EUVIMEDEUVIMED entdecken
Open Access

Personalized MR-Informed Diffusion Models for 3-D PET Image Reconstruction

George Webber, Alexander Hammers, Andrew P King, Andrew J Reader

IEEE Transactions on Radiation and Plasma Medical Sciences · 2026-03 · 10 (3) · 333-343

DOI: 10.1109/trpms.2025.3602262 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Radiation and Plasma Medical Sciences, 2026-03. Verfasst von George Webber und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Biomedical Engineering and Imaging Sciences, King's College London, UK. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: Wellcome Trust, EPSRC Center for Doctoral Training in Smart Medical Imaging, GSK studentship.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recent work has shown improved lesion detectability and flexibility to reconstruction hyperparameters (e.g. scanner geometry or dose level) when PET images are reconstructed by leveraging pre-trained diffusion models. Such methods train a diffusion model (without sinogram data) on high-quality, but still noisy, PET images. In this work, we propose a simple method for generating subject-specific PET images from a dataset of multisubject PET-MR scans, synthesizing "pseudo-PET" images by transforming between different patients' anatomy using image registration. The images we synthesize retain information from the subject's MR scan, leading to higher resolution and the retention of anatomical features compared to the original set of PET images. With simulated and real [18F]FDG datasets, we show that pre-training a personalized diffusion model with subject-specific "pseudo-PET" images improves reconstruction accuracy with low-count data. In particular, the method shows promise in combining information from a guidance MR scan without overly imposing anatomical features, demonstrating an improved trade-off between reconstructing PET-unique image features versus features present in both PET and MR. We believe this approach for generating and utilizing synthetic data has further applications to medical imaging tasks, particularly because patient-specific PET images can be generated without resorting to generative deep learning or large training datasets.

Schlagwörter

Stichwörter der Autor:innen

Image Reconstruction AlgorithmsMagnetic Resonance ImagingPositron Emission TomographyScore-based Generative ModelingSynthetic Data

Autor:innen und Institutionen

  • School of Biomedical Engineering and Imaging Sciences, King's College London, UK.
  • King's College London and Guy's & St Thomas' PET Centre.

Förderung

  • Wellcome Trust
  • EPSRC Center for Doctoral Training in Smart Medical Imaging
  • GSK studentship
  • Wellcome/EPSRC Center for Medical Engineering
  • Engineering and Physical Sciences Research Council

Zitieren

APA

Webber, G., Hammers, A., King, A. P., & Reader, A. J. (2026). Personalized MR-Informed Diffusion Models for 3-D PET Image Reconstruction. IEEE Transactions on Radiation and Plasma Medical Sciences, 10(3), 333-343. https://doi.org/10.1109/trpms.2025.3602262

Vancouver

Webber G, Hammers A, King AP, Reader AJ. Personalized MR-Informed Diffusion Models for 3-D PET Image Reconstruction. IEEE Transactions on Radiation and Plasma Medical Sciences. 2026;10(3):333-343. doi:10.1109/trpms.2025.3602262

BibTeX
@article{Webber2026,
  author = {Webber, George and Hammers, Alexander and King, Andrew P and Reader, Andrew J},
  title = {Personalized MR-Informed Diffusion Models for 3-D PET Image Reconstruction},
  journal = {IEEE Transactions on Radiation and Plasma Medical Sciences},
  year = {2026},
  volume = {10},
  number = {3},
  pages = {333--343},
  doi = {10.1109/trpms.2025.3602262}
}
Kostenlos starten →