EchoTracker: Advancing Myocardial Point Tracking in Echocardiography
About
Tissue tracking in echocardiography is challenging due to the complex cardiac motion and the inherent nature of ultrasound acquisitions. Although optical flow methods are considered state-of-the-art (SOTA), they struggle with long-range tracking, noise occlusions, and drift throughout the cardiac cycle. Recently, novel learning-based point tracking techniques have been introduced to tackle some of these issues. In this paper, we build upon these techniques and introduce EchoTracker, a two-fold coarse-to-fine model that facilitates the tracking of queried points on a tissue surface across ultrasound image sequences. The architecture contains a preliminary coarse initialization of the trajectories, followed by reinforcement iterations based on fine-grained appearance changes. It is efficient, light, and can run on mid-range GPUs. Experiments demonstrate that the model outperforms SOTA methods, with an average position accuracy of 67% and a median trajectory error of 2.86 pixels. Furthermore, we show a relative improvement of 25% when using our model to calculate the global longitudinal strain (GLS) in a clinical test-retest dataset compared to other methods. This implies that learning-based point tracking can potentially improve performance and yield a higher diagnostic and prognostic value for clinical measurements than current techniques. Our source code is available at: https://github.com/riponazad/echotracker/.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Myocardial Motion Estimation | SSHF 240 videos | MTE (A2C) [mm]1.21 | 7 | |
| Myocardial Motion Estimation | HUNT-A 588 videos | MTE (A2C) [mm]1.26 | 7 | |
| Myocardial Motion Estimation | HUNT 180 videos | MTE (A2C) [mm]1.45 | 7 | |
| Point Tracking | SynUS 19 (test) | AJ0.871 | 6 | |
| Point Tracking | In-distribution | Avg Displacement Error63.27 | 6 | |
| Point Tracking | OOD RV | Avg Displacement Error (δ_avg)46.63 | 6 | |
| Global Longitudinal Strain calculation | Clinical Dataset comparison Private (Reference) | Bias-0.0013 | 6 | |
| Point Tracking | CAMUS | Mean Tracking Error (MTE)1.58 | 6 | |
| Peak GLS estimation | SSHF+HUNT (Test-retest) | MAE1.98 | 5 | |
| Peak GLS estimation | HUNT-A 264 videos (Agreement) | MAE1.14 | 5 |