Saved in:
Bibliographic Details
Main Authors: Bell, Andrew, Choi, Yan Kit, Petersen, Steffen E, King, Andrew, Nazir, Muhummad Sohaib, Young, Alistair A
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.09004
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909805667418112
author Bell, Andrew
Choi, Yan Kit
Petersen, Steffen E
King, Andrew
Nazir, Muhummad Sohaib
Young, Alistair A
author_facet Bell, Andrew
Choi, Yan Kit
Petersen, Steffen E
King, Andrew
Nazir, Muhummad Sohaib
Young, Alistair A
contents 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
format Preprint
id arxiv_https___arxiv_org_abs_2509_09004
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Implicit Neural Representations of Intramyocardial Motion and Strain
Bell, Andrew
Choi, Yan Kit
Petersen, Steffen E
King, Andrew
Nazir, Muhummad Sohaib
Young, Alistair A
Computer Vision and Pattern Recognition
Artificial Intelligence
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
title Implicit Neural Representations of Intramyocardial Motion and Strain
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2509.09004