EUVIMEDEUVIMED entdecken
Open Access

Synthesis of Amyloid Images Using a Generative Adversarial Network from 2-Dimensional 18 F-FDG Images and Evaluation for Clinical Use

Misa Honda, Takahiro Yamada, Shogo Watanabe, Aya Watanabe, Takashi Nagaoka, Mitsutaka Nemoto, Katsuhiro Mikami, Kohei Hanaoka, Hayato Kaida, Hisashi Handa, Kazunari Ishii, Yuichi Kimura

Journal of Nuclear Medicine Technology · 2026

DOI: 10.2967/jnmt.125.270154 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Nuclear Medicine Technology, 2026. Verfasst von Misa Honda und 11 weiteren Autor:innen. Beteiligte Einrichtung: Graduate School of Science and Engineering, Kindai University, Osaka, Japan. Hauptthemen laut MEDLINE: Amyloid, Generative Adversarial Networks, Generative Artificial Intelligence, Image Processing, Computer-Assisted. Die Arbeit nennt 19 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The use of amyloid PET to assess patient suitability of disease-modifying drugs for Alzheimer disease is increasing. This study aimed to synthesize amyloid PET images from 18F-FDG PET images using a generative artificial intelligence algorithm to reduce unnecessary amyloid PET scans.

Methods

A 2-dimensional pix2pix algorithm was used. The algorithm was evaluated across 4 domains: image quality, voxel values, contrast between white and gray matter, and diagnostic performance for detecting the presence or absence of β-amyloid (Aβ) deposition. Pairs of 18F-FDG PET and amyloid PET images from 55 Aβ-negative and -positive cases were evaluated. A 6-fold cross-validation was conducted.

Results

Synthetic images were visually consistent, producing plausible negative and positive patterns while preserving continuity in the sagittal plane. Voxel values of the synthetic images showed a significant linear relationship with the real images. The contrast correlated well with the real images, and the differences between the negative and positive cases were significant as well as those in the real images. The performance of the positive or negative 2-class classifier exceeded 85% for the synthetic images.

Conclusion

The synthetic images successfully captured features of Aβ deposition, and evaluation with a 2-class classifier achieved an acceptable accuracy of 85%. These results suggest that amyloid images can potentially be generated from 18F-FDG PET images for use in clinical practice.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AmyloidGenerative Adversarial NetworksGenerative Artificial IntelligenceImage Processing, Computer-AssistedPositron-Emission TomographyHumansFluorodeoxyglucose F18

Stichwörter der Autor:innen

Alzheimer diseasePETgenerative AIimage processing

Substanzen

AmyloidFluorodeoxyglucose F18

Autor:innen und Institutionen

  • Graduate School of Science and Engineering, Kindai University, Osaka, Japan.
  • Division of Positron Emission Tomography, Institute of Advanced Clinical Medicine, Kindai University Hospital, Osaka, Japan.
  • National Cerebral and Cardiovascular Center Hospital, Osaka, Japan.
  • Akita Cerebrospinal and Cardiovascular Center, Akita, Japan.
  • Faculty of Biology-Oriented Science and Technology, Kindai University, Wakayama, Japan.
  • Department of Radiology, Faculty of Medicine, Kindai University, Osaka, Japan; and.

Zitieren

APA

Honda, M., Yamada, T., Watanabe, S., Watanabe, A., Nagaoka, T., Nemoto, M., Mikami, K., Hanaoka, K., Kaida, H., Handa, H., Ishii, K., & Kimura, Y. (2026). Synthesis of Amyloid Images Using a Generative Adversarial Network from 2-Dimensional 18 F-FDG Images and Evaluation for Clinical Use. Journal of Nuclear Medicine Technology. https://doi.org/10.2967/jnmt.125.270154

Vancouver

Honda M, Yamada T, Watanabe S, Watanabe A, Nagaoka T, Nemoto M, et al. Synthesis of Amyloid Images Using a Generative Adversarial Network from 2-Dimensional 18 F-FDG Images and Evaluation for Clinical Use. Journal of Nuclear Medicine Technology. 2026. doi:10.2967/jnmt.125.270154

BibTeX
@article{Honda2026,
  author = {Honda, Misa and Yamada, Takahiro and Watanabe, Shogo and Watanabe, Aya and Nagaoka, Takashi and Nemoto, Mitsutaka and Mikami, Katsuhiro and Hanaoka, Kohei and Kaida, Hayato and Handa, Hisashi and Ishii, Kazunari and Kimura, Yuichi},
  title = {Synthesis of Amyloid Images Using a Generative Adversarial Network from 2-Dimensional 18 F-FDG Images and Evaluation for Clinical Use},
  journal = {Journal of Nuclear Medicine Technology},
  year = {2026},
  doi = {10.2967/jnmt.125.270154}
}
Kostenlos starten →