EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multi-Modality ViT-cGAN for Low-Dose PET Image Reconstruction

Yaling Fang, Jiahui Yang, Haoran Wan, Shuhan Jin, Shaoya Wang, Yueyang Teng

AI Medicine · 2026

DOI: 10.53941/aim.2026.100001 ↗

Kurz gefasst

Fachartikel in der Zeitschrift AI Medicine, 2026. Verfasst von Yaling Fang und 5 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Positron emission tomography (PET) is an important medical imaging technique that reflects the molecular activity of tissues and organs by injecting radioactive tracers. Low-dose (LD) PET is gradually being adopted to reduce radiation dose and scanning costs, however this usually leads to increased image noise and artifacts, which can affect clinical diagnosis. Therefore, in order to maintain high-quality PET image generation while utilizing LD-PET data, this paper proposes a multi-modality Vision Transformer-based conditional generative adversarial network (ViT-cGAN) that directly achieves high-quality PET image reconstruction using the corresponding LD-PET sinogram data and computed tomography (CT) images. Specifically, the network incorporates the advantages of Vision Transformer and multi-modality inputs. In addition, an extensive objective function is designed to optimize the network for improving the details and visual quality of the reconstructed images. Experimental results show that our proposed method can effectively reconstruct high-quality PET images, outperforming current state-of-the-art methods.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Fang, Y., Yang, J., Wan, H., Jin, S., Wang, S., & Teng, Y. (2026). Multi-Modality ViT-cGAN for Low-Dose PET Image Reconstruction. AI Medicine. https://doi.org/10.53941/aim.2026.100001

Vancouver

Fang Y, Yang J, Wan H, Jin S, Wang S, Teng Y. Multi-Modality ViT-cGAN for Low-Dose PET Image Reconstruction. AI Medicine. 2026. doi:10.53941/aim.2026.100001

BibTeX
@article{Fang2026,
  author = {Fang, Yaling and Yang, Jiahui and Wan, Haoran and Jin, Shuhan and Wang, Shaoya and Teng, Yueyang},
  title = {Multi-Modality ViT-cGAN for Low-Dose PET Image Reconstruction},
  journal = {AI Medicine},
  year = {2026},
  doi = {10.53941/aim.2026.100001}
}
Kostenlos starten →