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

Joel Honkamaa1Orcid, Pekka Marttinen1Orcid
1: Department of Computer Science, Aalto University, Finland
Publication date: 2024/11/27
https://doi.org/10.59275/j.melba.2024-276b
PDF · Code

Abstract

Deep learning has emerged as a strong alternative for classical iterative methods for de- formable 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 construction. However, while many deep learning registration methods encourage these properties via loss functions, no earlier methods enforce all of them by construction. Here, we propose a novel registration architecture based on extracting multi-resolution feature representations which is by construction symmetric, inverse consistent, and topology pre- serving. We also develop an implicit layer for memory efficient inversion of the deformation fields. Our method achieves state-of-the-art registration accuracy on three datasets. The code is available at https://github.com/honkamj/SITReg

Keywords

Machine Learning · Image Registration

Bibtex @article{melba:2024:026:honkamaa, title = "SITReg: Multi-resolution architecture for symmetric, inverse consistent, and topology preserving image registration", author = "Honkamaa, Joel and Marttinen, Pekka", journal = "Machine Learning for Biomedical Imaging", volume = "2", issue = "November 2024 issue", year = "2024", pages = "2148--2194", issn = "2766-905X", doi = "https://doi.org/10.59275/j.melba.2024-276b", url = "https://melba-journal.org/2024:026" }
RISTY - JOUR AU - Honkamaa, Joel AU - Marttinen, Pekka PY - 2024 TI - SITReg: Multi-resolution architecture for symmetric, inverse consistent, and topology preserving image registration T2 - Machine Learning for Biomedical Imaging VL - 2 IS - November 2024 issue SP - 2148 EP - 2194 SN - 2766-905X DO - https://doi.org/10.59275/j.melba.2024-276b UR - https://melba-journal.org/2024:026 ER -

2024:026 cover