基于锚框语义感知与连续伪标签重铸的半监督超声心动图视频分割
Semi-supervised Echocardiography Video Segmentation via Anchor Semantic Awareness and Continuous Pseudo-label Reforging
针对医学视频中噪声和动态运动导致的边界模糊问题，提出可学习的锚框语义感知模块和连续伪标签重铸策略，可迁移到其他半监督视频分割任务中提升时序一致性和伪标签质量。
原文依据 EchoForge introduces an Anchor Semantic Awareness (ASA) module that refines ambiguous regions using learnable anchors and propagates structural prototypes across frames
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论自动且准确的超声心动图视频分割对于高效、可重复地测量心血管疾病诊断中的关键临床功能指标至关重要。然而，由于（1）超声心动图视频中固有的斑点噪声，（2）心脏结构的复杂动态运动，以及（3）标注数据的稀缺，在整个心动周期内获得高质量的分割结果是一项极具挑战性的任务。为了全面应对这些挑战，我们提出了一种新颖的半监督模型EchoForge，它能够在非常有限的标注下实现准确且实时的超声心动图视频分割。EchoForge引入了一个锚框语义感知（ASA）模块，该模块利用可学习的锚框细化模糊区域，并在帧间传播结构原型以增强边界描绘和时序一致性。在ASA的基础上，一个连续伪标签重铸（CPR）模块通过通道注意力逐步整合和细化伪标签，提供稳健的监督。在CAMUS和EchoNet-Dynamic基准上的大量实验表明，EchoForge在保持实时效率的同时，在准确性上优于最优方法。代码可在https://github.com/YunPeng-Fang/EchoForge获取。
英文原文摘要 1345 字符
Automatic and accurate echocardiography video segmentation is essential for efficient and repeatable measurements of key clinical functional indicators for the diagnosis of cardiovascular diseases. However, it is an extremely challenging task to obtain high-quality segmentation results throughout the cardiac cycle owing to (1) the inherent speckle noise in echocardiography videos, (2) the complex dynamic motions of cardiac structures, and (3) the scarcity of annotated data. To comprehensively address these challenges, we propose a novel semi-supervised model, EchoForge, which can achieve accurate and real-time echocardiography video segmentation with very limited annotations. EchoForge introduces an Anchor Semantic Awareness (ASA) module that refines ambiguous regions using learnable anchors and propagates structural prototypes across frames to enhance boundary delineation and temporal consistency. Building upon ASA, a Continuous Pseudo-label Reforging (CPR) module progressively integrates and refines pseudo-labels via channel-wise attention, providing robust supervision. Extensive experiments on the CAMUS and EchoNet-Dynamic benchmarks demonstrate that EchoForge outperforms state-of-the-art (SOTA) methods in accuracy while maintaining real-time efficiency. The code is available at https://github.com/YunPeng-Fang/EchoForge.