70, 95% CI 1.30-5.94, p = 0.008). LGE presence was not associated with HF events (HR 1.49, 95% CI 0.73-3.01, p = 0.270). Conversely, LV GLS was not associated with SCD/aSCD (per % HR 1.07, 95% CI 0.95-1.22, p = 0.257), whereas LGE presence was (HR 3.58, 95% CI 1.39-9.23, p = 0.008). LVEF was neither associated with HF events nor SCD/aSCD. CONCLUSION: Multi-parametric CMR has utility for precision prognostic stratification of patients with DCMmrEF. LV GLS stratifies risk of progressive HF, while LGE stratifies SCD risk.