EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

4D cardiac medical image generation based on a dual U-Net temporal conditional diffusion model

Mei Zhang, Zhengjie Liang, Jiaqi Li, Xiangtai Lai, HeLing Jiang, Jinghua Wen

Biomedical Engineering / Biomedizinische Technik · 2026

DOI: 10.1515/bmt-2025-0503 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Biomedical Engineering / Biomedizinische Technik, 2026. Verfasst von Mei Zhang und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Information, Guizhou University of Finance and Economics, Guiyang, China. Hauptthemen laut MEDLINE: Image Processing, Computer-Assisted, Heart. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Existing medical image generation tasks primarily employ Generative Adversarial Networks (GANs), which perform poorly on datasets with temporal characteristics and suffer from slow generation speed and mode collapse.

Methods

In response to this question, this study puts forward a temporal conditional diffusion model based on a dual U-Net structure, which leverages the dual U-Net to extract rich detail information within a denoising diffusion framework while incorporating temporal information as a condition to guide the generation of 4D cardiac datasets with temporal features. Additionally, a deformation field is utilized to accelerate medical image generation.

Results

Experimental results show that compared to existing methods, the proposed approach can generate dynamic scan time frames while maintaining strong continuity and temporal consistency in both transverse and longitudinal spatial dimensions. In addition, the synthesized images are highly similar to those captured in reality. The proposed method effectively preserves anatomical structural details, making it highly suitable for medical image generation tasks.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Image Processing, Computer-AssistedHeartHumansGenerative Adversarial NetworksAlgorithmsGenerative Artificial Intelligence

Stichwörter der Autor:innen

deformation fielddual U-Netmedical image generationtemporal conditional diffusiontemporal features

Autor:innen und Institutionen

  • School of Information, Guizhou University of Finance and Economics, Guiyang, China.

Zitieren

APA

Zhang, M., Liang, Z., Li, J., Lai, X., Jiang, H., & Wen, J. (2026). 4D cardiac medical image generation based on a dual U-Net temporal conditional diffusion model. Biomedical Engineering / Biomedizinische Technik. https://doi.org/10.1515/bmt-2025-0503

Vancouver

Zhang M, Liang Z, Li J, Lai X, Jiang H, Wen J. 4D cardiac medical image generation based on a dual U-Net temporal conditional diffusion model. Biomedical Engineering / Biomedizinische Technik. 2026. doi:10.1515/bmt-2025-0503

BibTeX
@article{Zhang2026,
  author = {Zhang, Mei and Liang, Zhengjie and Li, Jiaqi and Lai, Xiangtai and Jiang, HeLing and Wen, Jinghua},
  title = {4D cardiac medical image generation based on a dual U-Net temporal conditional diffusion model},
  journal = {Biomedical Engineering / Biomedizinische Technik},
  year = {2026},
  doi = {10.1515/bmt-2025-0503}
}
Kostenlos starten →