European heart journal. Imaging methods and practice最新文献

Coronary artery disease (CAD) remains one of the most frequent comorbidities among transcatheter aortic valve implantation (TAVI) candidates. Whether routine assessment of CAD by invasive coronary angiography (CA) and eventual peri-procedural percutaneous coronary intervention (PCI) is generally beneficial in TAVI patients has recently been heavily questioned. CA carries significant risks, such as kidney injury, bleeding, and prolonged hospital stay, and may frequently be unnecessary if significant stenoses of the proximal coronary segments can be ruled out on computed tomography angiography. Moreover, the benefits of pre-emptive coronary revascularization at the time of TAVI are not well defined. Despite these facts and weak guideline recommendations, CA and eventual PCI of stable significant coronary lesions at the time of TAVI remain common practice. However, ongoing randomized trials currently challenge the efficacy of such strategies to enable a more streamlined, individualized, and resource-sparing treatment with TAVI.

Aims: To address the limitations of traditional diagnostic methods for mitral valve prolapse (MVP), specifically fibroelastic deficiency (FED) and Barlow's disease (BD), by introducing an automated diagnostic approach utilizing multi-view echocardiographic sequences and deep learning.

Methods and results: An echocardiographic data set, collected from Zhongshan Hospital, Fudan University, containing apical 2 chambers (A2C), apical 3 chambers (A3C), and apical 4 chambers (A4C) views, was employed to train the deep learning models. We separately trained view-specific and view-agnostic deep neural network models, which were denoted as MVP-VS and MVP view-agonistic (VA), for MVP diagnosis. Diagnostic accuracy, precision, sensitivity, F1-score, and specificity were evaluated for both BD and FED phenotypes. MVP-VS demonstrated an overall diagnostic accuracy of 0.94 for MVP. In the context of BD diagnosis, precision, sensitivity, F1-score, and specificity were 0.83, 1.00, 0.90, and 0.92, respectively. For FED diagnosis, the metrics were 1.00, 0.83, 0.91, and 1.00. MVP-VA exhibited an overall accuracy of 0.95, with BD-specific metrics of 0.85, 1.00, 0.92, and 0.94 and FED-specific metrics of 1.00, 0.83, 0.91, and 1.00. In particular, the MVP-VA model using mixed views for training demonstrated efficient diagnostic performance, eliminating the need for repeated development of MVP-VS models and improving the efficiency of the clinical pipeline by using arbitrary views in the deep learning model.

Conclusion: This study pioneers the integration of artificial intelligence into MVP diagnosis and demonstrates the effectiveness of deep neural networks in overcoming the challenges of traditional diagnostic methods. The efficiency and accuracy of the proposed automated approach suggest its potential for clinical applications in the diagnosis of valvular heart disease.

Aims: The clinical utility of regional strain measurements in echocardiography is challenged by suboptimal reproducibility. In this study, we aimed to evaluate the test-retest reproducibility of regional longitudinal strain (RLS) per coronary artery perfusion territory (RLS_Territory) and basal-to-apical level of the left ventricle (RLS_Level), measured by a novel fully automated deep learning (DL) method based on point tracking.

Methods and results: We measured strain in a dual-centre test-retest data set that included 40 controls and 40 patients with suspected non-ST elevation acute coronary syndrome. Two consecutive echocardiograms per subject were recorded by different operators. The reproducibility of RLS_Territory and RLS_Level measured by the DL method and by three experienced observers using semi-automatic software (2D Strain, EchoPAC, GE HealthCare) was evaluated as minimal detectable change (MDC). The DL method had MDC for RLS_Territory and RLS_Level ranging from 3.6 to 4.3%, corresponding to a 33-35% improved reproducibility compared with the inter- and intraobserver scenarios (MDC 5.5-6.4% and 4.9-5.4%). Furthermore, the DL method had a lower variance of test-retest differences for both RLS_Territory and RLS_Level compared with inter- and intraobserver scenarios (all P < 0.001). Bland-Altman analyses demonstrated superior reproducibility by the DL method for the whole range of strain values compared with the best observer scenarios. The feasibility of the DL method was 93% and measurement time was only 1 s per echocardiogram.

Conclusion: The novel DL method provided fully automated measurements of RLS, with improved test-retest reproducibility compared with semi-automatic measurements by experienced observers. RLS measured by the DL method has the potential to advance patient care through a more detailed, more efficient, and less user-dependent clinical assessment of myocardial function.

Aims: Structural heart defects, including congenital ventricular septal defect closure or intracardiac rerouting, frequently require surgical reconstruction using hand-cut patch materials. Digitally modelled patch templates may improve patch fit and reduce outflow tract obstruction, residual defect risk, and conduction system damage. In this study, we benchmarked mixed-reality and a desktop application against a digitalized model of a real implanted patch.

Methods and results: Ten patients scheduled for the repair of various defects consented to prospective inclusion in the study. After surgery, a digital model of the implanted patch was created from the residual material. Five clinical experts created 10 digital patches, 1 per patient, both in mixed-reality and desktop application, for comparison with the reference measurements, including the digitalized model of the real patch used during the surgery. Subjective residual shunt risk prediction was performed using both modalities. Digital patches created in mixed-reality closely matched the surgical material, whereas those created using desktop applications were significantly smaller. Different evaluators showed varying preferences for the application of the residual shunt risk and area.

Conclusion: Digitally created patches can assist surgeons in preoperatively sizing of patch implants, potentially reducing post-operative complications.

Aims: This study aims to assess the diagnostic performance of a novel computed tomography-derived fractional flow reserve (CT-FFR) algorithm and to compare its accuracy at three predefined sites: (i) at the location of invasive FFR measurements (CT-FFR_atloc), (ii) at selected sites determined by an automated module integrated within the algorithm (CT-FFR_auto), and (iii) distally in the vessel (CT-FFR_distal).

Methods and results: We prospectively recruited 108 consecutive patients with stable symptoms of coronary artery disease and at least one suspected obstructive lesion on coronary computed tomography angiography (CCTA). CT-FFR was validated against invasive FFR as gold standard using FFR ≤ 0.80 to define myocardial ischaemia. CT-FFR_atloc showed good correlation with invasive FFR (r = 0.67) and improved the ability to detect myocardial ischaemia compared with CCTA at both lesion [area under the curve (AUC) 0.83 vs. 0.65, P < 0.001] and patient level (AUC 0.87 vs. 0.74, P = 0.007). CT-FFR_auto demonstrated similar diagnostic accuracy to CT-FFR_atloc and significantly improved specificity compared with CT-FFR_distal (86% vs. 49%, P < 0.001). High end CT quality improved the diagnostic performance of CT-FFR_auto, demonstrating an AUC of 0.92; similarly, the performance was improved in patients with low-to-intermediate coronary artery calcium score with an AUC of 0.88.

Conclusion: Implementing an automated module to determine the site of CT-FFR evaluations was feasible, and CT-FFR_auto demonstrated comparable diagnostic accuracy to CT-FFR_atloc when assessed against invasive FFR. Both CT-FFR_atloc and CT-FFR_auto improved the diagnostic performance compared with CCTA and improved specificity compared with CT-FFR_distal. High end CT quality and low-to-intermediate calcium burden improved the diagnostic performance of our algorithm.

Clinicaltrialsgov identifier: NCT03045601.

[This corrects the article DOI: 10.1093/ehjimp/qyae062.].