Learning Cardiac Motion Priors for Implicit Neural Representations

2026-07-01

AI Summary

Implicit neural representations for cardiac motion estimation are often computationally expensive and highly sensitive to initialization due to the absence of effective prior guidance. To address this, this work proposes integrating population-level motion priors to accelerate optimization and enhance the accuracy and stability of motion estimation. The study systematically evaluates four prior-learning strategies: population joint optimization, weight-averaged consensus, self-decoder, and meta-learning. Experiments on short-axis tagged cardiac MRI data from the UK Biobank demonstrate that all learned priors significantly outperform random initialization. Among them, the consensus prior exhibits robust performance, the self-decoder excels at recovering large deformations, and meta-learning achieves the most accurate adaptation trajectory within only 50 optimization iterations.

Abstract

Implicit neural representations (INRs) are well suited to cardiac motion estimation, providing continuous, compact representations of motion fields. However, fitting an INR to each image sequence is time-consuming and sensitive to the optimisation trajectory. Learned priors can help guide optimisation towards plausible motion fields and enable faster adaptation, but learning priors for cardiac motion INRs remains under-explored. In this work, we compare four strategies for learning cardiac motion priors, including a population prior learned by joint optimisation, a consensus prior obtained by weight averaging, auto-decoders, and meta-learning. Using short-axis tagged cardiac magnetic resonance images from the UK Biobank, we evaluate their impact on tracking accuracy, motion behaviour, and adaptation trajectory. All learned priors substantially improved early adaptation performance compared with random initialisation. While the simple consensus prior was effective, auto-decoders recovered large deformations faster during early adaptation. Meta-learning achieved strong early performance and maintained the best adaptation trajectory over 50 iterations.

Problem

• implicit neural representations
• cardiac motion estimation
• motion priors
• optimization trajectory
• image sequence fitting

Innovation

• implicit neural representations
• cardiac motion estimation
• learned priors
• meta-learning
• auto-decoders