Learning Cardiac Motion Priors for Implicit Neural Representations
2026-07-01 • Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionArtificial Intelligence
AI summaryⓘ
The authors looked at ways to make estimating heart motion from MRI scans faster and more reliable by using learned starting points (priors) for a special type of neural network called implicit neural representations (INRs). They compared four methods for learning these priors to help the network quickly find realistic heart motions. All the methods helped speed up the process compared to starting from scratch, with some methods like meta-learning giving the best results over time. This helps improve tracking of how the heart moves in medical images.
implicit neural representationcardiac motion estimationmagnetic resonance imaginglearned prioroptimization trajectoryauto-decodermeta-learningUK Biobankmotion field
Authors
Andrew Bell, George Webber, Andrew P King, Steffen E Petersen, Muhummad Sohaib Nazir, Alistair Young
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.