# Domain-Adaptive 3D Medical Image Synthesis: An Efficient Unsupervised Approach

arXiv: https://arxiv.org/abs/2207.00844 · HTML: https://mlsanity.com/paper/2207.00844/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 18 references that are in the map.
- First posted on arXiv 2 Jul 2022.

## Builds on (most cited first, 9 of 9)

- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Adversarial Discriminative Domain Adaptation](https://mlsanity.com/paper/1702.05464/) (2017)
- [Unsupervised domain adaptation in brain lesion segmentation with adversarial networks](https://mlsanity.com/paper/1612.08894/) (2016)
- [Test-Time Adaptable Neural Networks for Robust Medical Image Segmentation](https://mlsanity.com/paper/2004.04668/) (2020)
- [Unsupervised domain adaptation for medical imaging segmentation with self-ensembling](https://mlsanity.com/paper/1811.06042/) (2018)
- [Unsupervised Cross-Modality Domain Adaptation of ConvNets for Biomedical Image Segmentations with Adversarial Loss](https://mlsanity.com/paper/1804.10916/) (2018)
- [Data Efficient Unsupervised Domain Adaptation for Cross-Modality Image Segmentation](https://mlsanity.com/paper/1907.02766/) (2019)
- [Continual Learning for Domain Adaptation in Chest X-ray Classification](https://mlsanity.com/paper/2001.05922/) (2020)
- [Modelling the Distribution of 3D Brain MRI using a 2D Slice VAE](https://mlsanity.com/paper/2007.04780/) (2020)

## Built on by (most cited first, 8 of 8)

- [Deep Learning Approaches for Data Augmentation in Medical Imaging: A Review](https://mlsanity.com/paper/2307.13125/) (2023)
- [The Brain Tumor Segmentation (BraTS) Challenge 2023: Brain MR Image Synthesis for Tumor Segmentation (BraSyn)](https://mlsanity.com/paper/2305.09011/) (2023)
- [Deep Generative Models for 3D Medical Image Synthesis](https://mlsanity.com/paper/2410.17664/) (2024)
- [Data efficient deep learning for medical image analysis: A survey](https://mlsanity.com/paper/2310.06557/) (2023)
- [Memory-efficient High-resolution OCT Volume Synthesis with Cascaded Amortized Latent Diffusion Models](https://mlsanity.com/paper/2405.16516/) (2024)
- [Navigating Distribution Shifts in Medical Image Analysis: A Survey](https://mlsanity.com/paper/2411.05824/) (2024)
- [Cascaded 3D Diffusion Models for Whole-body 3D 18-F FDG PET/CT synthesis from Demographics](https://mlsanity.com/paper/2505.22489/) (2025)
- [VS-DDPM: Efficient Low-Cost Diffusion Model for Medical Modality Translation](https://mlsanity.com/paper/2604.22942/) (2026)

## Abstract (arXiv)

Medical image synthesis has attracted increasing attention because it could generate missing image data, improving diagnosis and benefits many downstream tasks. However, so far the developed synthesis model is not adaptive to unseen data distribution that presents domain shift, limiting its applicability in clinical routine. This work focuses on exploring domain adaptation (DA) of 3D image-to-image synthesis models. First, we highlight the technical difference in DA between classification, segmentation and synthesis models. Second, we present a novel efficient adaptation approach based on 2D variational autoencoder which approximates 3D distributions. Third, we present empirical studies on the effect of the amount of adaptation data and the key hyper-parameters. Our results show that the proposed approach can significantly improve the synthesis accuracy on unseen domains in a 3D setting. The code is publicly available at https://github.com/WinstonHuTiger/2D_VAE_UDA_for_3D_sythesis