# XCAT-GAN for Synthesizing 3D Consistent Labeled Cardiac MR Images on Anatomically Variable XCAT Phantoms

arXiv: https://arxiv.org/abs/2007.13408 · HTML: https://mlsanity.com/paper/2007.13408/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Jul 2020.

## Built on by (most cited first, 11 of 11)

- [D'ARTAGNAN: Counterfactual Video Generation](https://mlsanity.com/paper/2206.01651/) (2022)
- [GAN-Based Data Augmentation and Anonymization for Skin-Lesion Analysis: A Critical Review](https://mlsanity.com/paper/2104.10603/) (2021)
- [BOSS: Bones, Organs and Skin Shape Model](https://mlsanity.com/paper/2303.04923/) (2023)
- [Synthetic Data in Healthcare](https://mlsanity.com/paper/2304.03243/) (2023)
- [Pathology Synthesis of 3D-Consistent Cardiac MR Images using 2D VAEs and GANs](https://mlsanity.com/paper/2209.04223/) (2022)
- [A Data Augmentation Pipeline to Generate Synthetic Labeled Datasets of 3D Echocardiography Images using a GAN](https://mlsanity.com/paper/2403.05384/) (2024)
- [Optimized Automated Cardiac MR Scar Quantification with GAN-Based Data Augmentation](https://mlsanity.com/paper/2109.12940/) (2021)
- [3D Brain and Heart Volume Generative Models: A Survey](https://mlsanity.com/paper/2210.05952/) (2022)
- [3D Conditional Image Synthesis of Left Atrial LGE MRI from Composite Semantic Masks](https://mlsanity.com/paper/2601.04588/) (2026)
- [Automated Diagnosis of Cardiovascular Diseases from Cardiac Magnetic Resonance Imaging Using Deep Learning Models: A Review](https://mlsanity.com/paper/2210.14909/) (2022)
- [PathCo-LatticE: Pathology-Constrained Lattice-Of Experts Framework for Fully-supervised Few-Shot Cardiac MRI Segmentation](https://mlsanity.com/paper/2512.09779/) (2025)

## Abstract (arXiv)

Generative adversarial networks (GANs) have provided promising data enrichment solutions by synthesizing high-fidelity images. However, generating large sets of labeled images with new anatomical variations remains unexplored. We propose a novel method for synthesizing cardiac magnetic resonance (CMR) images on a population of virtual subjects with a large anatomical variation, introduced using the 4D eXtended Cardiac and Torso (XCAT) computerized human phantom. We investigate two conditional image synthesis approaches grounded on a semantically-consistent mask-guided image generation technique: 4-class and 8-class XCAT-GANs. The 4-class technique relies on only the annotations of the heart; while the 8-class technique employs a predicted multi-tissue label map of the heart-surrounding organs and provides better guidance for our conditional image synthesis. For both techniques, we train our conditional XCAT-GAN with real images paired with corresponding labels and subsequently at the inference time, we substitute the labels with the XCAT derived ones. Therefore, the trained network accurately transfers the tissue-specific textures to the new label maps. By creating 33 virtual subjects of synthetic CMR images at the end-diastolic and end-systolic phases, we evaluate the usefulness of such data in the downstream cardiac cavity segmentation task under different augmentation strategies. Results demonstrate that even with only 20% of real images (40 volumes) seen during training, segmentation performance is retained with the addition of synthetic CMR images. Moreover, the improvement in utilizing synthetic images for augmenting the real data is evident through the reduction of Hausdorff distance up to 28% and an increase in the Dice score up to 5%, indicating a higher similarity to the ground truth in all dimensions.