SITReg: Multi-resolution architecture for symmetric, inverse consistent, and topology preserving image registration using deformation inversion layers

Joel Honkamaa, Pekka Marttinen

Primary Area: applications to neuroscience & cognitive science

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Keywords: Deformable image registration, Unsupervised learning, Symmetric registration, Medical imaging, Deep equilibrium models

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

TL;DR: A deep learning intra-modality image registration arhitecture fulfilling strict symmetry properties

Abstract: Deep learning has emerged as a strong alternative for classical iterative methods for deformable medical image registration, where the goal is to find a mapping between the coordinate systems of two images. Popular classical image registration methods enforce the useful inductive biases of symmetricity, inverse consistency, and topology preservation by construct. However, while many deep learning registration methods encourage these properties via loss functions, none of the methods enforces all of them by construct. Here, we propose a novel registration architecture based on extracting multi-resolution feature representations which is by construct symmetric, inverse consistent, and topology preserving. We also develop an implicit layer for memory efficient inversion of the deformation fields. Our method achieves state-of-the-art registration accuracy on two datasets.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 3299