The international journal of cardiovascular imaging最新文献

The role of right ventricular (RV) dysfunction in pulmonary hypertension (PH) has garnered increasing interest in terms of outcomes. This systematic review and meta-analysis evaluated the prognostic utility of three-dimensional echocardiography (3DE) derived right ventricular ejection fraction (RVEF) in PH. A systematic review and meta-analysis were performed using MEDLINE, Embase, and Scopus databases for publications reporting the hazard ratio (HR) of 3DE-derived RVEF in PH patients for the clinical end-points of composite outcome or all-cause mortality. Nine articles totaling 885 subjects were included, among which 67.23% had pulmonary arterial hypertension (PAH), with the remainder having a range of PH etiologies. The mean value of 3DE-derived RVEF was 35.5 ± 9.07% reflecting impaired RV function. The primary endpoint was all-cause mortality in three studies, while the rest of the studies reported composite outcomes. Follow-up duration ranges from 6 to 44 months. From seven publications, the pooled HR by 3DE-derived RVEF was 0.91 (95% CI: 0.85 to 0.97, p = 0.001; heterogeneity: I² = 62%, p = 0.004). In subgroup analysis, 3DE-derived RVEF was a significant prognostic factor for group 1 PH (HR: 0.90, CI: 0.86-0.94; heterogeneity I² = 43%, p < 0.0001). From meta-regression analysis, only follow-up duration was found statistically significant with the HR of RVEF in the population (estimate: 0.028, p = 0.026). 3DE-derived RVEF provides important prognostic value in a large population of PH patients, especially for group 1 PH. Further accumulation of evidence is needed to perform a detailed subgroup analysis in each type of PH.

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.

The initial evaluation of stenosis during coronary angiography is typically performed by visual assessment. Visual assessment has limited accuracy compared to fractional flow reserve and quantitative coronary angiography, which are more time-consuming and costly. Applying deep learning might yield a faster and more accurate stenosis assessment. We developed a deep learning model to classify cine loops into left or right coronary artery (LCA/RCA) or "other". Data were obtained by manual annotation. Using these classifications, cine loops before revascularization were identified and curated automatically. Separate deep learning models for LCA and RCA were developed to estimate stenosis using these identified cine loops. From a cohort of 19,414 patients and 332,582 cine loops, we identified cine loops for 13,480 patients for model development and 5056 for internal testing. External testing was conducted using automated identified cine loops from 608 patients. For identification of significant stenosis (visual assessment of diameter stenosis > 70%), our model obtained a receiver operator characteristic (ROC) area under the curve (ROC-AUC) of 0.903 (95% CI: 0.900-0.906) on the internal test. The performance was evaluated on the external test set against visual assessment, 3D quantitative coronary angiography, and fractional flow reserve (≤ 0.80), obtaining ROC AUC values of 0.833 (95% CI: 0.814-0.852), 0.798 (95% CI: 0.741-0.842), and 0.780 (95% CI: 0.743-0.817), respectively. The deep-learning-based stenosis estimation models showed promising results for predicting stenosis. Compared to previous work, our approach demonstrates performance increase, includes all 16 segments, does not exclude revascularized patients, is externally tested, and is simpler using fewer steps.

Our study aims to assess the robustness of myocardial radiomic texture features (RTF) to segmentation variability and variations across scanners with different field strengths, addressing concerns about reliability in clinical practices. We conducted a retrospective analysis on 45 pairs of CMR T1 maps from 15 healthy volunteers using 1.5 T and 3 T Siemens scanners. Manual left ventricular myocardium segmentation and a deep learning-based model with Monte Carlo Dropout generated masks with different levels of variability and 1023 RTFs extracted from each region of interest (ROI). Reproducibility: the extent to which RTFs extracted from 1.5 T and 3 T images are consistent, and repeatability: the extent to which RTFs extracted from multiple segmentation runs at the same field strength agree with each other, were measured by the intraclass correlation coefficient (ICC). We categorized ICC values as excellent, good, moderate, and poor. We reported the proportion of RTFs that fell in each category. The proportion of RTFs with excellent repeatability decreased as the proportion of ROI pixels in congruence across segmentation runs decreased. Up to 31% of RTFs showed excellent repeatability, while 35% showed good repeatability across segmentation runs from the manually generated masks. Across scanners (i.e., 1.5 T vs 3 T), only 7% exhibited good reproducibility. While our results demonstrate RTF sensitivity to differences in field strength and segmentation variability, we identified certain preprocessing filters and feature classes that are less sensitive to these variations and, as such, may be good candidates for imaging biomarkers or building machine-learning models.

T1 relaxation time quantification on parametric maps is routinely used in cardiac imaging and may serve as a non-invasive biomarker for diffuse liver disease. In this study, we aimed to investigate the relationship between liver T1 values and cardiac function in patients with congenital heart disease (CHD) and compared patients with a biventricular circulation (BVC) to those with a Fontan circulation (FC). Magnetic resonance images from patients with CHD, obtained between June and December 2023 on a 1.5 T machine, were retrospectively reviewed. The examinations included cardiac cine sequences to assess ventricular mass and volumes, along with liver T1 mapping. T1 values were measured in eight liver segments and were compared with ventricular mass and volumes in patients with BVC and FC. In total, 104 patients (75 with BVC and 29 with FC) were included. T1 values varied significantly among the eight liver segments in both patient groups. In an age-matched comparison, patients with FC had significantly higher T1 values in all liver segments. In patients with BVC and right ventricular (RV) enlargement, a positive correlation between RV volume and T1 values in the right liver lobe was found (R > 0.504, p < 0.033). In patients with FC, the T1 values did not differ between patients with an extracardiac conduit or a lateral tunnel. Liver T1 mapping suggests more severe liver affection in patients with FC compared to those with BVC. It seems a valuable addition to cardiovascular magnetic resonance for patients who are at risk of systemic venous congestion.

Endovascular treatment (EVT) for patients with lower extremity artery disease is widely used as a less invasive alternative to surgical bypass. Recently, transradial artery intervention has gained popularity owing to its minimally invasive nature. The distance from the radial artery to the target vessel is critical for success; however, effective pre-assessment methods have not yet been established. This study aimed to evaluate the usefulness of predistance measurements from the left radial artery using simple computed tomography (CT) images. In this study, distance measurements were performed from the left radial artery to the left and right iliac artery bifurcations and from the left radial artery to the common femoral artery at the upper femoral border. These distances, measured using CT images before and after the lower-extremity contrast study, were compared with the distances identified during the lower-extremity contrast study. Distances measured using simple CT images showed a high correlation with the distances identified during the lower-extremity contrast examination (r = 0.9317, p < 0.0001; from the left radial artery to the left and right iliac artery bifurcation; r = 0.9402, p < 0.0001; and from the left radial artery to the right common femoral artery at the upper femoral border). Our results suggest that pre-distance measurement using simple CT images can be a useful tool for EVT using the left radial artery approach. Although future large-scale studies are required, this technique merits consideration owing to its widespread adoption in clinical practice.

A 65-year-old woman with a history of ductal mammary carcinoma and recent autonomic dysfunction underwent a Rb-82 chloride (RbCl) cardiac PET/CT scan that showed no ischemia or scarring, but significantly reduced myocardial flow reserve (MFR) (global: 1.5) and a CAC-Score of 0. The patient's chemotherapy history (paclitaxel, carboplatin, epirubicin, pembrolizumab 2 years before) with elevated Troponin T and NT-pro-BNP levels at that time, and now reduced MFR with 0 CAC suggests cancer-therapy-related cardiotoxicity. An important differential diagnosis to the more common CAD-associated microvascular disease. Furthermore, tumor recurrence with a PET-avid lymph node metastasis was found additionally.