Academic Journal
Synthesis of Amyloid Images Using a Generative Adversarial Network from 2-Dimensional 18F-FDG Images and Evaluation for Clinical Use.
| Title: | Synthesis of Amyloid Images Using a Generative Adversarial Network from 2-Dimensional 18F-FDG Images and Evaluation for Clinical Use. |
|---|---|
| Authors: | Honda M; Graduate School of Science and Engineering, Kindai University, Osaka, Japan., Yamada T; Division of Positron Emission Tomography, Institute of Advanced Clinical Medicine, Kindai University Hospital, Osaka, Japan., Watanabe S; National Cerebral and Cardiovascular Center Hospital, Osaka, Japan., Watanabe A; Graduate School of Science and Engineering, Kindai University, Osaka, Japan.; Akita Cerebrospinal and Cardiovascular Center, Akita, Japan., Nagaoka T; Faculty of Biology-Oriented Science and Technology, Kindai University, Wakayama, Japan., Nemoto M; Faculty of Biology-Oriented Science and Technology, Kindai University, Wakayama, Japan., Mikami K; Faculty of Biology-Oriented Science and Technology, Kindai University, Wakayama, Japan., Hanaoka K; Division of Positron Emission Tomography, Institute of Advanced Clinical Medicine, Kindai University Hospital, Osaka, Japan., Kaida H; Division of Positron Emission Tomography, Institute of Advanced Clinical Medicine, Kindai University Hospital, Osaka, Japan.; Department of Radiology, Faculty of Medicine, Kindai University, Osaka, Japan; and., Handa H; Graduate School of Science and Engineering, Kindai University, Osaka, Japan.; Faculty of Informatics, Cyber Informatics Research Institute, Kindai University, Osaka, Japan., Ishii K; Division of Positron Emission Tomography, Institute of Advanced Clinical Medicine, Kindai University Hospital, Osaka, Japan.; Department of Radiology, Faculty of Medicine, Kindai University, Osaka, Japan; and., Kimura Y; Graduate School of Science and Engineering, Kindai University, Osaka, Japan; ukimura@ieee.org.; Faculty of Informatics, Cyber Informatics Research Institute, Kindai University, Osaka, Japan. |
| Source: | Journal of nuclear medicine technology [J Nucl Med Technol] 2026 Jun 03; Vol. 54 (2), pp. 177-182. Date of Electronic Publication: 2026 Jun 03. |
| Publication Type: | Journal Article |
| Language: | English |
| Journal Info: | Publisher: Society of Nuclear Medicine Country of Publication: United States NLM ID: 0430303 Publication Model: Electronic Cited Medium: Internet ISSN: 1535-5675 (Electronic) Linking ISSN: 00914916 NLM ISO Abbreviation: J Nucl Med Technol Subsets: MEDLINE |
| Imprint Name(s): | Publication: Reston, VA : Society of Nuclear Medicine Original Publication: New York. |
| MeSH Terms: | Amyloid*/metabolism , Image Processing, Computer-Assisted*/methods , Positron-Emission Tomography*/methods , Generative Adversarial Networks* , Generative Artificial Intelligence*, Humans ; Fluorodeoxyglucose F18 |
| Abstract: | 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. (© 2026 by the Society of Nuclear Medicine and Molecular Imaging.) |
| Contributed Indexing: | Keywords: Alzheimer disease; PET; generative AI; image processing |
| Substance Nomenclature: | 0 (Amyloid) 0Z5B2CJX4D (Fluorodeoxyglucose F18) |
| Entry Date(s): | Date Created: 20260113 Date Completed: 20260607 Latest Revision: 20260726 |
| Update Code: | 20260726 |
| PubMed Central ID: | PMC13235630 |
| DOI: | 10.2967/jnmt.125.270154 |
| PMID: | 41529928 |
| Database: | MEDLINE |
| ISSN: | 1535-5675 |
|---|---|
| DOI: | 10.2967/jnmt.125.270154 |