MRI-to-PET synthesis via deep learning for amyloid-β quantification in Alzheimer’s disease - Takeaways - MDSpire

MRI-to-PET synthesis via deep learning for amyloid-β quantification in Alzheimer’s disease

  • By

  • Zhigeng Chen

  • Sheng Bi

  • Yi Shan

  • Feng Wang

  • Yong Wang

  • Zhongyuan Qi

  • Tao Wang

  • Xiaoyuan Li

  • Shengnan Li

  • Huanhui Xiao

  • Silun Wang

  • Bixiao Cui

  • Zhigang Qi

  • Ying Han

  • Shaozhen Yan

  • Jie Lu

  • January 7, 2026

  • 0 min

Share

  • 1

    Alzheimer's disease is marked by amyloid-β plaque accumulation, which can be detected years before clinical diagnosis.

  • 2

    Current Aβ assessment methods include CSF analysis, plasma biomarkers, and PET imaging, each with significant limitations.

  • 3

    Generative adversarial networks (GAN) can synthesize Aβ PET images from structural MRI, offering a non-invasive alternative.

  • 4

    The study developed a GAN-based model to generate synthetic Aβ PET images and evaluate their consistency with real PET scans.

  • 5

    The research included 1009 subjects and aimed to explore the clinical applicability of synthesized Aβ PET images in AD.

Original Source(s)

MRI-to-PET synthesis via deep learning for amyloid-β quantification in Alzheimer’s disease

  • by Zhigeng Chen, Sheng Bi, Yi Shan, Feng Wang, Yong Wang, Zhongyuan Qi, Tao Wang, Xiaoyuan Li, Shengnan Li, Huanhui Xiao, Silun Wang, Bixiao Cui, Zhigang Qi, Ying Han, Shaozhen Yan, Jie Lu

  • January 7, 2026

Related Content

Mass Spec Roundup: From Alzheimer’s to Antarctic Dust 

New studies highlight hidden molecular patterns in Alzheimer’s disease, dolphin milk, Antarctic dust, and oxidative DNA damage 

  • April 29, 2026

  • 7 min
Association of high-density lipoprotein cholesterol with the top 10 causes of death

New Horizons in Menopause, Menopausal Hormone Therapy, and Alzheimer's Disease: Current Insights and Future Directions