Flip Distribution Alignment VAE for Multi-Phase MRI Synthesis
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916987377025024 |
|---|---|
| author | Kui, Xiaoyan Xiao, Qianmu Li, Qqinsong Ji, Zexin Zhang, JIelin Zou, Beiji |
| author_facet | Kui, Xiaoyan Xiao, Qianmu Li, Qqinsong Ji, Zexin Zhang, JIelin Zou, Beiji |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_02970 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Flip Distribution Alignment VAE for Multi-Phase MRI Synthesis Kui, Xiaoyan Xiao, Qianmu Li, Qqinsong Ji, Zexin Zhang, JIelin Zou, Beiji Computer Vision and Pattern Recognition 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. |
| title | Flip Distribution Alignment VAE for Multi-Phase MRI Synthesis |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2510.02970 |