# Myocardial Strain Drift Correction in Deep Learning Based Ultrasound Tracking

arXiv: https://arxiv.org/abs/2609.09577 · HTML: https://mlsanity.com/paper/2609.09577/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 17 references that are in the map.
- First posted on arXiv 9 Sep 2026.

## Builds on (most cited first, 11 of 11)

- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [A Point Set Generation Network for 3D Object Reconstruction from a Single Image](https://mlsanity.com/paper/1612.00603/) (2016)
- [CoTracker: It is Better to Track Together](https://mlsanity.com/paper/2307.07635/) (2023)
- [Deep Learning for Segmentation using an Open Large-Scale Dataset in 2D Echocardiography](https://mlsanity.com/paper/1908.06948/) (2019)
- [CoTracker3: Simpler and Better Point Tracking by Pseudo-Labelling Real Videos](https://mlsanity.com/paper/2410.11831/) (2024)
- [EchoTracker: Advancing Myocardial Point Tracking in Echocardiography](https://mlsanity.com/paper/2405.08587/) (2024)
- [Extraction of volumetric indices from echocardiography: which deep learning solution for clinical use?](https://mlsanity.com/paper/2305.01997/) (2023)
- [Low Complexity Point Tracking of the Myocardium in 2D Echocardiography](https://mlsanity.com/paper/2503.10431/) (2025)
- [Estimation of Segmental Longitudinal Strain in Transesophageal Echocardiography by Deep Learning](https://mlsanity.com/paper/2511.02210/) (2025)
- [Generation of realistic cardiac ultrasound sequences with ground truth motion and speckle decorrelation](https://mlsanity.com/paper/2509.05261/) (2025)
- [Deep Learning Strain Estimation: Is Physics-Based Simulation the Solution?](https://mlsanity.com/paper/2605.28697/) (2026)

## Abstract (arXiv)

Myocardial strain from echocardiography is a key biomarker for cardiac function. Recent deep learning methods show strong performance for myocardial motion tracking but often lack physiological constraints, leading to temporal drift across the cardiac cycle. Consequently, tracked points may not return to their relative initial positions at the end of each cardiac cycle, producing inaccurate strain estimates and even divergence in some cases. We propose a deep learning framework that compensates for drift during myocardial tracking. We extend a state-of-the-art echocardiographic tracking method (TAS-Net) with persistent memory tokens that share information across sliding windows over full cardiac cycles. A teacher-student fine-tuning strategy on real echocardiographic data then enforces physiologically consistent cyclic motion while preserving tracking accuracy. Experiments show reduced global and regional strain drift, improved agreement with clinical references, and better test-retest reproducibility, supporting more reliable myocardial strain estimation in clinical practice.