MRGen: Segmentation Data Engine for Underrepresented MRI Modalities (ICCV 2025)

This repository contains the pre-trained checkpoints of MRGen: https://arxiv.org/abs/2412.04106/.

Some Information

Project Page · Paper · Dataset · Checkpoints

Checkpoints - Model Zoo

Please refer to MRGen to download our pre-trained checkpoints.

Generative Model Checkpoints

Source Modality	Target Modality	Link
CHAOS-MRI_T1	CHAOS-MRI_T2-SPIR	CHAOS-MRI_T1_to_CHAOS-MRI_T2
CHAOS-MRI_T2-SPIR	CHAOS-MRI_T1	CHAOS-MRI_T2_to_CHAOS-MRI_T1
MSD-Prostate_T2	MSD-Prostate_ADC	MSDProstate_T2_to_MSDProstate_ADC
MSD-Prostate_ADC	MSD-Prostate_T2	MSDProstate_ADC_to_MSDProstate_T2
PanSeg_T1	PanSeg_T2	PanSeg_T1_to_PanSeg_T2
PanSeg_T2	PanSeg_T1	PanSeg_T2_to_PanSeg_T1
LiQA_T1	CHAOS-MRI_T2-SPIR	LiQA_T1_to_CHAOS-MRI_T2
CHAOS-MRI_T2-SPIR	LiQA_T1	CHAOS-MRI_T2_to_LiQA_T1
MSD-Prostate_ADC	PROMISE12_T2	MSDProstate_ADC_to_PROMISE12_T2
PROMISE12_T2	MSD-Prostate_ADC	PROMISE12_T2_to_MSDProstate_ADC

Segmentation Model Checkpoints

Please check them out here.

Citation

If you use this code and data for your research or project, please cite:

@inproceedings{wu2025mrgen,
  author    = {Wu, Haoning and Zhao, Ziheng and Zhang, Ya and Wang, Yanfeng and Xie, Weidi},
  title     = {MRGen: Segmentation Data Engine for Underrepresented MRI Modalities},
  booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}
  year      = {2025},
}

Contact

If you have any questions, please feel free to contact [email protected] or [email protected].