The international journal of cardiovascular imaging最新文献

{"title":"Machine learning prediction of right ventricular volume and ejection fraction from two-dimensional echocardiography in patients with pulmonary regurgitation.","authors":"Son Q Duong, Calista Dominy, Naveen Arivazhagan, David M Barris, Kali Hopkins, Kenan W D Stern, Nadine Choueiter, David Ezon, Jennifer Cohen, Mark K Friedberg, Ali N Zaidi, Girish N Nadkarni","doi":"10.1007/s10554-025-03368-z","DOIUrl":"https://doi.org/10.1007/s10554-025-03368-z","url":null,"abstract":"<p><p>Right ventricular (RV) end-diastolic volume (RVEDV) and ejection fraction (RVEF) by cardiac MRI (cMRI) guide management in chronic pulmonary regurgitation (PR). Two-dimensional echocardiography suboptimally correlate with RV volumes. This study tested whether combination of guideline-directed RV measures in a machine learning (ML) framework improves quantitative assessment of RVEDV and RVEF. RV measurements were obtained on subjects with > mild PR who had cMRI and echocardiogram within 90 days. A gradient-boosted trees algorithm predicted cMRI RV dilation (RVEDV > 160 ml/m²) and RV dysfunction (RVEF<47%), first with \"guideline-only\" measures, and then with \"expanded-features\" to include 44 total echocardiographic, clinical, and demographic variables. Model performance was compared to clinician visual assessment. Of 232 studies (56% tetralogy of Fallot, 20% pulmonary stenosis), the median age was 21.5 years, 21 (9%) had RV dilation, and 42 (18%) had RV dysfunction. For RV dilation prediction, the guideline-only model area under the receiver operating characteristic (AUROC)=0.68, and expanded-features model AUROC=0.85. At 90% sensitivity, the expanded-features model had 73% specificity, 25% positive predictive value (PPV), and 99% negative predictive value (NPV) This was similar to clinician performance (sensitivity 81%, specificity 81%, PPV 29%, NPV 98%). For prediction of RV dysfunction, the guideline-only AUROC= 0.71, additional features did not improve the model, and clinicians outperformed the model. In patients with PR, a ML model combining guidelines for RV assessment with demographic and additional echocardiographic parameters may effectively rule-out those with significant RV dilation at clinical thresholds for intervention, and performs similarly to expert clinicians.</p>","PeriodicalId":94227,"journal":{"name":"The international journal of cardiovascular imaging","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143627068","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A case of constrictive pericarditis with aortic insufficiency: the role of cardiac magnetic resonance imaging.","authors":"Juthipong Benjanuwattra, Nicholas Biondi, Jonathan D Feazell, Sara A Dressman, David M Harris","doi":"10.1007/s10554-025-03373-2","DOIUrl":"https://doi.org/10.1007/s10554-025-03373-2","url":null,"abstract":"<p><p>Transthoracic echocardiography is recommended as a diagnostic test of choice for constrictive pericarditis. Nevertheless, several limitations exist. Hereby, we present the role of cardiac magnetic resonance imaging in a case of constrictive pericarditis with concurrent aortic insufficiency that masked the echocardiographic features of ventricular interdependence.</p>","PeriodicalId":94227,"journal":{"name":"The international journal of cardiovascular imaging","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143598684","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Reliability of spectral Doppler in handheld ultrasonographic device.","authors":"Dominika Filipiak-Strzecka, Jarosław D Kasprzak, Piotr Lipiec","doi":"10.1007/s10554-025-03372-3","DOIUrl":"https://doi.org/10.1007/s10554-025-03372-3","url":null,"abstract":"<p><p>To verify and validate the reliability of diastolic function parameters and valvular flow velocities acquired during the handheld ultrasound device (HUD) echocardiographic examination. Study population consisted of the consecutive patients referred for consultation due to dyspnea or impaired exercise tolerance. All patients underwent brief bedside echocardiographic screening with HUD. Within the next 24 h all patients underwent full echocardiographic examination (treated as reference). 105 patients (58 men, mean age 65 ± 14 years) were enrolled in the study. All correlations of HUD and standard echo derived measurements were high or very high. Bland-Altman plot analysis revealed the underestimation bias for mitral inflow velocities- early (E) and late (A), ), mitral annular peak early diastolic velocity (e') was not burdened with bias. The agreement between the major HFA-PEFF score parameters showed either substantial or almost perfect agreement, minor parameter- moderate agreement. The correlation of the measurements of maximum mitral velocity was high with no clinically relevant bias. Kappa coefficient showed very good agreement between HUD and reference echocardiography for detecting accelerated blood flow through the mitral valve (Kappa coefficient 0.83). The assessment of the aortic valve showed a very good correlation, with a slight underestimation bias of -0.17 m/sec (P <.001). Kappa coefficient showed good agreement between HUD and reference echocardiography for detecting accelerated blood flow (Kappa coefficient 0.74). HUD equipped with pulse and continuous wave Doppler modality enables reliable measurements of the parameters used during the left ventricle diastolic function assessment. Similarly, aortic and mitral peak jet velocities can be accurately measured using the mentioned devices.</p>","PeriodicalId":94227,"journal":{"name":"The international journal of cardiovascular imaging","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143598687","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Non-invasive derivation of instantaneous free-wave ratio from invasive coronary angiography using a new deep learning artificial intelligence model and comparison with human operators' performance.","authors":"Catarina Oliveira, Marta Vilela, João Silva Marques, Cláudia Jorge, Tiago Rodrigues, Ana Rita Francisco, Rita Marante de Oliveira, Beatriz Silva, João Lourenço Silva, Arlindo L Oliveira, Fausto J Pinto, Miguel Nobre Menezes","doi":"10.1007/s10554-025-03369-y","DOIUrl":"https://doi.org/10.1007/s10554-025-03369-y","url":null,"abstract":"<p><p>Invasive coronary physiology is underused and carries risks/costs. Artificial Intelligence (AI) might enable non-invasive physiology from invasive coronary angiography (CAG), possibly outperforming humans, but has seldom been explored, especially for instantaneous wave-free Ratio (iFR). We aimed to develop binary iFR lesion classification AI models and compare them with human performance. single-center retrospective study of patients undergoing CAG and iFR. A validated encoder-decoder convolutional neural network (CNN) performed segmentation. Manual annotation of target vessel and pressure sensor location on a segmented telediastolic frame followed. Three AI models classified lesions as positive (≤ 0.89) or negative (> 0.89). Model 1 uses preprocessed vessel diameters with a transformer. Models 2/3 are EfficientNet-B5 CNNs using concatenated angiography and segmentation - Model 3 employs class-frequency-weighted Cross-Entropy Loss. Previous findings demonstrated Model 3's superiority for left anterior descending (LAD) and Model 1's for circumflex (Cx)/right coronary artery (RCA) - they were therefore unified into a vessel-based model. Ten-fold patient-level cross-validation enabled full sample training/testing. Three experienced operators performed binary iFR classification using single frames of raw/segmented images. Comparison metrics were accuracy, sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV). Across 250 measurements, AI accuracy was 72%, PPV 48%, NPV 90%, sensitivity 77%, and specificity 71%. Human accuracy ranged from 54 to 74%. NPV was high for the Cx/RCA (AI: 96/98%; operators: 94/97%), but AI significantly outperformed humans in the LAD (78% vs. 60-64%). An AI model capable of binary iFR lesions classification mildly outperformed interventional cardiologists, supporting further validation studies.</p>","PeriodicalId":94227,"journal":{"name":"The international journal of cardiovascular imaging","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143598685","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Predicting the need for calcium modification techniques using computed tomography coronary angiography.","authors":"David Murphy, Benjamin Hudson, Stephen Lyen, Robert Lowe, Kevin Carson, Sri Raveen Kandan, Daniel McKenzie, Ali Khavandi, Jonathan Carl Luis Rodrigues","doi":"10.1007/s10554-025-03371-4","DOIUrl":"https://doi.org/10.1007/s10554-025-03371-4","url":null,"abstract":"<p><p>Calcified coronary arteries pose a challenge to percutaneous coronary intervention (PCI). Calcium modification techniques (CMTs) increase procedural length, complexity and risk. Computed tomography coronary angiography (CTCA) is well suited to calcium identification and quantification and may offer valuable pre-procedural information. We hypothesised that CTCA could predict cases where CMT would be required during PCI. A single centre retrospective review (2021/2022) of consecutive patients who underwent PCI with a preceding CTCA demonstrating a calcified lesion in a major epicardial vessel. Blinded to the PCI strategy CTCA images were re-reviewed and calcium thickness, length, density and circumferential arc quantified. Receiver operating characteristic (ROC) curve for CMT defined optimum cut-off values. Calcium density (> 1000 HU) and calcific arc (> 180°) were proposed as a calcium planning score (CPS_CTCA), with 1 point assigned per criteria met. 76 PCI procedures were included (72 patients). CMT was used in 53% at the discretion of the operator. Calcific arc, density, length and thickness had an area under the curve (AUC) of 0.74, 0.7, 0.67 and 0.63 respectively. There was a step-wise increase in the proportion of cases requiring CMT with increasing CPS_CTCA. 0 vs. 1 point; OR 9 (1.1-82, p =.04), RR 5 (0.8-36, p =.09), 1 vs. 2 points; OR 3.2 (1.1-9.3, p =.03), RR 1.6 (1-2.3, p =.04), 0 vs. 2 points; OR 30 (3.3-272, p =.003), RR of 8 (1.3-54, p =.03). The incorporation of CTCA measured calcium density > 1000 HU and calcium arc > 180° into a calcium planning score may help with predicting the need for CMT at the time of PCI.</p>","PeriodicalId":94227,"journal":{"name":"The international journal of cardiovascular imaging","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143598686","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Usefulness of two-dimensional speckle tracking echocardiography in assessment of left atrial fibrosis degree and its application in atrial fibrillation.","authors":"Yuzhe Song, Lijuan Huang, Cheng Jiang, Fang Du, Jing Zhang, Peng Chang","doi":"10.1007/s10554-025-03345-6","DOIUrl":"https://doi.org/10.1007/s10554-025-03345-6","url":null,"abstract":"<p><p>This study aimed to establish a clinical prediction model for assessing the degree of left atrial fibrosis (LAF) in patients with atrial fibrillation (AF) by combining two-dimensional speckle tracking echocardiography (2D-STE). Additionally, the study sought to evaluate the predictive utility of 2D-STE for left atrial appendage thrombosis (LAAT) and the recurrence of AF after radiofrequency catheter ablation (RFA). A total of 195 patients with AF were included, and late gadolinium enhanced cardiac magnetic resonance was adopted to assess LAF degree. Fibrotic tissue as a percentage of total left atrial wall volume > 20% was defined as severe LAF. Echocardiographic parameters were obtained and analyzed using 2D-STE. The patients were randomly divided into two cohorts (7:3) as the training and testing cohorts. Independent predictors of severe LAF were determined via univariate and multivariate logistic regression, including age, CHA₂DS₂-VA score, left atrial appendage emptying fraction (LAA-EF), peak atrial longitudinal strain (PALS), left atrial stiffness index (LASI), left atrial strain during contraction phase (LASct) and left atrial strain during conduit phase (LAScd). The nomogram was established with the above variables and the area under the curve of the nomogram in testing cohorts was 0.89 (95% CI, 0.80-0.98). As validated by receiver operating characteristic curves, calibration curves and decision curve analysis, the nomogram model demonstrated promising potential for clinical application. Besides, by univariate and multivariate logistic regression analyses, CHA₂DS₂-VA score, uric acid, LAA-EF, left atrial appendage peak blood flow emptying velocity (LAA-PEV) and LASct were found to be independent predictors of LAAT, and left atrial appendage length, E/e' and LASct were found to be independent predictors of post-ablation AF recurrence. 2D-STE can be applied to evaluate LAF degree of AF patients and predict LAAT and AF recurrence.</p>","PeriodicalId":94227,"journal":{"name":"The international journal of cardiovascular imaging","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143598688","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Cross-sectional imaging for presurgical planning of dialysis circuit vascular access creation in the end stage renal disease patient population.","authors":"Daniel Raskin, Levester Kirksey, Abraham Levitin, Ali Khalifeh, Jon G Quatromoni, Sean P Lyden, Cassandra Kovach, Patrick Ghibes, Amrit Khooblall, Sasan Partovi","doi":"10.1007/s10554-025-03357-2","DOIUrl":"https://doi.org/10.1007/s10554-025-03357-2","url":null,"abstract":"<p><p>This systematic review explores the role of cross-sectional imaging modalities-computed tomography angiography (CTA) and magnetic resonance angiography (MRA)-in the preoperative planning of dialysis vascular access for patients with end-stage renal disease (ESRD). A systematic search was conducted using PubMed and Cochrane databases, yielding 45 studies meeting inclusion criteria. These modalities are particularly valuable in cases of complex vascular anatomy, central venous stenosis, and prior surgical interventions. Findings emphasize the advantages of CTA for detailed anatomical mapping and MRA for cases requiring soft-tissue contrast or preservation of renal function. Representative clinical cases illustrate how imaging findings directly influence surgical and endovascular decision-making, optimizing patient outcomes. This manuscript describes the role of cross-sectional imaging for dialysis circuit vascular access interventions including representative clinical examples.</p>","PeriodicalId":94227,"journal":{"name":"The international journal of cardiovascular imaging","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-03-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143574946","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Value of upfront coronary computed tomography angiography in patients with non-ST-segment elevation acute coronary syndrome.","authors":"Zhong-Fei Lu, Wei-Hua Yin, Bin Lu","doi":"10.1007/s10554-025-03360-7","DOIUrl":"https://doi.org/10.1007/s10554-025-03360-7","url":null,"abstract":"<p><p>This study aimed to evaluate the diagnostic performance of coronary computed tomography angiography (CCTA) in ruling out coronary artery stenosis ≥ 70% across all segments and its role in providing preprocedural guidance for chronic total occlusion (CTO) management in patients with non-ST-segment elevation acute coronary syndrome (NSTE-ACS). This study was a post hoc analysis of a prospective, multicenter cohort comprising 347 patients with NSTE-ACS. All patients underwent CCTA immediately after being diagnosed with NSTE-ACS, followed by invasive coronary angiography (ICA) within 1 day. The diagnostic performance of CCTA in ruling out obstructive coronary stenosis was assessed using negative predictive value (NPV). Additionally, segments distal to CTO were analyzed to compare the detection capabilities of CCTA and ICA. The NPV of CCTA for ruling out coronary stenosis ≥ 70% was robust, ranging from 94.7 to 100.0% across the 18-segment model at the segment level, and 25.9% of patients had no significant stenosis and could have avoided unnecessary ICA based on CCTA findings. CCTA identified 71.0% of segments distal to CTO, significantly higher than ICA (48.8%, P < 0.001). 25.1% of patients had CTO, where CCTA provided valuable preprocedural guidance for revascularization. CCTA demonstrated high diagnostic accuracy in ruling out significant stenosis and provided critical information for CTO revascularization, highlighting its potential as a triaging and planning tool in NSTE-ACS.</p>","PeriodicalId":94227,"journal":{"name":"The international journal of cardiovascular imaging","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-03-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143569308","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Positional mitral regurgitation: a dynamic phenomenon.","authors":"Marta Leite, Eduardo Vilela, Jorge Oliveira, Ricardo Fontes-Carvalho","doi":"10.1007/s10554-025-03364-3","DOIUrl":"https://doi.org/10.1007/s10554-025-03364-3","url":null,"abstract":"<p><p>Mitral regurgitation (MR) is a dynamic condition influenced by positional changes and physical stress. We report a case of severe positional MR in a 74-year-old woman with dilated cardiomyopathy, highlighted by echocardiographic findings of leaflet tethering and restricted mobility. Upright positioning significantly alleviated symptoms and MR severity, underscoring the impact of hemodynamic factors on its clinical presentation.</p>","PeriodicalId":94227,"journal":{"name":"The international journal of cardiovascular imaging","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-03-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143560504","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multimodal deep learning for predicting in-hospital mortality in heart failure patients using longitudinal chest X-rays and electronic health records.","authors":"Dengao Li, Wen Xing, Jumin Zhao, Changcheng Shi, Fei Wang","doi":"10.1007/s10554-025-03322-z","DOIUrl":"10.1007/s10554-025-03322-z","url":null,"abstract":"<p><p>Amid an aging global population, heart failure has become a leading cause of hospitalization among older people. Its high prevalence and mortality rates underscore the importance of accurate mortality prediction for swift disease progression assessment and better patient outcomes. The evolution of artificial intelligence (AI) presents new avenues for predicting heart failure mortality. Yet current research has predominantly leveraged structured data and unstructured clinical notes from electronic health records (EHR), underutilizing the prognostic value of chest X-rays (CXRs). This study aims to harness deep learning methodologies to explore the feasibility of enhancing the precision of predicting in-hospital all-cause mortality in heart failure patients using CXRs data. We propose a novel multimodal deep learning network based on the spatially and temporally decoupled Transformer (MN-STDT) for in-hospital mortality prediction in heart failure by integrating longitudinal CXRs and structured EHR data. The MN-STDT captures spatial and temporal information from CXRs through a Hybrid Spatial Encoder and a Distance-Aware Temporal Encoder, ultimately fusing features from both modalities for predictive modeling. Initial pre-training of the spatial encoder was conducted on CheXpert, followed by full model training and evaluation on the MIMIC-IV and MIMIC-CXR datasets for mortality prediction tasks. In a comprehensive view, the MN-STDT demonstrated the best performance, with an AUC-ROC of 0.8620, surpassing all baseline models. Comparative analysis revealed that the AUC-ROC of the multimodal model (0.8620) was significantly higher than that of models using only structured data (0.8166) or chest X-ray data alone (0.7479). This study demonstrates the value of CXRs in the prognosis of heart failure, showing that the combination of longitudinal CXRs with structured EHR data can significantly improve the accuracy of mortality prediction in heart failure. Feature importance analysis based on SHAP provides interpretable decision support, paving the way for potential clinical applications.</p>","PeriodicalId":94227,"journal":{"name":"The international journal of cardiovascular imaging","volume":" ","pages":"427-440"},"PeriodicalIF":0.0,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142960874","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}