Contrastive Learning of Inter-domain Similarity for Unsupervised Multi-modality Deformable Registration

Neel Dey, Jo Schlemper, Seyed Sadegh Mohseni Salehi, Bo Zhou, Michal SofkaProceedings on CD-ROM - International Society for Magnetic Resonance in Medicine. Scientific Meeting and Exhibition/Proceedings of the International Society for Magnetic Resonance in Medicine, Scientific Meeting and Exhibition 2023 · DOI

Abstract

We propose an unsupervised contrastive representation learning framework for deformable and diffeomorphic multi-modality MR image registration. The proposed deep network and data-driven objective function yield improved registration performance in terms of anatomical volume overlap over several previous hand-crafted objectives such as Mutual Information and others. For fair comparison, our experiments train all methods over the entire range of a key registration hyperparameter controlling deformation smoothness using conditional registration hypernetworks. T1w and T2w brain MRI registration improvements are presented across a large cohort of 1041 high-field 3T research-grade acquisitions while maintaining comparable deformation smoothness and invertibility characteristics to previous methods.
BibTeX
@inproceedings{dey2023contrastive,
  author = {Neel Dey and Jo Schlemper and Seyed Sadegh Mohseni Salehi and Bo Zhou and Michal Sofka},
  title = {{Contrastive Learning of Inter-domain Similarity for Unsupervised Multi-modality Deformable Registration}},
  booktitle = {Proceedings on CD-ROM - International Society for Magnetic Resonance in Medicine. Scientific Meeting and Exhibition/Proceedings of the International Society for Magnetic Resonance in Medicine, Scientific Meeting and Exhibition},
  year = {2023},
  doi = {10.58530/2022/3467},
}

Loading related content...

Figure