EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

SynthPET: A 3D generative AI approach for FDG‐PET image synthesis from T1‐weighted MRI and ASL CBF in Alzheimer's disease

Xavier Beltran-Urbano iD, Katie R Jobson, Ilya M Nasrallah, Ajay Kumar, Manuel Taso, Sandhitsu R Das, Christopher A Brown, Sipei Li, Long Xie, Corey T McMillan, Paul A Yushkevich, Dave A Wolk und 4 weitere

Alzheimer's & Dementia · 2026

DOI: 10.1002/alz.71822 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Alzheimer's & Dementia, 2026. Verfasst von Xavier Beltran-Urbano und 15 weiteren Autor:innen. Beteiligte Einrichtung: Department of Bioengineering, University of Pennsylvania, Philadelphia, Pennsylvania, USA. Hauptthemen laut MEDLINE: Alzheimer Disease, Positron-Emission Tomography, Magnetic Resonance Imaging, Deep Learning. Die Arbeit nennt 69 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: NIH HHS, National Institutes of Health.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

INTRODUCTION Fluorodeoxyglucose (FDG) positron emission tomography (PET) is widely used for detecting metabolic changes associated with neurodegeneration in Alzheimer's disease (AD) and other dementias but is costly and involves ionizing radiation. Here we developed SynthPET, a multimodal deep learning framework that synthesizes FDG PET images from T1‐weighted (T1w) and arterial spin labeling (ASL) perfusion magnetic resonance imaging (MRI) data. METHODS Two conditional generative models were trained on paired MRI and FDG PET acquisitions: one using T1w alone ( n = 1170) and one integrating T1w with ASL via cross‐modality transfer learning ( n = 220). We evaluated synthetic FDG PET through voxel‐wise fidelity metrics, regional correlation and receiver operating characteristic analyses, blinded reader studies, and differential diagnosis across independent external cohorts. RESULTS Both models achieved high fidelity with real FDG PET (structural similarity > 93%) and strong diagnostic performance in AD‐specific regions, with ASL providing modest improvements. Results generalized to an independent AD external cohort. DISCUSSION SynthPET generates clinically plausible FDG PET from routinely acquired MRI, potentially expanding access to metabolic neuroimaging where PET is unavailable.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Alzheimer DiseasePositron-Emission TomographyMagnetic Resonance ImagingDeep LearningHumansFluorodeoxyglucose F18Generative Artificial IntelligencePerfusion Magnetic Resonance ImagingBrainMaleRadiopharmaceuticalsFemaleCerebrovascular CirculationAgedImaging, Three-DimensionalSpin Labels

Stichwörter der Autor:innen

Alzheimer's diseaseT1‐weighted magnetic resonance imagingarterial spin labelingcerebral blood flowcross‐modality synthesisdeep learningfluorodeoxyglucose positron emission tomographygenerative adversarial networkneurodegenerationsynthetic positron emission tomographytransfer learning

Substanzen

Fluorodeoxyglucose F18RadiopharmaceuticalsSpin Labels

Autor:innen und Institutionen

  • Department of Bioengineering, University of Pennsylvania, Philadelphia, Pennsylvania, USA.
  • Department of Neurology, University of Pennsylvania, Philadelphia, Pennsylvania, USA.
  • Department of Radiology, University of Pennsylvania, Philadelphia, Pennsylvania, USA.
  • Department of Digital Technology and Innovation, Siemens Healthineers, Princeton, New Jersey, USA.
  • Department of Radiology, Stanford University, Stanford, California, USA.

ORCID-Profile: Xavier Beltran-Urbano

Förderung

  • NIH HHS
  • National Institutes of Health

Zitieren

APA

Beltran-Urbano, X., Jobson, K. R., Nasrallah, I. M., Kumar, A., Taso, M., Das, S. R., Brown, C. A., Li, S., Xie, L., McMillan, C. T., Yushkevich, P. A., Wolk, D. A., Zaharchuk, G., Dolui, S., Detre, J. A., & Alzheimer's Disease Neuroimaging Initiative (2026). SynthPET: A 3D generative AI approach for FDG‐PET image synthesis from T1‐weighted MRI and ASL CBF in Alzheimer's disease. Alzheimer's & Dementia. https://doi.org/10.1002/alz.71822

Vancouver

Beltran-Urbano X, Jobson KR, Nasrallah IM, Kumar A, Taso M, Das SR, et al. SynthPET: A 3D generative AI approach for FDG‐PET image synthesis from T1‐weighted MRI and ASL CBF in Alzheimer's disease. Alzheimer's & Dementia. 2026. doi:10.1002/alz.71822

BibTeX
@article{BeltranUrbano2026,
  author = {Beltran-Urbano, Xavier and Jobson, Katie R and Nasrallah, Ilya M and Kumar, Ajay and Taso, Manuel and Das, Sandhitsu R and Brown, Christopher A and Li, Sipei and Xie, Long and McMillan, Corey T and Yushkevich, Paul A and Wolk, Dave A and Zaharchuk, Greg and Dolui, Sudipto and Detre, John A and Alzheimer's Disease Neuroimaging Initiative, Alzheimer's Disease Neuroimaging Initiative},
  title = {SynthPET: A 3D generative AI approach for FDG‐PET image synthesis from T1‐weighted MRI and ASL CBF in Alzheimer's disease},
  journal = {Alzheimer's & Dementia},
  year = {2026},
  doi = {10.1002/alz.71822}
}
Kostenlos starten →