Implicit Neural Representations of Intramyocardial Motion and Strain
This work addresses the problem of scalable and accurate analysis of myocardial strain in large cardiac MRI datasets for medical imaging applications, representing an incremental improvement over existing deep learning methods.
The paper tackled the challenge of automatically quantifying intramyocardial motion and strain from tagging MRI by proposing a method using implicit neural representations (INRs) conditioned on learned latent codes to predict continuous left ventricular displacement without inference-time optimization. It achieved the best tracking accuracy with 2.14 mm RMSE, the lowest combined error in global circumferential (2.86%) and radial (6.42%) strain compared to baselines, and was approximately 380 times faster than the most accurate baseline.
Automatic quantification of intramyocardial motion and strain from tagging MRI remains an important but challenging task. We propose a method using implicit neural representations (INRs), conditioned on learned latent codes, to predict continuous left ventricular (LV) displacement -- without requiring inference-time optimisation. Evaluated on 452 UK Biobank test cases, our method achieved the best tracking accuracy (2.14 mm RMSE) and the lowest combined error in global circumferential (2.86%) and radial (6.42%) strain compared to three deep learning baselines. In addition, our method is $\sim$380$\times$ faster than the most accurate baseline. These results highlight the suitability of INR-based models for accurate and scalable analysis of myocardial strain in large CMR datasets. The code can be found at https://github.com/andrewjackbell/Displacement-INR