OSA：基于正交化状态更新与解剖先验感知特征增强的超声心动图视频分割
OSA: Echocardiography Video Segmentation via Orthogonalized State Update and Anatomical Prior-aware Feature Enhancement
将循环状态更新约束在 Stiefel 流形上以避免秩坍缩，为视频分割中的时序建模提供稳定记忆机制；解剖先验感知的特征增强模块可分离散斑噪声，可迁移到其他医学视频分割任务。
原文依据 constrains the state evolution on the Stiefel manifold
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论从超声心动图视频中准确且时序一致地分割左心室对于估计射血分数和评估心脏功能至关重要。然而，由于严重的散斑噪声和快速的非刚性形变，时空动态建模仍然困难。现有的线性循环模型为时序跟踪提供了高效的上下文关联回忆，但依赖于无约束的状态更新，这会导致状态矩阵中渐进奇异值衰减，即秩坍缩现象，使得解剖细节被噪声淹没。为解决此问题，我们提出 OSA 框架，将状态演化约束在 Stiefel 流形上。我们引入正交化状态更新（OSU）机制，将记忆演化建模为 Stiefel 流形上的欧几里得投影梯度下降，以防止秩坍缩并保持稳定的时序转换。此外，解剖先验感知特征增强模块通过物理驱动过程显式地将解剖结构与散斑噪声分离，为时序跟踪器提供抗噪声的结构线索。在 CAMUS 和 EchoNet-Dynamic 数据集上的综合实验表明，OSA 在保持临床部署所需的实时推理效率的同时，实现了最优的分割精度和时序稳定性。代码见 https://github.com/wangrui2025/OSA。
英文原文摘要 1463 字符
Accurate and temporally consistent segmentation of the left ventricle from echocardiography videos is essential for estimating the ejection fraction and assessing cardiac function. However, modeling spatiotemporal dynamics remains difficult due to severe speckle noise and rapid non-rigid deformations. Existing linear recurrent models offer efficient in-context associative recall for temporal tracking, but rely on unconstrained state updates, which cause progressive singular value decay in the state matrix, a phenomenon known as rank collapse, resulting in anatomical details being overwhelmed by noise. To address this, we propose OSA, a framework that constrains the state evolution on the Stiefel manifold. We introduce the Orthogonalized State Update (OSU) mechanism, which formulates the memory evolution as Euclidean projected gradient descent on the Stiefel manifold to prevent rank collapse and maintain stable temporal transitions. Furthermore, an Anatomical Prior-aware Feature Enhancement module explicitly separates anatomical structures from speckle noise through a physics-driven process, providing the temporal tracker with noise-resilient structural cues. Comprehensive experiments on the CAMUS and EchoNet-Dynamic datasets show that OSA achieves state-of-the-art segmentation accuracy and temporal stability, while maintaining real-time inference efficiency for clinical deployment. Codes are available at https://github.com/wangrui2025/OSA.