ESPNet: An Automated Left Ventricular Ejection Fraction Measurement via Multi-Frame Temporal Aggregation.

Beyond Doppler: Scalable AI Detection of LVOT Obstruction in HCM.

BACKGROUND Accurate assessment of left ventricular outflow tract (LVOT) gradients is critical for hypertrophic cardiomyopathy management, yet Doppler-based measurements are technically demanding and require expertise. The objective of this work was to develop a multi-view deep learning model capable of classifying LVOT obstruction (>20 mm Hg) using routine 2-dimensional echocardiographic windows without reliance on Doppler imaging. METHODS We trained and externally validated a cross-attention-based video-to-video fusion framework that integrated EchoPrime-derived video representations from 3 standard transthoracic echocardiographic views to classify LVOT gradients. RESULTS Training was performed on a derivation cohort (N=1833) from a tertiary care system in the United States, with model performance evaluated on an internally held-out test set (N=275) and a Korean external validation cohort (N=46). Single-view baselines showed limited discrimination (external area under the receiver operating curves, 0.47-0.70). Conversely, the domain-specific foundational model (EchoPrime) achieved superior single-view performance (area under the receiver operating curves, 0.75-0.80 internal; 0.79-0.83 external), highlighting the importance of echo-specific pretraining and temporal modeling. The proposed multi-view fusion further enhanced predictive performance, with the late fusion model reaching an area under the receiver operating curve of 0.84 on the external cohort with significant population-shift. CONCLUSIONS These results suggest LVOT physiology is encoded in routine 2-dimensional imaging and can be leveraged for clinically relevant gradient classification without Doppler input. The proposed artificial intelligence-guided strategy demonstrates substantial cost savings compared with the screen-all approach. By integrating complementary spatial-temporal information across multiple views, our approach generalizes robustly across populations and may enable real-time decision support, extend LVOT assessment to portable or resource-limited settings, and complement Doppler-based evaluation for longitudinal hypertrophic cardiomyopathy management.

Cardiac Time Intervals from Electrocardiogram and Phonocardiogram for Heart Failure Assessment

Dual-flow convolutional neural network for automatic measurement of left ventricular ejection fraction and global longitudinal strain in echocardiography

Echo-DFCNN achieves simultaneous and precise assessment of LVEF and GLS in the study cohorts, demonstrating its potential for robust performance across a wide range of cardiac functions, different image qualities, and machine types.

Echo-EU-Net: Lightweight Deep Learning for Fully Automated Left Ventricular Segmentation and Ejection Fraction Quantification in Transgastric Short-Axis View on Transesophageal Echocardiography.

The feasibility of the proposed Echo-EU-Net-based method in automatically segmenting the left ventricle and measuring EF in TSV TEE has been demonstrated and may shed light on lightweight deep learning-based fully automated left ventricular segmentation and EF quantification in TSV TEE.

Ejection fraction on a budget: mapping the accuracy-compute trade space for video-based ejection fraction estimation

Deep video networks estimate left ventricular ejection fraction (EF) from echocardiograms with expert-level accuracy, but the compute cost of running them is rarely reported. This leaves anyone building a handheld or bedside tool without clear guidance on what to deploy. We measured the accuracy-versus-compute tradeoff for EF estimation on EchoNet-Dynamic by training 22 configurations that varied clip length (8 to 64 frames), frame sampling period (1 to 4), and backbone: R(2+1)D-18, R3D-18, MC3-18, X3D-S, X3D-M, and a 2D ResNet-18 with temporal pooling. All models used one fixed training recipe. Every configuration was evaluated for accuracy using mean absolute error, R-squared, and Bland-Altman agreement; clinical utility using sensitivity and specificity at the clinically relevant EF cutoffs of 40% and 50%, plus error stratified by EF band; and cost using floating-point operations, parameter count, GPU and CPU latency, and peak memory under a single frozen measurement protocol. We stress-tested the main findings with replicate training seeds. Sparse temporal sampling outperformed dense sampling at matched frame budgets. A sampling period of 4 outperformed a period of 1 at every tested frame count while also reducing per-video cost. In the seed-replicated 8-frame comparison, the advantage averaged one full point lower mean absolute error across all nine cross-seed pairings. A standard R3D-18 achieved the best accuracy in the study, with a mean absolute error of 3.99, while requiring 19% less CPU latency than the reference configuration. A 16-frame, period-4 R(2+1)D-18 cut reference cost in half with no statistically confirmed loss in accuracy. Removing temporal modeling entirely substantially reduced accuracy, with a mean absolute error of 5.65, setting a practical floor for how inexpensive this task can be. We release the code, cost-measurement protocol, and per-configuration results.

CURL-AID: Automated Echocardiographic Motion Analysis for Quantitative Assessment of Posterior Systolic Curling.

OBJECTIVE Posterior systolic curling (PSC) is a morphofunctional abnormality of the posterior mitral annulus associated with malignant ventricular arrhythmias and sudden cardiac death. Current diagnosis is qualitative and operator-dependent, limiting reproducibility, objectivity and standardization. This study introduces CURL-AID (Curling Ultrasound-based Recognition and Labeling-Automated Intelligence-driven Diagnosis), a fully automated echocardiographic framework for PSC detection through quantitative analysis of posterior annular and left ventricular wall hypermobility. METHODS Parasternal long-axis transthoracic echocardiograms from 100 patients (47 female; median age 58 years) were retrospectively analyzed. Three independent clinicians classified subjects as PSC (n = 40) or noPSC (n = 60) based on dynamic visual assessment. CURL-AID integrates convolutional neural network segmentation of the posterior wall and annulus, point-wise tissue tracking, extraction of interpretable kinematic and dynamic features and supervised machine learning classification. Feature selection combined bootstrapped Elastic Net and Sequential Backward Selection, identifying nine motion descriptors. Model performance was evaluated using repeated, stratified nested cross-validation. RESULTS Manual annotations showed high inter-operator consistency. Automated segmentation achieved a median Dice of 0.88 and Jaccard index of 0.79 for the posterior wall, with median centroid differences of 2.0 mm (validation) and 1.6 mm (test) for the annulus. Selected features reflected increased tangential and radial displacement and irregular systolic acceleration in PSC. The linear support vector machine achieved the best balance between accuracy and interpretability (area under the curve 0.865 [interquartile range 0.855-0.875], accuracy 0.82, sensitivity 0.84, specificity 0.82, F1-score 0.79). CONCLUSION CURL-AID provides a quantitative and reproducible assessment of PSC and may support automated identification of a phenotype associated with arrhythmic risk.