Echo-E$^3$Net：高效的心内膜时空网络用于射血分数估计
Echo-E$^3$Net: Efficient Endocardial Spatio-Temporal Network for Ejection Fraction Estimation
AI总结：
本文提出Echo-E$^3$Net，一种结合心脏解剖结构的心内膜时空网络，用于从超声视频中高效估计左室射血分数，通过轻量级特征融合和相位感知地标建模提升效率与鲁棒性。
摘要：
目标：开发一种稳健且计算高效的深度学习模型，用于从超声视频中自动估计左室射血分数（LVEF），适用于实时床旁超声（POCUS）部署。方法：提出Echo-E$^3$Net，一种心内膜时空网络，明确将心脏解剖结构纳入LVEF预测。模型包含一个双相心内膜边界检测器（E$^2$CBD），利用相位特定的交叉注意力来定位终舒张期和终收缩期心内膜地标，并学习相位感知地标嵌入；以及一个心内膜特征聚合器（E$^2$FA），将这些嵌入与深度特征图的全局统计描述融合以优化EF回归。训练由受Simpson双平面方法启发的多组件损失指导，联合监督EF和地标几何。在EchoNet-Dynamic数据集上评估Echo-E$^3$Net，使用RMSE和R$^2$，并报告参数数量和GFLOPs以表征效率。结果：在EchoNet-Dynamic上，Echo-E$^3$Net达到RMSE 5.20和R$^2$分数0.82，仅使用1.55M参数和8.05 GFLOPs。该模型无需外部预训练、重数据增强或测试时集成，支持实用实时部署。结论：通过结合相位感知心内膜地标建模与轻量级时空特征融合，Echo-E$^3$Net提升了自动LVEF估计的效率和鲁棒性，并适用于POCUS场景中的可扩展临床应用。代码可在https://github.com/moeinheidari7829/Echo-E3Net获取。
英文摘要：
Left ventricular ejection fraction (LVEF) is a primary marker of cardiac function. However, routine estimation from endocardial measurements requires manual delineation at end-diastole (ED) and end-systole (ES), a process that is time-consuming and subject to inter-observer variability. Reliable automation is especially valuable for point-of-care ultrasound (POCUS), where computational resources are limited and acquisition quality varies. We propose Echo-E$^3$Net, an anatomy-guided spatio-temporal network that explicitly embeds cardiac anatomy into LVEF prediction. A dual-phase Endocardial Border Detector (E$^2$CBD) uses phase-specific cross-attention to localize ED/ES endocardial landmarks and produce phase-aware landmark embeddings, while an Endocardial Feature Aggregator (E$^2$FA) fuses these embeddings with global statistical descriptors of deep feature maps to refine EF regression. Training is guided by a lightweight geometric loss that uses ED and ES endocardial landmarks to regularize EF prediction. On EchoNet-Dynamic and a PSAX subset of EchoNet-Pediatric, Echo-E$^3$Net attains competitive performance using only 1.55M parameters and 8.05 GFLOPs, an order-of-magnitude compute reduction versus recent baselines, supporting real-time deployment. Our code is publicly available at https://github.com/moeinheidari7829/Echo-E3Net.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
