EchoDiST: Self-distillation-based joint learning for diffusion-conditioned echocardiographic myocardial motion estimation

📄 arXiv: 2610.11431v1 📥 PDF

作者: Feiyue Qi, Xingyue Wei, Jianwen Luo

分类: cs.CV

发布日期: 2026-10-08

备注: 19 pages, 14 figures


💡 一句话要点

提出EchoDiST以解决超声心动图心肌运动估计问题

🎯 匹配领域: 支柱二:RL算法与架构 (RL & Architecture) 支柱七:动作重定向 (Motion Retargeting) 支柱八:物理动画 (Physics-based Animation)

关键词: 超声心动图 心肌运动估计 自蒸馏 无监督学习 扩散条件网络 心脏功能评估 解剖分割

📋 核心要点

  1. 现有方法在心动图运动估计中面临图像伪影和真实位移场稀缺等挑战,导致定量评估困难。
  2. EchoDiST框架结合自蒸馏联合学习与扩散条件运动估计,能够在无监督条件下进行心肌运动估计。
  3. 在三个超声心动图数据集上,EchoDiST在解剖对齐和心肌应变评估上均显著优于七种代表性学习方法。

📝 摘要(中文)

心动图中的运动估计对于定量评估心脏功能和心肌力学至关重要,但由于图像伪影、信息有限、散斑去相关及真实位移场稀缺等问题,仍然面临挑战。本文提出EchoDiST框架,通过自蒸馏联合学习与扩散条件运动估计网络相结合,实现无监督的心肌运动估计。该方法在训练中使用随机扰动的扩散条件,而推理时仅需一次确定性前向传播,无需迭代反向扩散采样。实验结果表明,EchoDiST在多个数据集上显著提高了解剖对齐、心肌应变评估及运动导向的功能和心脏相位评估,提供了一种在有限解剖监督下可靠的心肌运动估计方法。

🔬 方法详解

问题定义:本论文旨在解决超声心动图中的心肌运动估计问题,现有方法受限于图像伪影和缺乏真实位移场的标注,导致运动估计的准确性不足。

核心思路:提出的EchoDiST框架通过自蒸馏联合学习,结合扩散条件运动估计网络,能够在缺乏充分标注的情况下进行有效的心肌运动估计。

技术框架:EchoDiST的整体架构包括自蒸馏模块和扩散条件运动估计网络。自蒸馏模块优化解剖分割与运动估计,而扩散条件网络则在训练中引入随机扰动,推理时仅需一次前向传播。

关键创新:EchoDiST的主要创新在于自蒸馏策略的引入,使得在有限的解剖标注下,能够同时优化解剖分割和运动估计,显著提升了估计的准确性。

关键设计:在网络结构上,采用了适应性损失函数以平衡解剖分割与运动估计的优化目标,同时在扩散条件网络中设计了随机扰动机制,以增强模型的鲁棒性。

🖼️ 关键图片

fig_0
fig_1
fig_2

📊 实验亮点

在实验中,EchoDiST在解剖对齐、心肌应变评估及运动导向的功能评估上均显著优于七种基线方法,统计结果显示在多个任务和数据集上均有显著提升,证明了其有效性和可靠性。

🎯 应用场景

该研究具有广泛的应用潜力,尤其是在心脏病学领域。通过提高心肌运动估计的准确性,EchoDiST能够为临床医生提供更可靠的心脏功能评估工具,促进个性化医疗的发展。此外,该方法的无监督特性也为数据稀缺的场景提供了新的解决方案。

📄 摘要(原文)

Motion estimation in echocardiography is essential for quantitative assessment of cardiac function and myocardial mechanics, but remains challenging due to image artifacts, limited image information, speckle decorrelation, and the scarcity of ground-truth displacement fields. Anatomy-guided approaches can provide structural information, yet often rely on expert-labeled myocardial segmentations. We propose EchoDiST, a framework for unsupervised echocardiographic myocardial motion estimation that integrates self-distillation-based joint learning with a diffusion-conditioned motion estimation network. Here, unsupervised motion estimation refers to learning without ground-truth displacement fields. The self-distillation strategy jointly optimizes anatomical segmentation and myocardial motion estimation under limited anatomical annotations. Diffusion-based conditioning is used during training with stochastic perturbations, while inference requires only a single deterministic forward pass without iterative reverse-diffusion sampling. EchoDiST was evaluated on three echocardiographic datasets, including two external test datasets under cross-view and cross-dataset settings. Compared with seven representative learning-based methods, EchoDiST consistently improved anatomical alignment, myocardial strain assessment, and motion-derived functional and cardiac-phase assessment. These gains were statistically significant across the evaluated tasks and datasets. Overall, EchoDiST provides an effective approach for reliable myocardial motion estimation under limited anatomical supervision and supports downstream quantitative assessment of cardiac function.