arXiv:2503.17543v2 Announce Type: replace-cross 
Abstract: Left ventricular ejection fraction (LVEF) is a key indicator of cardiac function and is routinely used to diagnose heart failure and guide treatment decisions. Although deep learning has advanced automated LVEF estimation, many existing approaches are computationally demanding and underutilize the joint structure of spatial and temporal information in echocardiography videos, limiting their suitability for real-time clinical deployment. We propose Echo-E$^3$Net, an efficient endocardial spatio-temporal network specifically designed for LVEF estimation from echocardiography videos. Echo-E$^3$Net comprises two complementary modules: (1) a dual-phase Endocardial Border Detector (E$^2$CBD), which uses phase-specific cross-attention to predict ED/ES endocardial landmarks (EBs) and learn phase-aware landmark embeddings (LEs), and (2) an Endocardial Feature Aggregator (E$^2$FA), which fuses these embeddings with global statistical descriptors (mean, maximum, variance) of deep feature maps to refine EF regression. A multi-component loss function, inspired by Simpson's biplane method, jointly supervises EF, volumes, and landmark geometry, thereby aligning optimization with the clinical definition of LVEF and promoting robust spatio-temporal representation learning. Evaluated on the EchoNet-Dynamic dataset, Echo-E$^3$Net achieves an RMSE of 5.20 and an $R^2$ score of 0.82, while using only 1.54M parameters and 8.05 GFLOPs. The model operates without external pre-training, heavy data augmentation, or test-time ensembling, making it highly suitable for real-time point-of-care ultrasound (POCUS) applications. Code is available at https://github.com/UltrAi-lab/Echo-E3Net.

تم تقديم Echo-E$^3$Net كشبكة زمنية مكانية بطانة فعالة تهدف إلى تقدير كسر الإخراج للبطين الأيسر (LVEF) من مقاطع الفيديو الخاصة بتخطيط القلب بالموجات فوق الصوتية. تتناول هذه الطريقة المبتكرة التحديات الحاسوبية للطرق الحالية من خلال استخدام كاشف حدود بطيني مزدوج المرحلة ومجمع ميزات بطيني لتحسين دقة وكفاءة تقدير LVEF.

Se ha presentado Echo-E$^3$Net como una red espaciotemporal endocárdica eficiente destinada a estimar la fracción de eyección del ventrículo izquierdo (LVEF) a partir de videos de ecocardiografía. Este enfoque innovador aborda los desafíos computacionales de los métodos existentes mediante el uso de un detector de bordes endocárdicos de doble fase y un agregador de características endocárdicas para mejorar la precisión y eficiencia de la estimación de la LVEF.

Echo-E$^3$Net a été présenté comme un réseau spatio-temporel endocardique efficace visant à estimer la fraction d'éjection du ventricule gauche (LVEF) à partir de vidéos d'échocardiographie. Cette approche innovante répond aux défis computationnels des méthodes existantes en utilisant un détecteur de bord endocardique à double phase et un agrégateur de caractéristiques endocardiques pour améliorer la précision et l'efficacité de l'estimation de la LVEF.

Echo-E$^3$Net has been introduced as an efficient endocardial spatio-temporal network aimed at estimating left ventricular ejection fraction (LVEF) from echocardiography videos. This innovative approach addresses the computational challenges of existing methods by utilizing a dual-phase Endocardial Border Detector and an Endocardial Feature Aggregator to enhance the accuracy and efficiency of LVEF estimation.

Echo-E$^3$Net: Efficient Endocardial Spatio-Temporal Network for Ejection Fraction Estimation

Was this article worth reading? Share it

finlight.me

LucidQuery AI

MicroEstimates

Eyeye

Echometer

Attentive AI

Ready to build your own newsroom?