# Mono-Modalizing Extremely Heterogeneous Multi-Modal Medical Image Registration

arXiv: https://arxiv.org/abs/2506.15596 · HTML: https://mlsanity.com/paper/2506.15596/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 30 references that are in the map.
- First posted on arXiv 18 Jun 2025.

## Builds on (most cited first, 9 of 9)

- [SynthStrip: Skull-Stripping for Any Brain Image](https://mlsanity.com/paper/2203.09974/) (2022)
- [A survey on deep learning in medical image registration: new technologies, uncertainty, evaluation metrics, and beyond](https://mlsanity.com/paper/2307.15615/) (2023)
- [textttGradICON: Approximate Diffeomorphisms via Gradient Inverse Consistency](https://mlsanity.com/paper/2206.05897/) (2022)
- [Correlation-aware Coarse-to-fine MLPs for Deformable Medical Image Registration](https://mlsanity.com/paper/2406.00123/) (2024)
- [ICON: Learning Regular Maps Through Inverse Consistency](https://mlsanity.com/paper/2105.04459/) (2021)
- [Voxelmorph++ Going beyond the cranial vault with keypoint supervision and multi-channel instance optimisation](https://mlsanity.com/paper/2203.00046/) (2022)
- [Modality-Agnostic Structural Image Representation Learning for Deformable Multi-Modality Medical Image Registration](https://mlsanity.com/paper/2402.18933/) (2024)
- [multiGradICON: A Foundation Model for Multimodal Medical Image Registration](https://mlsanity.com/paper/2408.00221/) (2024)
- [Constrained H1-regularization schemes for diffeomorphic image registration](https://mlsanity.com/paper/1503.00757/) (2015)

## Built on by (most cited first, 1 of 1)

- [Benchmarking Intra-Patient 3D Deformable Multimodal Image Registration](https://mlsanity.com/paper/2609.15669/) (2026)

## Abstract (arXiv)

In clinical practice, imaging modalities with functional characteristics, such as positron emission tomography (PET) and fractional anisotropy (FA), are often aligned with a structural reference (e.g., MRI, CT) for accurate interpretation or group analysis, necessitating multi-modal deformable image registration (DIR). However, due to the extreme heterogeneity of these modalities compared to standard structural scans, conventional unsupervised DIR methods struggle to learn reliable spatial mappings and often distort images. We find that the similarity metrics guiding these models fail to capture alignment between highly disparate modalities. To address this, we propose M2M-Reg (Multi-to-Mono Registration), a novel framework that trains multi-modal DIR models using only mono-modal similarity while preserving the established architectural paradigm for seamless integration into existing models. We also introduce GradCyCon, a regularizer that leverages M2M-Reg's cyclic training scheme to promote diffeomorphism. Furthermore, our framework naturally extends to a semi-supervised setting, integrating pre-aligned and unaligned pairs only, without requiring ground-truth transformations or segmentation masks. Experiments on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset demonstrate that M2M-Reg achieves up to 2x higher DSC than prior methods for PET-MRI and FA-MRI registration, highlighting its effectiveness in handling highly heterogeneous multi-modal DIR. Our code is available at https://github.com/MICV-yonsei/M2M-Reg.