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

Key points

• 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.1
• The self-distillation strategy jointly optimizes anatomical segmentation and myocardial motion estimation under limited anatomical annotations.1
• Compared with seven representative learning-based methods, EchoDiST consistently improved anatomical alignment, myocardial strain assessment, and motion-derived functional and cardiac-phase assessment.1
• Overall, EchoDiST provides an effective approach for reliable myocardial motion estimation under limited anatomical supervision and supports downstream quantitative assessment of cardiac function.1

Sources (1)

• [1]EchoDiST: Self-distillation-based joint learning for diffusion-conditioned echocardiographic myocardial motion estimation
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 8, 07:55 AM

  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.

  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.

Extractive summary: sentences quoted from the sources.