Set-Based Groupwise Registration for Variable-Length, Variable-Contrast Cardiac MRI

Conference Paper (2027)
Author(s)

Yi Zhang (TU Delft - Applied Sciences)

Yidong Zhao (TU Delft - Applied Sciences)

Tijmen Toxopeus (Student TU Delft)

Maša Božić-Iven (TU Delft - Applied Sciences)

Sebastian Weingärtner (TU Delft - Applied Sciences, TU Delft - ImPhys/Computational Imaging)

Qian Tao (TU Delft - Applied Sciences)

Research Group
ImPhys/Tao group
DOI related publication
https://doi.org/10.1007/978-3-032-38186-6_28 Final published version
More Info
expand_more
Publication Year
2027
Language
English
Research Group
ImPhys/Tao group
Pages (from-to)
290-300
Publisher
Springer Nature
ISBN (print)
9783032381859
Event
29th International Conference on Medical Image Computing and Computer Assisted Intervention, MICCAI 2026 (2026-09-27 - 2026-10-01), Strasbourg, France
Page Views
2
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

Quantitative cardiac magnetic resonance imaging (MRI) enables non-invasive myocardial tissue characterization but relies on robust motion correction within these variable-length, variable-contrast image sequences. Groupwise registration, which simultaneously aligns all images, has shown greater robustness than pairwise registration for motion correction. However, current deep-learning-based groupwise registration methods cannot generalize across MRI sequences: the architecture typically encodes input data as a fixed-length channel stack, which rigidly couples network design to protocol-specific sequence length, input ordering, and contrast dynamics. At inference time, any change in imaging protocols will render the network unusable. In this work, we introduce Any2Reg, a new set-based groupwise registration framework that takes a quantitative MRI sequence as an unordered set. This set formulation fundamentally decouples network design from sequence length and input ordering. By utilizing a shared encoder and correlation-guided feature aggregation, Any2Reg constructs a permutation-invariant canonical reference for registration, and learns a permutation-equivariant mapping from images to deformation fields. Additionally, we extract contrast-insensitive image features from an existing foundation model to handle extreme contrast variations. Trained exclusively on a single public T1 mapping dataset (STONE, sequence length L=11), Any2Reg generalizes to two unseen quantitative MRI datasets (MOLLI, ASL) with variable lengths (L∈[11,60]) and different contrast dynamics. It achieves strong cross-protocol generalization in a zero-shot manner, and consistently improves downstream quantitative mapping quality. Notably, while designed for quantitative MRI sequences, our framework is directly applicable to Cine MRI sequences for inter-cardiac-phase registration.

Files

978-3-032-38186-6_28.pdf
(pdf | 2.2 Mb)
– Personal use only – Dutch Copyright Act (Article 25fa)
warning

File under embargo until 25-03-2027