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

• URL: http://arxiv.org/abs/2605.28697v1
• Date: Wed, 27 May 2026 16:24:05 GMT
• Title: Deep Learning Strain Estimation: Is Physics-Based Simulation the Solution?
• Abstract summary: 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.<n>The proposed method achieves unmatched performance on global and regional strain, notably reaching a GLS variability of 1.42% in an inter-expert setting.
• Score: 2.530975530875256
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Rethinking Medical Landmark Localization with Prototype Learning-based Progressive Offset Correction [9.30702458761404]
  We propose a parameter-economic model, PPOC-LL, which leverages Prototype learning-based Progressive Offset Correction for Landmark localization.<n>Our contribution is three-fold. First, to drive coarse-to-fine landmark optimization, we introduce a multi-scale dynamic perception strategy for patch-level feature pyramid modeling. Second, to effectively handle anatomically similar patterns, we design a similarity-driven prototype learning mechanism that captures informative local semantics for robust offset prediction. Last, to stabilize the model learning and improve the overall performance, we incorporate a novel error-aware reliability regularization via tolerance-based balancing.
  arXiv  Detail & Related papers  (2026-08-10T06:49:16Z)
• Suppressing Prior-Comparison Hallucinations in Radiology Report Generation via Semantically Decoupled Latent Steering [94.37535002230504]
  We develop a training-free, inference-time control framework termed Semantically Decoupled Latent Steering.<n>Our approach constructs a semantic-free intervention vector via large language model (LLM)-driven semantic decomposition.<n>We show that our approach significantly reduces the probability of historical hallucinations.
  arXiv  Detail & Related papers  (2026-02-27T04:49:01Z)
• Latent Neural-ODE for Model-Informed Precision Dosing: Overcoming Structural Assumptions in Pharmacokinetics [3.0991186209192794]
  We introduce a novel data-driven alternative based on Latent Ordinary Differential Equations (Latent ODEs) for tacrolimus AUC prediction.<n>This deep learning approach learns individualized dynamics directly from sparse clinical data.<n>Latent ODE model demonstrated superior robustness, maintaining high accuracy even when underlying biological mechanisms deviated from standard assumptions.
  arXiv  Detail & Related papers  (2026-02-03T07:30:48Z)
• A Semantically Enhanced Generative Foundation Model Improves Pathological Image Synthesis [82.01597026329158]
  We introduce a Correlation-Regulated Alignment Framework for Tissue Synthesis (CRAFTS) for pathology-specific text-to-image synthesis.<n>CRAFTS incorporates a novel alignment mechanism that suppresses semantic drift to ensure biological accuracy.<n>This model generates diverse pathological images spanning 30 cancer types, with quality rigorously validated by objective metrics and pathologist evaluations.
  arXiv  Detail & Related papers  (2025-12-15T10:22:43Z)
• Estimation of Segmental Longitudinal Strain in Transesophageal Echocardiography by Deep Learning [4.266983119889826]
  This study introduces the first automated pipeline, autoStrain, for SLS estimation in transesophageal echocardiography (TEE) using deep learning (DL) methods for motion estimation.<n>We present a comparative analysis of two DL approaches: TeeFlow, based on the RAFT optical flow model for dense frame-to-frame predictions, and TeeTracker, based on the CoTracker point trajectory model for sparse long-sequence predictions.<n>Our evaluation shows that TeeTracker outperforms TeeFlow in accuracy, achieving a mean distance error in motion estimation of 0.65 mm on a synTEE test dataset.
  arXiv  Detail & Related papers  (2025-11-04T03:02:27Z)
• Prediction-Powered Causal Inferences [59.98498488132307]
  We focus on Prediction-Powered Causal Inferences (PPCI)<n>We first show that conditional calibration guarantees valid PPCI at population level.<n>We then introduce a sufficient representation constraint transferring validity across experiments.
  arXiv  Detail & Related papers  (2025-02-10T10:52:17Z)
• Thermodynamics-informed graph neural networks for real-time simulation of digital human twins [2.6811507121199325]
  This paper presents a novel methodology aimed at advancing current lines of research in soft tissue simulation.<n>The proposed approach integrates the geometric bias of graph neural networks with the physical bias derived from the imposition of a metriplectic structure.<n>Based on the adopted methodologies, we propose a model that predicts human liver responses to traction and compression loads in as little as 7.3 milliseconds.
  arXiv  Detail & Related papers  (2024-12-16T18:01:40Z)
• SISMIK for brain MRI: Deep-learning-based motion estimation and model-based motion correction in k-space [0.0]
  We propose a retrospective method for motion estimation and correction for 2D Spin-Echo scans of the brain. The method leverages the power of deep neural networks to estimate motion parameters in k-space. It uses a model-based approach to restore degraded images to avoid ''hallucinations''
  arXiv  Detail & Related papers  (2023-12-20T17:38:56Z)
• Generic Lithography Modeling with Dual-band Optics-Inspired Neural Networks [52.200624127512874]
  We introduce a dual-band optics-inspired neural network design that considers the optical physics underlying lithography. Our approach yields the first published via/metal layer contour simulation at 1nm2/pixel resolution with any tile size. We also achieve 85X simulation speedup over traditional lithography simulator with 1% accuracy loss.
  arXiv  Detail & Related papers  (2022-03-12T08:08:50Z)
• Data-driven generation of plausible tissue geometries for realistic photoacoustic image synthesis [53.65837038435433]
  Photoacoustic tomography (PAT) has the potential to recover morphological and functional tissue properties. We propose a novel approach to PAT data simulation, which we refer to as "learning to simulate" We leverage the concept of Generative Adversarial Networks (GANs) trained on semantically annotated medical imaging data to generate plausible tissue geometries.
  arXiv  Detail & Related papers  (2021-03-29T11:30:18Z)
• Prediction of progressive lens performance from neural network simulations [62.997667081978825]
  The purpose of this study is to present a framework to predict visual acuity (VA) based on a convolutional neural network (CNN) The proposed holistic simulation tool was shown to act as an accurate model for subjective visual performance.
  arXiv  Detail & Related papers  (2021-03-19T14:51:02Z)
• Statistical control for spatio-temporal MEG/EEG source imaging with desparsified multi-task Lasso [102.84915019938413]
  Non-invasive techniques like magnetoencephalography (MEG) or electroencephalography (EEG) offer promise of non-invasive techniques. The problem of source localization, or source imaging, poses however a high-dimensional statistical inference challenge. We propose an ensemble of desparsified multi-task Lasso (ecd-MTLasso) to deal with this problem.
  arXiv  Detail & Related papers  (2020-09-29T21:17:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.