Deep Learning Strain Estimation: Is Physics-Based Simulation the Solution?

2026-05-27

AI Summary

This study addresses the limited accuracy of regional myocardial strain estimation in clinical echocardiography, which hinders early detection of subtle cardiac abnormalities. To overcome this challenge, the authors propose a physics-informed simulation framework that incorporates realistic spatiotemporal speckle decorrelation characteristics observed in real ultrasound videos. For the first time, authentic speckle dynamics are integrated into cardiac motion simulation, enabling the generation of high-fidelity synthetic echocardiographic sequences through joint image-motion iterative optimization. Leveraging this approach, they construct and publicly release a dataset comprising 1,478 realistic ultrasound videos with reference motion annotations to train deep optical flow networks. Experimental results demonstrate state-of-the-art performance in both global and regional strain estimation, with inter-observer variability in global longitudinal strain (GLS) reduced to 1.42%, surpassing the clinical standard method (1.78%).

Abstract

Speckle tracking echocardiography (STE) is the clinical standard for myocardial strain estimation. Despite good performance on global strain (GLS), its accuracy for regional strain remains limited, even though this biomarker is highly relevant for early diagnosis and the characterization of subtle abnormalities. from clinical data. Deep learning is a promising alternative, but its development is constrained by the lack of reliable motion references. Existing solutions rely either on STE-derived labels or on simulations generated by physics-based models, but these synthetic sequences still have limited realism compared with clinical data.In this paper, we propose a novel simulation strategy that incorporates speckle decorrelation measures from real videos and uses an iterative refinement process to improve the motion realism in the simulations. We created an open-source photorealistic dataset of 1,478 videos with reference motion, which was used to train an echocardiographic motion estimation algorithm. The proposed method achieves unmatched performance on global and regional strain, notably reaching a GLS variability of 1.42% in an inter-expert setting compared to 1.78% for the clinical reference.

Problem

• myocardial strain estimation
• speckle tracking echocardiography
• regional strain
• motion reference
• deep learning

Innovation

• speckle decorrelation
• physics-based simulation
• deep learning
• myocardial strain estimation
• photorealistic dataset