# Flip Distribution Alignment VAE for Multi-Phase MRI Synthesis

arXiv: https://arxiv.org/abs/2510.02970 · HTML: https://mlsanity.com/paper/2510.02970/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 33 references that are in the map.
- First posted on arXiv 3 Oct 2025.

## Builds on (most cited first, 23 of 23)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation](https://mlsanity.com/paper/2102.04306/) (2021)
- [Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction](https://mlsanity.com/paper/2404.02905/) (2024)
- [Contrastive Learning for Unpaired Image-to-Image Translation](https://mlsanity.com/paper/2007.15651/) (2020)
- [Brain Imaging Generation with Latent Diffusion Models](https://mlsanity.com/paper/2209.07162/) (2022)
- [ResViT: Residual vision transformers for multi-modal medical image synthesis](https://mlsanity.com/paper/2106.16031/) (2021)
- [Hi-Net: Hybrid-fusion Network for Multi-modal MR Image Synthesis](https://mlsanity.com/paper/2002.05000/) (2020)
- [Generative AI for Medical Imaging: extending the MONAI Framework](https://mlsanity.com/paper/2307.15208/) (2023)
- [mustGAN: Multi-Stream Generative Adversarial Networks for MR Image Synthesis](https://mlsanity.com/paper/1909.11504/) (2019)
- [I2I-Mamba: Multi-modal medical image synthesis via selective state space modeling](https://mlsanity.com/paper/2405.14022/) (2024)
- [Structure-Preserving Synthesis: MaskGAN for Unpaired MR-CT Translation](https://mlsanity.com/paper/2307.16143/) (2023)
- [Attri-VAE: attribute-based interpretable representations of medical images with variational autoencoders](https://mlsanity.com/paper/2203.10417/) (2022)
- [SDR-Former: A Siamese Dual-Resolution Transformer for Liver Lesion Classification Using 3D Multi-Phase Imaging](https://mlsanity.com/paper/2402.17246/) (2024)
- [Deform-Mamba Network for MRI Super-Resolution](https://mlsanity.com/paper/2407.05969/) (2024)
- [ImUnity: a generalizable VAE-GAN solution for multicenter MR image harmonization](https://mlsanity.com/paper/2109.06756/) (2021)
- [Multi-scale Transformer Network with Edge-aware Pre-training for Cross-Modality MR Image Synthesis](https://mlsanity.com/paper/2212.01108/) (2022)
- [PTNet: A High-Resolution Infant MRI Synthesizer Based on Transformer](https://mlsanity.com/paper/2105.13993/) (2021)
- [Structural Attention: Rethinking Transformer for Unpaired Medical Image Synthesis](https://mlsanity.com/paper/2406.18967/) (2024)

## Abstract (arXiv)

Separating shared and independent features is crucial for multi-phase contrast-enhanced (CE) MRI synthesis. However, existing methods use deep autoencoder generators with low parameter efficiency and lack interpretable training strategies. In this paper, we propose Flip Distribution Alignment Variational Autoencoder (FDA-VAE), a lightweight feature-decoupled VAE model for multi-phase CE MRI synthesis. Our method encodes input and target images into two latent distributions that are symmetric concerning a standard normal distribution, effectively separating shared and independent features. The Y-shaped bidirectional training strategy further enhances the interpretability of feature separation. Experimental results show that compared to existing deep autoencoder-based end-to-end synthesis methods, FDA-VAE significantly reduces model parameters and inference time while effectively improving synthesis quality. The source code is publicly available at https://github.com/QianMuXiao/FDA-VAE.