# Generative Adversarial Networks for MR-CT Deformable Image Registration

arXiv: https://arxiv.org/abs/1807.07349 · HTML: https://mlsanity.com/paper/1807.07349/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Jul 2018.

## Built on by (most cited first, 12 of 12)

- [Anatomy-aware and acquisition-agnostic joint registration with SynthMorph](https://mlsanity.com/paper/2301.11329/) (2023)
- [Data synthesis and adversarial networks: A review and meta-analysis in cancer imaging](https://mlsanity.com/paper/2107.09543/) (2021)
- [Light-weight Deformable Registration using Adversarial Learning with Distilling Knowledge](https://mlsanity.com/paper/2110.01293/) (2021)
- [A multi-stage GAN for multi-organ chest X-ray image generation and segmentation](https://mlsanity.com/paper/2106.05132/) (2021)
- [Bridging the gap between paired and unpaired medical image translation](https://mlsanity.com/paper/2110.08407/) (2021)
- [Unsupervised Echocardiography Registration through Patch-based MLPs and Transformers](https://mlsanity.com/paper/2211.11687/) (2022)
- [Synth-by-Reg (SbR): Contrastive learning for synthesis-based registration of paired images](https://mlsanity.com/paper/2107.14449/) (2021)
- [From Traditional to Deep Learning Approaches in Whole Slide Image Registration: A Methodological Review](https://mlsanity.com/paper/2502.19123/) (2025)
- [Style transfer between Microscopy and Magnetic Resonance Imaging via Generative Adversarial Network in small sample size settings](https://mlsanity.com/paper/2310.10414/) (2023)
- [Automatic laminectomy cutting plane planning based on artificial intelligence in robot assisted laminectomy surgery](https://mlsanity.com/paper/2312.17266/) (2023)
- [Multi-modal deformable image registration using untrained neural networks](https://mlsanity.com/paper/2411.02672/) (2024)
- [RealKeyMorph: Keypoints in Real-world Coordinates for Resolution-agnostic Image Registration](https://mlsanity.com/paper/2506.10344/) (2025)

## Abstract (arXiv)

Deformable Image Registration (DIR) of MR and CT images is one of the most challenging registration task, due to the inherent structural differences of the modalities and the missing dense ground truth. Recently cycle Generative Adversarial Networks (cycle-GANs) have been used to learn the intensity relationship between these 2 modalities for unpaired brain data. Yet its usefulness for DIR was not assessed. In this study we evaluate the DIR performance for thoracic and abdominal organs after synthesis by cycle-GAN. We show that geometric changes, which differentiate the two populations (e.g. inhale vs. exhale), are readily synthesized as well. This causes substantial problems for any application which relies on spatial correspondences being preserved between the real and the synthesized image (e.g. plan, segmentation, landmark propagation). To alleviate this problem, we investigated reducing the spatial information provided to the discriminator by decreasing the size of its receptive fields. Image synthesis was learned from 17 unpaired subjects per modality. Registration performance was evaluated with respect to manual segmentations of 11 structures for 3 subjects from the VISERAL challenge. State-of-the-art DIR methods based on Normalized Mutual Information (NMI), Modality Independent Neighborhood Descriptor (MIND) and their novel combination achieved a mean segmentation overlap ratio of 76.7, 67.7, 76.9%, respectively. This dropped to 69.1% or less when registering images synthesized by cycle-GAN based on local correlation, due to the poor performance on the thoracic region, where large lung volume changes were synthesized. Performance for the abdominal region was similar to that of CT-MRI NMI registration (77.4 vs. 78.8%) when using 3D synthesizing MRIs (12 slices) and medium sized receptive fields for the discriminator.