# Boosting Medical Image Synthesis via Registration-guided Consistency and Disentanglement Learning

arXiv: https://arxiv.org/abs/2407.07660 · HTML: https://mlsanity.com/paper/2407.07660/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 26 references that are in the map.
- First posted on arXiv 10 Jul 2024.

## Builds on (most cited first, 13 of 13)

- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Multimodal Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/1804.04732/) (2018)
- [VoxelMorph: A Learning Framework for Deformable Medical Image Registration](https://mlsanity.com/paper/1809.05231/) (2018)
- [Unsupervised Image-to-Image Translation Networks](https://mlsanity.com/paper/1703.00848/) (2017)
- [ResViT: Residual vision transformers for multi-modal medical image synthesis](https://mlsanity.com/paper/2106.16031/) (2021)
- [MedGAN: Medical Image Translation using GANs](https://mlsanity.com/paper/1806.06397/) (2018)
- [Breaking the Dilemma of Medical Image-to-image Translation](https://mlsanity.com/paper/2110.06465/) (2021)
- [Unsupervised Multi-Modal Image Registration via Geometry Preserving Image-to-Image Translation](https://mlsanity.com/paper/2003.08073/) (2020)
- [SynthRAD2023 Grand Challenge dataset: generating synthetic CT for radiotherapy](https://mlsanity.com/paper/2303.16320/) (2023)
- [Unsupervised Deformable Registration for Multi-Modal Images via Disentangled Representations](https://mlsanity.com/paper/1903.09331/) (2019)
- [Structure-Preserving Synthesis: MaskGAN for Unpaired MR-CT Translation](https://mlsanity.com/paper/2307.16143/) (2023)
- [Deformation equivariant cross-modality image synthesis with paired non-aligned training data](https://mlsanity.com/paper/2208.12491/) (2022)
- [AngioMoCo: Learning-based Motion Correction in Cerebral Digital Subtraction Angiography](https://mlsanity.com/paper/2310.05445/) (2023)

## Built on by (most cited first, 2 of 2)

- [SynerMedGen: Synergizing Medical Multimodal Understanding with Generation via Task Alignment](https://mlsanity.com/paper/2605.08724/) (2026)
- [When Misalignment Becomes Supervision: Structured Label Noise in Supervised Synthetic CT Generation](https://mlsanity.com/paper/2609.29387/) (2026)

## Abstract (arXiv)

Medical image synthesis remains challenging due to misalignment noise during training. Existing methods have attempted to address this challenge by incorporating a registration-guided module. However, these methods tend to overlook the task-specific constraints on the synthetic and registration modules, which may cause the synthetic module to still generate spatially aligned images with misaligned target images during training, regardless of the registration module's function. Therefore, this paper proposes registration-guided consistency and incorporates disentanglement learning for medical image synthesis. The proposed registration-guided consistency architecture fosters task-specificity within the synthetic and registration modules by applying identical deformation fields before and after synthesis, while enforcing output consistency through an alignment loss. Moreover, the synthetic module is designed to possess the capability of disentangling anatomical structures and specific styles across various modalities. An anatomy consistency loss is introduced to further compel the synthetic module to preserve geometrical integrity within latent spaces. Experiments conducted on both an in-house abdominal CECT-CT dataset and a publicly available pelvic MR-CT dataset have demonstrated the superiority of the proposed method.