Artificial intelligence-based classification of cardiac autonomic neuropathy from retinal fundus images in patients with diabetes: The Silesia Diabetes Heart Study.

BACKGROUND: Cardiac autonomic neuropathy (CAN) in diabetes mellitus (DM) is independently associated with cardiovascular (CV) events and CV death. Diagnosis of this complication of DM is time-consuming and not routinely performed in the clinical practice, in contrast to fundus retinal imaging which is accessible and routinely performed. Whether artificial intelligence (AI) utilizing retinal images collected through diabetic eye screening can provide an efficient diagnostic method for CAN is unknown. METHODS: This was a single center, observational study in a cohort of patients with DM as a part of the Cardiovascular Disease in Patients with Diabetes: The Silesia Diabetes-Heart Project (NCT05626413). To diagnose CAN, we used standard CV autonomic reflex tests. In this analysis we implemented AI-based deep learning techniques with non-mydriatic 5-field color fundus imaging to identify patients with CAN. Two experiments have been developed utilizing Multiple Instance Learning and primarily ResNet 18 as the backbone network. Models underwent training and validation prior to testing on an unseen image set. RESULTS: In an analysis of 2275 retinal images from 229 patients, the ResNet 18 backbone model demonstrated robust diagnostic capabilities in the binary classification of CAN, correctly identifying 93% of CAN cases and 89% of non-CAN cases within the test set. The model achieved an area under the receiver operating characteristic curve (AUCROC) of 0.87 (95% CI 0.74-0.97). For distinguishing between definite or severe stages of CAN (dsCAN), the ResNet 18 model accurately classified 78% of dsCAN cases and 93% of cases without dsCAN, with an AUCROC of 0.94 (95% CI 0.86-1.00). An alternate backbone model, ResWide 50, showed enhanced sensitivity at 89% for dsCAN, but with a marginally lower AUCROC of 0.91 (95% CI 0.73-1.00). CONCLUSIONS: AI-based algorithms utilising retinal images can differentiate with high accuracy patients with CAN. AI analysis of fundus images to detect CAN may be implemented in routine clinical practice to identify patients at the highest CV risk. TRIAL REGISTRATION: This is a part of the Silesia Diabetes-Heart Project (Clinical-Trials.gov Identifier: NCT05626413).

Cardiac magnetic resonance reveals concealed structural heart disease in patients with frequent premature ventricular contractions and normal echocardiography: A systematic review.

Premature ventricular contractions (PVCs) are a common form of arrhythmic events, often representing an idiopathic and benign condition without further therapeutic interventions. However, in certain circumstances PVCs may represent the epiphenomenon of a concealed structural heart disease (SHD). Surface 12­leads EKG and 24-h dynamic EKG are necessary to assess their main characteristics such as site of origin, frequency and complexity. Echocardiography represents the first-line imaging tool recommended to evaluate cardiac structures and function. Cardiac Magnetic Resonance (CMR) is recognized as a superior modality for detecting structural cardiac alterations, that might evade detection by conventional echocardiography. Moreover, in specific populations such as athletes, CMR may have a crucial role to exclude a concealed SHD and the risk of serious arrhythmic events during sport activity. Some clinical characteristics such as male sex, older age or family history of sudden cardiac death (SCD) or cardiomyopathy, and some electrocardiographic features of PVCs, in particular a right branch bundle block (RBBB) with superior/intermediate axis morphology, the reproducibility of VAs during exercise test (ET) or the evidence of complex ventricular arrhythmias, may warrant a CMR evaluation, due to the high probability of SHD. In this systematic review our objective was to provide an exhaustive overview on the role of CMR in detecting a concealed SHD in patients with high daily burden of PVCs and a normal echocardiographic evaluation, paving the way for a more extensive utilization of CMR in presence of certain high-risk clinical and/or EKG features identified during the diagnostic workup.

Cardiac disease discrimination from 3D-convolutional kinematic patterns on cine-MRI sequences. / Discriminación de enfermedades cardiacas utilizando patrones cinemáticos codificados con convoluciones 3D en secuencias de cine-RM

INTRODUCTION: Cine-MRI (cine-magnetic resonance imaging) sequences are a key diagnostic tool to visualize anatomical information, allowing experts to localize and determine suspicious pathologies. Nonetheless, such analysis remains subjective and prone to diagnosis errors. OBJECTIVE: To develop a binary and multi-class classification considering various cardiac conditions using a spatiotemporal model that highlights kinematic movements to characterize each disease. MATERIALS AND METHODS: This research focuses on a 3D convolutional representation to characterize cardiac kinematic patterns during the cardiac cycle, which may be associated with pathologies. The kinematic maps are obtained from the apparent velocity maps computed from a dense optical flow strategy. Then, a 3D convolutional scheme learns to differentiate pathologies from kinematic maps. RESULTS: The proposed strategy was validated with respect to the capability to discriminate among myocardial infarction, dilated cardiomyopathy, hypertrophic cardiomyopathy, abnormal right ventricle, and normal cardiac sequences. The proposed method achieves an average accuracy of 78.00% and a F1 score of 75.55%. Likewise, the approach achieved 92.31% accuracy for binary classification between pathologies and control cases. CONCLUSION: The proposed method can support the identification of kinematically abnormal patterns associated with a pathological condition. The resultant descriptor, learned from the 3D convolutional net, preserves detailed spatiotemporal correlations and could emerge as possible digital biomarkers of cardiac diseases.

Introducción. Las secuencias del cine-resonancia magnética (cine-MRI, cine magnetic resonance imaging) son una herramienta diagnóstica clave para visualizar la información anatómica que les permite a los expertos localizar y determinar aquellas anomalías que resulten sospechosas. No obstante, este análisis sigue siendo subjetivo y propenso a errores de diagnóstico. Objetivo. Desarrollar una clasificación binaria y multiclase, considerando diferentes condiciones cardiacas, mediante un modelo espaciotemporal que permita resaltar los movimientos cinéticos para caracterizar cada enfermedad. Materiales y métodos. Este estudio se centra en el uso de una representación de convolución 3D para caracterizar los patrones cinéticos durante el ciclo cardiaco que puedan estar asociados con enfermedades. Para ello, se obtienen mapas cinéticos a partir de mapas de velocidad aparente, calculados mediante una estrategia de flujo óptico denso. A continuación, un esquema de convolución 3D "aprende" a diferenciar patologías a partir de mapas cinemáticos. Resultados. La estrategia propuesta se validó según la capacidad de discriminar entre infarto de miocardio, miocardiopatía dilatada, miocardiopatía hipertrófica, ventrículo derecho anormal y un examen normal. El método propuesto alcanza una precisión media del 78,0 % y una puntuación F1 score del 75,55 %. Asimismo, el enfoque alcanzó el 92,31 % de precisión para la clasificación binaria entre enfermedades y casos de control. Conclusiones. El método propuesto es capaz de apoyar la identificación de patrones cinéticos anormales asociados con una condición patológica. El descriptor resultante, aprendido de la red de convolución 3D, conserva correlaciones espaciotemporales detalladas y podría surgir como posible biomarcador digital de enfermedades cardiacas.

Morphology and location of thrombus and sludge in patients with non-valvular atrial fibrillation.

BACKGROUND: Stroke and thromboembolism in nonvalvular atrial fibrillation (NVAF) primarily arise from thrombi or sludge in the left atrial appendage (LAA). Comprehensive insight into the characteristics of these formations is essential for effective risk assessment and management. METHODS: We conducted a single-center retrospective observational of 176 consecutive NVAF patients with confirmed atrial/appendage thrombus or sludge determined by a pre-ablation transesophageal echocardiogram (TEE) from December 2017 to April 2019. We obtained clinical and echocardiographic characteristics, including left atrial appendage emptying velocity (LAAeV) and filling velocity (LAAfV). Data analysis focused on identifying the morphology and location of thrombus or sludge. Patients were divided into the solid thrombus and sludge groups, and the correlation between clinical and echocardiographic variables and thrombotic status was analyzed. RESULTS: Morphological classification: In total, thrombi were identified in 78 patients, including 71 (40.3%) mass and 7 (4.0%) lamellar, while sludge was noted in 98 (55.7%). Location classification: 92.3% (72/78) of patients had thrombus confined to the LAA; 3.8% (3/78) had both LA and LAA involvement; 2.7% (2/78) had LA, LAA and RAA extended into the RA, the remained 1.2%(1/78) was isolated to RAA. 98.0% (96/98) of patients had sludge confined to the LAA; the remaining 2.0% (2/98) were present in the atrial septal aneurysm, which protrusion of interatrial septum into the RA. The thrombus and sludge groups showed low LAAeV (19.43 ± 9.59 cm/s) or LAAfV (17.40 ± 10.09 cm/s). Only LA dimension ≥ 40 mm was independently associated with the thrombus state in the multivariable model. CONCLUSION: This cohort study identified rare thrombus morphology and systematically summarized the classification of thrombus morphology. The distribution of thrombus and sludge outside limited to LAA was updated, including bilateral atrial and appendage involvement and rare atrial septal aneurysm sludge. LAAeV and LAAfV were of limited value in distinguishing solid thrombus from sludge. CLINICAL TRIAL NUMBER: ChiCTR-OCH-13,003,729.

Multidimensional Analysis of the Adult Human Heart in Health and Disease Using Hierarchical Phase-Contrast Tomography.

Background Current clinical imaging modalities such as CT and MRI provide resolution adequate to diagnose cardiovascular diseases but cannot depict detailed structural features in the heart across length scales. Hierarchical phase-contrast tomography (HiP-CT) uses fourth-generation synchrotron sources with improved x-ray brilliance and high energies to provide micron-resolution imaging of intact adult organs with unprecedented detail. Purpose To evaluate the capability of HiP-CT to depict the macro- to microanatomy of structurally normal and abnormal adult human hearts ex vivo. Materials and Methods Between February 2021 and September 2023, two adult human donor hearts were obtained, fixed in formalin, and prepared using a mixture of crushed agar in a 70% ethanol solution. One heart was from a 63-year-old White male without known cardiac disease, and the other was from an 87-year-old White female with a history of multiple known cardiovascular pathologies including ischemic heart disease, hypertension, and atrial fibrillation. Nondestructive ex vivo imaging of these hearts without exogenous contrast agent was performed using HiP-CT at the European Synchrotron Radiation Facility. Results HiP-CT demonstrated the capacity for high-spatial-resolution, multiscale cardiac imaging ex vivo, revealing histologic-level detail of the myocardium, valves, coronary arteries, and cardiac conduction system across length scales. Virtual sectioning of the cardiac conduction system provided information on fatty infiltration, vascular supply, and pathways between the cardiac nodes and adjacent structures. HiP-CT achieved resolutions ranging from gross (isotropic voxels of approximately 20 µm) to microscopic (approximately 6.4-µm voxel size) to cellular (approximately 2.3-µm voxel size) in scale. The potential for quantitative assessment of features in health and disease was demonstrated. Conclusion HiP-CT provided high-spatial-resolution, three-dimensional images of structurally normal and diseased ex vivo adult human hearts. Whole-heart image volumes were obtained with isotropic voxels of approximately 20 µm, and local regions of interest were obtained with resolution down to 2.3-6.4 µm without the need for sectioning, destructive techniques, or exogenous contrast agents. Published under a CC BY 4.0 license Supplemental material is available for this article. See also the editorial by Bluemke and Pourmorteza in this issue.

Gastropericardial fistula: A successfully operated heart code.

Gastropericardial fistula is a rare, extremely serious and life-threatening condition. Its most common aetiology is secondary to iatrogenic injury following gastric surgery. Clinical manifestations may be non-specific with precordial pain, simulating an acute coronary syndrome, and may be accompanied by electrocardiogram abnormalities. Diagnosis is made by thoracoabdominal computed tomography (CT) with oral and intravenous contrast. Treatment is surgical and consists of repair of the anomalous communication. We present the case of an 81-year-old male patient with gastropericardial fistula who underwent surgery, with the aim of reviewing the diagnosis and the appropriate therapeutic strategy.

Hydatid cyst in heart and lung: a rare case with a 5-year follow-up.

This report describes a male in his late 20s who presented with a 2-month history of recurrent haemoptysis and chest pain. A chronic infection, such as tuberculosis, was suspected. He had undergone surgical resection of an intrapericardial hydatid cyst in the past. His blood investigations showed peripheral eosinophilia, and his chest X-ray showed a cystic oval lesion in the left upper zone. A CT pulmonary angiogram revealed filling defects in the bilateral segmental and subsegmental arteries with a cystic lesion in the left upper lobe. Further workup, including bronchoalveolar lavage culture and MRI of the thorax, confirmed the diagnosis of a hydatid cyst of pulmonary echinococcosis. This case illustrates the presentation of multisystemic echinococcosis in a young male with no other risk factors, initially treated with surgical resection and antihelminthic therapy. The disease later recurred, which required prolonged medications, which brought the patient into remission.

Head-to-Head Comparison and Temporal Trends of Cardiac MRI Recommendations in ESC versus ACC/AHA Guidelines: A Systematic Review and Meta-Analysis.

Purpose To provide a comprehensive head-to-head comparison and temporal analysis of cardiac MRI indications between the European Society of Cardiology (ESC) and American College of Cardiology/American Heart Association (ACC/AHA) guidelines to identify areas of consensus and divergence. Materials and Methods A systematic review and meta-analysis was conducted. ESC and ACC/AHA guidelines published until May 2023 were systematically screened for recommendations related to cardiac MRI. The class of recommendation (COR) and level of evidence (LOE) for cardiac MRI recommendations were compared between the two guidelines and between newer versus older versions of each guideline using χ2 or Fisher exact tests. Results ESC guidelines included 109 recommendations regarding cardiac MRI, and ACC/AHA guidelines included 90 recommendations. The proportion of COR I and LOE B was higher in ACC/AHA versus ESC guidelines (60% [54 of 90] vs 46.8% [51 of 109]; P = .06 and 53% [48 of 90] vs 35.8% [39 of 109], respectively; P = .01). The increase in the number of cardiac MRI recommendations over time was significantly higher in ESC guidelines (from 63 to 109 for ESC vs from 65 to 90 for ACC/AHA; P = .03). The main areas of consensus were found in heart failure and hypertrophic cardiomyopathy, while the main divergences were in valvular heart disease, arrhythmias, and aortic disease. Conclusion ESC guidelines included more recommendations related to cardiac MRI use, whereas the ACC/AHA recommendations had higher COR and LOE. The number of cardiac MRI recommendations increased significantly over time in both guidelines, indicating the increasing role of cardiac MRI evaluation and management of cardiovascular disease. Keywords: Cardiovascular Magnetic Resonance, Guideline, European Society of Cardiology, ESC, American College of Cardiology/American Heart Association, ACC/AHA Supplemental material is available for this article. © RSNA, 2024.

CMRxRecon: A publicly available k-space dataset and benchmark to advance deep learning for cardiac MRI.

Cardiac magnetic resonance imaging (CMR) has emerged as a valuable diagnostic tool for cardiac diseases. However, a significant drawback of CMR is its slow imaging speed, resulting in low patient throughput and compromised clinical diagnostic quality. The limited temporal resolution also causes patient discomfort and introduces artifacts in the images, further diminishing their overall quality and diagnostic value. There has been growing interest in deep learning-based CMR imaging algorithms that can reconstruct high-quality images from highly under-sampled k-space data. However, the development of deep learning methods requires large training datasets, which have so far not been made publicly available for CMR. To address this gap, we released a dataset that includes multi-contrast, multi-view, multi-slice and multi-coil CMR imaging data from 300 subjects. Imaging studies include cardiac cine and mapping sequences. The 'CMRxRecon' dataset contains raw k-space data and auto-calibration lines. Our aim is to facilitate the advancement of state-of-the-art CMR image reconstruction by introducing standardized evaluation criteria and making the dataset freely accessible to the research community.

Ultrasound Rounds: Intraoperative Point-of-Care Ultrasound Identifies Intracardiac Thrombus and Pulmonary Embolism Allowing for Alteration in Surgical Management.

Most of the cases demonstrating describing acute findings using point-of-care ultrasound (POCUS) have been described in emergency medicine and critical care medicine. While the use of POCUS has become more prevalent in anesthesia practice, documentation of acute findings resulting in alteration in management based on real-time ultrasound findings during pediatric anesthesia remains limited. This case highlights the use of POCUS during cardiopulmonary collapse occurring during correction of neuromuscular scoliosis. POCUS excluded the presumed diagnosis of venous air embolism and identified an intracardiac thrombus leading to the diagnosis and treatment of pulmonary embolism.

A gray zone: Role of transesophageal echocardiography before atrial tachycardia catheter ablation.

INTRODUCTION: There is a lack of studies in the literature directly investigating the relationship between atrial tachycardia (AT) and left atrial (LA)/left atrial appendage (LAA) thrombus, and current guidelines do not provide strong recommendations regarding the use of transesophageal echocardiography (TEE) before AT catheter ablation. This study aims to elucidate the relationship between AT and the presence of LA/LAA thrombus and contribute to the literature on the use of TEE before AT catheter ablation. METHODS: This single-center retrospective observational study screened patients who underwent TEE between February 10, 2019, and February 10, 2023. Patients were assigned to the AT patient and control groups. TEE was conducted to exclude thrombus in the AT ablation group. The control group included patients who underwent TEE for interatrial septum evaluation and had LA imaging during TEE but did not have atrial arrhythmia. To mitigate bias between the AT patient group and the control group, they were randomized 1:1 using propensity-score matching (PSM). Following randomization, each group consisted of 49 patients. RESULTS: All analyses were conducted after PSM. There were no statistically significant differences between the AT patient and control groups in terms of baseline clinical characteristics and echocardiographic features. Additionally, no significant differences were found between the blood viscosities calculated at low and high shear rates in both groups. The study revealed a significant difference between the two groups in the presence of LA spontaneous echo contrast (SEC) (24.5% in AT group vs 0% in Control group, p = .001), but not in the presence of thrombi (8.2% in AT group vs 0% in Control group, p = .117). CONCLUSION: Compared to the control group, the presence of SEC was significantly higher in the AT patient group. The increased frequency of SEC in AT patients suggests the hypothesis that AT may contribute to LA stasis. The routine use of TEE before AT catheter ablation remains controversial, despite the presence of LA thrombus and SEC in the AT patient group. The clinical assessment of thrombus presence before the procedure must be conducted on a patient-specific basis.

Impact of left atrial appendage flow velocity on thrombus resolution and clinical outcomes in patients with atrial fibrillation and silent left atrial thrombi: insights from the LAT study.

AIMS: Blood stasis is crucial in developing left atrial (LA) thrombi. LA appendage peak flow velocity (LAAFV) is a quantitative parameter for estimating thromboembolic risk. However, its impact on LA thrombus resolution and clinical outcomes remains unclear. METHODS AND RESULTS: The LAT study was a multicentre observational study investigating patients with atrial fibrillation (AF) and silent LA thrombi detected by transoesophageal echocardiography (TEE). Among 17 436 TEE procedures for patients with AF, 297 patients (1.7%) had silent LA thrombi. Excluding patients without follow-up examinations, we enrolled 169 whose baseline LAAFV was available. Oral anticoagulation use increased from 85.7% at baseline to 97.0% at the final follow-up (P < 0.001). During 1 year, LA thrombus resolution was confirmed in 130 (76.9%) patients within 76 (34-138) days. Conversely, 26 had residual LA thrombi, 8 had thromboembolisms, and 5 required surgical removal. These patients with failed thrombus resolution had lower baseline LAAFV than those with successful resolution (18.0 [15.8-22.0] vs. 22.2 [17.0-35.0], P = 0.003). Despite limited predictive power (area under the curve, 0.659; P = 0.001), LAAFV ≤ 20.0 cm/s (best cut-off) significantly predicted failed LA thrombus resolution, even after adjusting for potential confounders (odds ratio, 2.72; 95% confidence interval, 1.22-6.09; P = 0.015). The incidence of adverse outcomes including ischaemic stroke/systemic embolism, major bleeding, or all-cause death was significantly higher in patients with reduced LAAFV than in those with preserved LAAFV (28.4% vs. 11.6%, log-rank P = 0.005). CONCLUSION: Failed LA thrombus resolution was not rare in patients with AF and silent LA thrombi. Reduced LAAFV was associated with failed LA thrombus resolution and adverse clinical outcomes.

Recurrent intra-cardiac thrombosis: A rare manifestation of Behçet's disease.

Behçet's disease is a systemic vasculitis characterized by recurrent bipolar aphtosis and ophthalmic disorders. Cardiac involvement is rarely reported and could be associated to poor prognosis. Intracardiac thrombosis is exceptional and represents a therapeutic issue. We report the case of a young man admitted in internal medicine department for management of prolonged fever and recurrent mouth ulcers.

Assessment of Native Myocardial T1 Mapping for Early Detection of Anthracycline-Induced Cardiotoxicity in Patients with Cancer: a Systematic Review and Meta-analysis.

Anthracycline antibiotic is one of the most effective anti-tumor drugs used to manage certain types of breast cancers, lymphomas, and leukemias. However, anthracyclines induce a dose-dependent cardiotoxicity that may progress to heart failure. Thus, using a sensitive predictor of early cardiac dysfunction in patients treated with anthracyclines can help detect subclinical cardiac dysfunction early and help initiate interventions to protect these patients. Among parameters of myocardial measure, cardiac magnetic resonance (CMR)-measured native myocardial T1 mapping is considered a sensitive and accurate quantitative measure of early subclinical cardiac changes, particularly cardiac inflammation and fibrosis. However, to understand the quality and the validity of the current evidence supporting the use of these measures in patients treated with anthracyclines, we aimed to conduct a systematic review of clinical studies of this measure to detect early myocardial changes in cancer patients treated with anthracyclines. The primary outcome was the level of native T1 mapping. We performed fixed-effects meta-analyses and assessed certainty in effect estimates. Of the 1780 publications reviewed (till 2022), 23 were retrieved, and 9 articles met the inclusion criteria. Our study showed that exposure to anthracycline was associated with a significant elevation of native myocardial T1 mapping from baseline (95% CI 0.1121 to 0.5802; p = 0.0037) as well as compared to healthy control patients (95% CI 0.2925 to 0.7448; p < 0.0001). No significant publication bias was noted on the assessment of the funnel plot and Egger's test. According to the Q test, there was no significant heterogeneity in the included studies (I2 = 0.0000% versus healthy controls and I2 = 14.0666% versus baseline). Overall, our study suggests that native myocardial T1 mapping is useful for detecting anthracycline-induced cardiotoxicity in patients with cancer.

Early myocardial injury in children on doxorubicin for cancer chemotherapy: a cross-sectional study in a tertiary referral centre in Kenya.

INTRODUCTION: Use of doxorubicin, an anthracycline chemotherapeutic agent has been associated with late-occurring cardiac toxicities. Detection of early-occurring cardiac effects of cancer chemotherapy is essential to prevent occurrence of adverse events including toxicity, myocardial dysfunction, and death. OBJECTIVE: To investigate the prevalence of elevated cardiac troponin T (cTnT) and associated factors of myocardial injury in children on doxorubicin cancer chemotherapy. METHODS: Design: A cross-sectional study. SETTING AND SUBJECTS: A hospital-based study conducted on children aged 1-month to 12.4-years who had a diagnosis of cancer and were admitted at Kenyatta National Hospital (KNH). INTERVENTIONS AND OUTCOMES: The patients underwent Echocardiography (ECHO) before their scheduled chemotherapy infusion. Twenty-four (24) hours after the chemotherapy infusion the patients had an evaluation of the serum cardiac troponin T (cTnT) and a repeat ECHO. Myocardial injury was defined as cTnT level > 0.014 ng/ml or a Fractional Shortening (FS) of < 29% on ECHO. RESULTS: One hundred (100) children were included in the final analysis. Thirty-two percent (32%) of the study population had an elevated cTnT. A cumulative doxorubicin dose of > 175 mg/m2 was significantly associated with and elevated cTnT (OR, 10.76; 95% CI, 1.18-97.92; p = 0.035). Diagnosis of nephroblastoma was also associated with an elevated cTnT (OR, 3.0; 95% CI, 1.23-7.26) but not statistically significant (p = 0.105). Nine percent (9%) of the participants had echocardiographic evidence of myocardial injury. CONCLUSION: When compared to echocardiography, elevated levels of cTnT showed a higher association with early-occurring chemotherapy-induced myocardial injury among children on cancer treatment at a tertiary teaching and referral hospital in Kenya.