Nuklearmedizin 2023; 62(02): 61-72
DOI: 10.1055/a-2026-0784
Radiochemie im Focus

Synthesis of Prospective Multiple Time Points F-18 FDG PET Images from a Single Scan Using a Supervised Generative Adversarial Network

Synthese von prospektiven F-18-FDG-PET-Bildern zu mehreren Zeitpunkten aus einem einzelnen Scan unter Verwendung eines überwachten generativen kontradiktorischen Netzwerks
Merhnoosh Karimipourfard
1   Shiraz University, Shiraz, Iran (the Islamic Republic of)
,
Sedigheh Sina
,
Fereshteh Khodadai Shoshtari
1   Shiraz University, Shiraz, Iran (the Islamic Republic of)
,
Mehrosadat Alavi
2   Shiraz University of Medical Sciences, Shiraz, Iran (the Islamic Republic of)
› Author Affiliations
Preview

Abstract

The cumulative activity map estimation are essential tools for patient specific dosimetry with high accuracy, which is estimated using biokinetic models instead of patient dynamic data or the number of static PET scans, owing to economical and time-consuming points of view. In the era of deep learning applications in medicine, the pix-to-pix (p2 p) GAN neural networks play a significant role in image translation between imaging modalities. In this pilot study, we extended the p2 p GAN networks to generate PET images of patients at different times according to a 60 min scan time after the injection of F-18 FDG. In this regard, the study was conducted in two sections: phantom and patient studies. In the phantom study section, the SSIM, PSNR, and MSE metric results of the generated images varied from 0.98–0.99, 31–34 and 1–2 respectively and the fine-tuned Resnet-50 network classified the different timing images with high performance. In the patient study, these values varied from 0.88–0.93, 36–41 and 1.7–2.2, respectively and the classification network classified the generated images in the true group with high accuracy. The results of phantom studies showed high values of evaluation metrics owing to ideal image quality conditions. However, in the patient study, promising results were achieved which showed that the image quality and training data number affected the network performance. This study aims to assess the feasibility of p2 p GAN network application for different timing image generation.



Publication History

Received: 09 August 2022

Accepted: 01 February 2023

Article published online:
06 March 2023

© 2023. Thieme. All rights reserved.

Georg Thieme Verlag KG
Rüdigerstraße 14, 70469 Stuttgart, Germany