3D MedDiffusion: A 3D Medical Latent Diffusion Model for Controllable and High-Quality Medical Image Generation
IEEE Transactions on Medical Imaging · 2025
DOI: 10.1109/tmi.2025.3585372 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Medical Imaging, 2025. Verfasst von Haoshen Wang und 5 weiteren Autor:innen. Hauptthemen laut MEDLINE: Imaging, Three-Dimensional. Die Arbeit wurde bisher 45-mal zitiert (Crossref) und nennt 64 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Shanghai Municipal Central Guided Local Science and Technology Development Fund, High Performance Computing (HPC) Platform of ShanghaiTech University.
Abstract (Originalsprache)
The generation of medical images presents significant challenges due to their high-resolution and three-dimensional nature. Existing methods often yield suboptimal performance in generating high-quality 3D medical images, and there is currently no universal generative framework for medical imaging. In this paper, we introduce a 3D Medical Latent Diffusion (3D MedDiffusion) model for controllable, high-quality 3D medical image generation. 3D MedDiffusion incorporates a novel, highly efficient Patch-Volume Autoencoder that compresses medical images into latent space through patch-wise encoding and recovers back into image space through volume-wise decoding. Additionally, we design a new noise estimator to capture both local details and global structural information during diffusion denoising process. 3D MedDiffusion can generate fine-detailed, high-resolution images (up to ${512}\times {512}\times {512}$ ) and effectively adapt to various downstream tasks as it is trained on large-scale datasets covering CT and MRI modalities and different anatomical regions (from head to leg). Experimental results demonstrate that 3D MedDiffusion surpasses state-of-the-art methods in generative quality and exhibits strong generalizability across tasks such as sparse-view CT reconstruction, fast MRI reconstruction, and data augmentation for segmentationand classification. Source code and checkpoints are available at https://github.com/ShanghaiTech-IMPACT/3D-MedDiffusion.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Förderung
- National Natural Science Foundation of China
- Shanghai Municipal Central Guided Local Science and Technology Development Fund
- High Performance Computing (HPC) Platform of ShanghaiTech University
Zitieren
APA
Wang, H., Liu, Z., Sun, K., Wang, X., Shen, D., & Cui, Z. (2025). 3D MedDiffusion: A 3D Medical Latent Diffusion Model for Controllable and High-Quality Medical Image Generation. IEEE Transactions on Medical Imaging. https://doi.org/10.1109/tmi.2025.3585372
Vancouver
Wang H, Liu Z, Sun K, Wang X, Shen D, Cui Z. 3D MedDiffusion: A 3D Medical Latent Diffusion Model for Controllable and High-Quality Medical Image Generation. IEEE Transactions on Medical Imaging. 2025. doi:10.1109/tmi.2025.3585372
BibTeX
@article{Wang2025,
author = {Wang, Haoshen and Liu, Zhentao and Sun, Kaicong and Wang, Xiaodong and Shen, Dinggang and Cui, Zhiming},
title = {3D MedDiffusion: A 3D Medical Latent Diffusion Model for Controllable and High-Quality Medical Image Generation},
journal = {IEEE Transactions on Medical Imaging},
year = {2025},
doi = {10.1109/tmi.2025.3585372}
}
EUVIMED