Deep Learning for Echo Analysis, Tracking, and Evaluation of Mitral Regurgitation (DELINEATE-MR).

BACKGROUND: Artificial intelligence, particularly deep learning (DL), has immense potential to improve the interpretation of transthoracic echocardiography (TTE). Mitral regurgitation (MR) is the most common valvular heart disease and presents unique challenges for DL, including the integration of multiple video-level assessments into a final study-level classification. METHODS: A novel DL system was developed to intake complete TTEs, identify color MR Doppler videos, and determine MR severity on a 4-step ordinal scale (none/trace, mild, moderate, and severe) using the reading cardiologist as a reference standard. This DL system was tested in internal and external test sets with performance assessed by agreement with the reading cardiologist, weighted κ, and area under the receiver-operating characteristic curve for binary classification of both moderate or greater and severe MR. In addition to the primary 4-step model, a 6-step MR assessment model was studied with the addition of the intermediate MR classes of mild-moderate and moderate-severe with performance assessed by both exact agreement and ±1 step agreement with the clinical MR interpretation. RESULTS: A total of 61 689 TTEs were split into train (n=43 811), validation (n=8891), and internal test (n=8987) sets with an additional external test set of 8208 TTEs. The model had high performance in MR classification in internal (exact accuracy, 82%; κ=0.84; area under the receiver-operating characteristic curve, 0.98 for moderate/severe MR) and external test sets (exact accuracy, 79%; κ=0.80; area under the receiver-operating characteristic curve, 0.98 for moderate or greater MR). Most (63% internal and 66% external) misclassification disagreements were between none/trace and mild MR. MR classification accuracy was slightly higher using multiple TTE views (accuracy, 82%) than with only apical 4-chamber views (accuracy, 80%). In subset analyses, the model was accurate in the classification of both primary and secondary MR with slightly lower performance in cases of eccentric MR. In the analysis of the 6-step classification system, the exact accuracy was 80% and 76% with a ±1 step agreement of 99% and 98% in the internal and external test set, respectively. CONCLUSIONS: This end-to-end DL system can intake entire echocardiogram studies to accurately classify MR severity and may be useful in helping clinicians refine MR assessments.

An attention-based deep learning method for right ventricular quantification using 2D echocardiography: Feasibility and accuracy.

AIM: To test the feasibility and accuracy of a new attention-based deep learning (DL) method for right ventricular (RV) quantification using 2D echocardiography (2DE) with cardiac magnetic resonance imaging (CMR) as reference. METHODS AND RESULTS: We retrospectively analyzed images from 50 adult patients (median age 51, interquartile range 32-62 42% women) who had undergone CMR within 1 month of 2DE. RV planimetry of the myocardial border was performed in end-diastole (ED) and end-systole (ES) for eight standardized 2DE RV views with calculation of areas. The DL model comprised a Feature Tokenizer module and a stack of Transformer layers. Age, gender and calculated areas were used as inputs, and the output was RV volume in ED/ES. The dataset was randomly split into training, validation and testing subsets (35, 5 and 10 patients respectively). Mean RVEDV, RVESV and RV ejection fraction (EF) were 163 ± 70 mL, 82 ± 42 mL and 51% ± 8% respectively without differences among the subsets. The proposed method achieved good prediction of RV volumes (R2  = .953, absolute percentage error [APE] = 9.75% ± 6.23%) and RVEF (APE = 7.24% ± 4.55%). Per CMR, there was one patient with RV dilatation and three with RV dysfunction in the testing dataset. The DL model detected RV dilatation in 1/1 case and RV dysfunction in 4/3 cases. CONCLUSIONS: An attention-based DL method for 2DE RV quantification showed feasibility and promising accuracy. The method requires validation in larger cohorts with wider range of RV size and function. Further research will focus on the reduction of the number of required 2DE to make the method clinically applicable.

Transcatheter aortic valve-in-valve implantation within stentless landing zones: Procedural insights from a single-center experience.

BACKGROUND: Valve-in-valve (VIV) transcatheter aortic valve implantation (TAVI) is a less invasive therapeutic option compared with redo surgical valve replacement for high-risk patients. Relative to procedures within stented surgical valves, VIV-TAVI within stentless valves is associated with a higher complication rate due to challenging underlying anatomy and absence of fluoroscopic landmarks. AIMS: We share a single-center experience with VIV-TAVI in stentless valves, discussing our procedural insights and associated outcomes. METHODS: Our institutional database was queried, and 25 patients who had undergone VIV-TAVI within a stentless bioprosthesis, homograft, or valve-sparing aortic root replacement between 2013 and 2022 were found. Outcome endpoints were based on the Valve Academic Research Consortium-3 criteria. RESULTS: The mean age of the cohort was 69.5 ± 13.6 years. VIV implantation was performed within a homograft in 11 patients, a stentless bioprothesis in 10 patients, and a valve-sparing aortic root replacement in 4 patients. Nineteen (76%) balloon-expandable valves, 5 (20%) self-expanding valves, and one mechanically-expandable (4%) valve were implanted with 100% procedural success, with no instances of significant paravalvular leak, coronary occlusion, or device embolization. There was one (4%) in-hospitality mortality after an emergency procedure; one (4%) patient experienced a transient ischemic attack; and two (8%) patients required permanent pacemaker implantation. The median length of hospital stay was 2 days. After a median follow-up time of 16.5 months, valve function was acceptable in all patients with available data. CONCLUSION: VIV-TAVI within stentless valves can be safely performed with methodical procedural technique and can provide clinical benefit in patients at high reoperation risk.

Valvular Heart Failure due to Tricuspid Regurgitation: Surgical and Transcatheter Management Options.

Given the independent association of mortality with higher grades of tricuspid regurgitation severity, there is an increasing interest in improving the outcomes of this prevalent valvular heart disease. A new classification of tricuspid regurgitation etiology allows for an improved understanding of different pathophysiologic forms of the disease, which may determine the appropriate management strategy. Current surgical outcomes remain suboptimal and multiple transcatheter device therapies are currently under investigation to give high and prohibitive surgical risk patients treatment options beyond medical therapy.

Mitral Regurgitation in 2020: The 2020 Focused Update of the 2017 American College of Cardiology Expert Consensus Decision Pathway on the Management of Mitral Regurgitation.

The recently published "2020 Focused Update of the 2017 ACC Expert Consensus Decision Pathway on the Management of Mitral Regurgitation" provides a framework for the clinical and echocardiographic assessment of mitral regurgitation and describes considerations for the medical, surgical, and transcatheter treatment of mitral regurgitation. The Update provides guidance for clinicians in light of the significant interim developments since the 2017 recommendations, particularly in the areas of secondary mitral regurgitation and transcatheter mitral valve repair. The present review focuses on the aspects of the Update that are most relevant to the cardiac anesthesiologist, with emphasis on the integrated assessment of mitral regurgitation with echocardiography and the indications and considerations for the surgical and transcatheter management of mitral regurgitation.

Computed tomography anatomic predictors of outcomes in patients undergoing tricuspid transcatheter edge-to-edge repair.

AIM: To identify anatomical computed tomography (CT) predictors of procedural and clinical outcomes in patients undergoing tricuspid transcatheter edge-to-edge repair (T-TEER). METHODS AND RESULTS: Consecutive patients undergoing T-TEER between March 2018 to December 2022 who had cardiac CT prior to the procedure were included. CT scans were automatically analyzed using a dedicated software that employs deep learning techniques to provide precise anatomical measurements and volumetric calculations. Technical success was defined as successful placement of at least one implant in the planned anatomic location without single leaflet device attachment. Procedural success was defined as tricuspid regurgitation reduction to moderate or less. Procedural complexity was assessed by measuring the fluoroscopy time. The clinical endpoint was a composite of death, heart failure hospitalization, or tricuspid re-intervention throughout two years. A total of 33 patients (63.6% male) were included. Procedural success was achieved in 22 patients (66.7%). Shorter end-systolic (ES) height between the inferior vena cava (IVC) and tricuspid annulus (TA) (r â€‹= â€‹- 0.398, p â€‹= â€‹0.044) and longer ES RV length (r â€‹= â€‹0.551, p â€‹= â€‹0.006) correlated with higher procedural complexity. ES RV length was independently associated with lower technical(adjusted Odds ratio [OR] 0.812 [95% CI 0.665-0.991], p â€‹= â€‹0.040) and procedural success (adjusted OR 0.766, CI [0.591-0.992], p â€‹= â€‹0.043). Patients with ES right ventricular (RV) length of >77.4 â€‹mm had a four-fold increased risk of experiencing the composite clinical endpoint compared to patients with ES RV length ≤77.4 â€‹mm (HR â€‹= â€‹3.964 [95% CI, 1.018-15.434]; p â€‹= â€‹0,034]). CONCLUSION: CT-derived RV length and IVC-to-TA height may be helpful to identify patients at increased risk for procedural complexity and adverse outcomes when undergoing T-TEER. CT provides valuable information for preprocedural decision-making and device selection.

Contemporary Evaluation and Clinical Treatment Options for Aortic Regurgitation.

Aortic regurgitation (AR) is the third most frequent form of valvular disease and has increasing prevalence with age. This will be of increasing clinical importance with the advancing age of populations around the globe. An understanding of the various etiologies and mechanisms leading to AR requires a detailed understanding of the structure of the aortic valve and aortic root. While acute and chronic AR may share a similar etiology, their hemodynamic impact on the left ventricle (LV) and management are very different. Recent studies suggest current guideline recommendations for chronic disease may result in late intervention and suboptimal outcomes. Accurate quantitation of ventricular size and function, as well as grading of the severity of regurgitation, requires a multiparametric and multimodality imaging approach with an understanding of the strengths and weaknesses of each metric. Echocardiography remains the primary imaging modality for diagnosis with supplemental information provided by computed tomography (CT) and cardiac magnetic resonance imaging (CMR). Emerging transcatheter therapies may allow the treatment of patients at high risk for surgery, although novel methods to assess AR severity and its impact on LV size and function may improve the timing and outcomes of surgical intervention.

Multimodality imaging for transcatheter tricuspid valve repair and replacement.

Transcatheter tricuspid intervention is a rapidly evolving field with multiple classes of therapeutic devices currently in development. Procedural success in tricuspid intervention is predicated on appropriate device selection for patient specific anatomy and satisfactory imaging for intra-procedural guidance. This review will outline protocols and methodology for multi-modality imaging assessment of the tricuspid valve and associated structures, with emphasis on anatomic and functional characteristics that determine suitability for each class of tricuspid intervention. Intra-procedural imaging requirements for each class of device, with design and procedural imaging guidance of specific devices, will also be addressed.

Tricuspid Leaflet Gap-Reduction Maneuvers During Transcatheter Tricuspid Valve Repair.

Transcatheter tricuspid valve edge-to-edge repair (T-TEER) has emerged as an option for treating patients with tricuspid regurgitation. Few studies have explored intraprocedural maneuvers to optimize leaflet-grasping T-TEER in order to improve technical success. This case series of 3 patients describes maneuvers that facilitated T-TEER in patients with large coaptation gaps or short leaflet lengths. (Level of Difficulty: Advanced.).

Zero-Contrast Left Atrial Appendage Occlusion Using a Hybrid Echocardiography-Fluoroscopy Technique Without Iodinated Contrast.

Contrast exposure during left atrial appendage occlusion may be harmful in those with chronic kidney disease or allergy. This single-center registry (n = 31) demonstrates the feasibility and safety of zero-contrast percutaneous left atrial appendage occlusion using echocardiography, fluoroscopy, and fusion imaging, with 100% procedural success and no device complications at 45 days.

Restructuring Structural Heart Disease Practice During the COVID-19 Pandemic: JACC Review Topic of the Week.

Patients with structural heart disease are at increased risk of adverse outcomes from the coronavirus disease-2019 (COVID-19) due to advanced age and comorbidity. In the midst of a global pandemic of a novel infectious disease, reality-based considerations comprise an important starting point for formulating clinical management pathways. The aims of these "crisis-driven" recommendations are: 1) to ensure appropriate and timely treatment of structural heart disease patients; 2) to minimize the risk of COVID-19 exposure to patients and health care workers; and 3) to limit resource utilization under conditions of constraint. Although the degree of disruption to usual practice will vary across the United States and elsewhere, we hope that early experiences from a heart team operating in the current global epicenter of COVID-19 may prove useful for others adapting their practice in advance of local surges of COVID-19.