# Anatomically constrained CT image translation for heterogeneous blood vessel segmentation

arXiv: https://arxiv.org/abs/2210.01713 · HTML: https://mlsanity.com/paper/2210.01713/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 42 references that are in the map.
- First posted on arXiv 4 Oct 2022.

## Builds on (most cited first, 16 of 16)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks](https://mlsanity.com/paper/1703.10593/) (2017)
- [Wasserstein GAN](https://mlsanity.com/paper/1701.07875/) (2017)
- [Unsupervised Image-to-Image Translation Networks](https://mlsanity.com/paper/1703.00848/) (2017)
- [Conditional Image Synthesis With Auxiliary Classifier GANs](https://mlsanity.com/paper/1610.09585/) (2016)
- [Generative Adversarial Network in Medical Imaging: A Review](https://mlsanity.com/paper/1809.07294/) (2018)
- [U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation](https://mlsanity.com/paper/1907.10830/) (2019)
- [ResViT: Residual vision transformers for multi-modal medical image synthesis](https://mlsanity.com/paper/2106.16031/) (2021)
- [TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Up](https://mlsanity.com/paper/2102.07074/) (2021)
- [Image Synthesis in Multi-Contrast MRI with Conditional Generative Adversarial Networks](https://mlsanity.com/paper/1802.01221/) (2018)
- [A U-Net Based Discriminator for Generative Adversarial Networks](https://mlsanity.com/paper/2002.12655/) (2020)
- [Attention Branch Network: Learning of Attention Mechanism for Visual Explanation](https://mlsanity.com/paper/1812.10025/) (2018)
- [Unsupervised Medical Image Translation Using Cycle-MedGAN](https://mlsanity.com/paper/1903.03374/) (2019)
- [InstaFormer: Instance-Aware Image-to-Image Translation with Transformer](https://mlsanity.com/paper/2203.16248/) (2022)
- [Cross-Domain Medical Image Translation by Shared Latent Gaussian Mixture Model](https://mlsanity.com/paper/2007.07230/) (2020)
- [Kernel of CycleGAN as a Principle homogeneous space](https://mlsanity.com/paper/2001.09061/) (2020)

## Built on by (most cited first, 6 of 6)

- [Diffusion-based Data Augmentation for Skin Disease Classification: Impact Across Original Medical Datasets to Fully Synthetic Images](https://mlsanity.com/paper/2301.04802/) (2023)
- [Generating Realistic Brain MRIs via a Conditional Diffusion Probabilistic Model](https://mlsanity.com/paper/2212.08034/) (2022)
- [Latent Causal Modeling for 3D Brain MRI Counterfactuals](https://mlsanity.com/paper/2409.05585/) (2024)
- [Generating 3D Brain Tumor Regions in MRI using Vector-Quantization Generative Adversarial Networks](https://mlsanity.com/paper/2310.01251/) (2023)
- [Integrating Anatomical Priors into a Causal Diffusion Model](https://mlsanity.com/paper/2509.09054/) (2025)
- [Unsupervised Domain Adaptation with Target-Only Margin Disparity Discrepancy](https://mlsanity.com/paper/2603.09932/) (2026)

## Abstract (arXiv)

Anatomical structures such as blood vessels in contrast-enhanced CT (ceCT) images can be challenging to segment due to the variability in contrast medium diffusion. The combined use of ceCT and contrast-free (CT) CT images can improve the segmentation performances, but at the cost of a double radiation exposure. To limit the radiation dose, generative models could be used to synthesize one modality, instead of acquiring it. The CycleGAN approach has recently attracted particular attention because it alleviates the need for paired data that are difficult to obtain. Despite the great performances demonstrated in the literature, limitations still remain when dealing with 3D volumes generated slice by slice from unpaired datasets with different fields of view. We present an extension of CycleGAN to generate high fidelity images, with good structural consistency, in this context. We leverage anatomical constraints and automatic region of interest selection by adapting the Self-Supervised Body Regressor. These constraints enforce anatomical consistency and allow feeding anatomically-paired input images to the algorithm. Results show qualitative and quantitative improvements, compared to stateof-the-art methods, on the translation task between ceCT and CT images (and vice versa).