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

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.

Key words

GAN - cumulative activity - image translation - PET

Publication History

Received: 09 August 2022

Accepted: 01 February 2023

Article published online:
06 March 2023

• References

• 1 Townsend DW, Carney JP, Yap JT. et al. PET/CT today and tomorrow. Journal of Nuclear Medicine 2004; 45 (01) 4S-14S
• 2 Hu P, Lin X, Zhuo W. et al. Internal dosimetry in F-18 FDG PET examinations based on long-time-measured organ activities using total-body PET/CT: does it make any difference from a short-time measurement?. EJNMMI physics 2021; 8 (01) 1-17
• 3 Dias AH, Hansen AK, Munk OL. et al. Normal values for 18F-FDG uptake in organs and tissues measured by dynamic whole body multiparametric FDG PET in 126 patients. EJNMMI research 2022; 12 (01) 1-14
• 4 Valentin J. Radiation dose to patients from radiopharmaceuticals: (Addendum 2 to ICRP Publication 53) ICRP Publication 80 Approved by the Commission in September 1997. Annals of the ICRP 1998; 28 (03) 1
• 5 Watabe H, Ikoma Y, Kimura Y. et al. PET kinetic analysis compartmental model. Annals of nuclear medicine 2006; 20 (09) 583-588
• 6 Baldock C. editor. Trends in Radiation Dosimetry: preliminary overview of active growth areas, research trends and hot topics from 2011-2015. Journal of Physics: Conference Series. IOP Publishing; 2017
• 7 Kjaer A. Hybrid imaging with PET/CT and PET/MR. Cancer Imaging 2014; 14 (Suppl. 01) O32
• 8 Weber WA. Quantitative analysis of PET studies. Radiotherapy and Oncology 2010; 96 (03) 308-310
• 9 Dimitrakopoulou-Strauss A, Pan L, Sachpekidis C. Kinetic modeling and parametric imaging with dynamic PET for oncological applications: general considerations, current clinical applications, and future perspectives. European Journal of Nuclear Medicine and Molecular Imaging 2021; 48 (01) 21-39
• 10 Karimipourfard M, Sina S, Alavi M. Toward three-dimensional patient-specific internal dosimetry using GATE Monte Carlo technique. Radiation Physics and Chemistry 2022; 195: 110046
• 11 Karimipourfard M, Sina S, Shobeiry M. et al. Effective dose Estimation in Whole Body 18F-FDG PET/CT Imaging. Radiation Protection Dosimetry 2022; 198 (18) 1444-1449
• 12 Isola P, Zhu J-Y, Zhou T. et al editors. Image-to-image translation with conditional adversarial networks. Proceedings of the IEEE conference on computer vision and pattern recognition. 2017
• 13 Armanious K, Jiang C, Fischer M. et al. MedGAN: Medical image translation using GANs. Computerized medical imaging and graphics 2020; 79: 101684
• 14 Goodfellow IJ, Pouget-Abadie J, Mirza M. et al. Generative adversarial nets (Advances in neural information processing systems). Red Hook, NY Curran; 2014: 2672-2680
• 15 Kong L, Lian C, Huang D. et al. Breaking the dilemma of medical image-to-image translation. Advances in Neural Information Processing Systems 2021; 34: 1964-1978
• 16 Segars WP, Sturgeon G, Mendonca S. et al. 4D XCAT phantom for multimodality imaging research. Medical physics 2010; 37 (09) 4902-4915
• 17 Wang C-Y, Liao H-YM, Wu Y-H. et al editors. CSPNet: A new backbone that can enhance learning capability of CNN. Proceedings of the IEEE/CVF conference on computer vision and pattern recognition workshops. 2020
• 18 Segars WP, Tsui BM, Cai J. et al. Application of the 4-D XCAT phantoms in biomedical imaging and beyond. IEEE transactions on medical imaging 2017; 37 (03) 680-692
• 19 Kaushik A, Jaimini A, Tripathi M. et al. Estimation of radiation dose to patients from 18FDG whole body PET/CT investigations using dynamic PET scan protocol. The Indian journal of medical research 2015; 142 (06) 721
• 20 Birindelli G, Drobnjakovic M, Morath V. et al. Is Hypoxia a Factor Influencing PSMA-Directed Radioligand Therapy? – An In Silico Study on the Role of Chronic Hypoxia in Prostate Cancer. Cancers 2021; 13 (14) 3429
• 21 Cheng X, Li Z, Liu Z. et al. Direct parametric image reconstruction in reduced parameter space for rapid multi-tracer PET imaging. IEEE transactions on medical imaging 2015; 34 (07) 1498-1512
• 22 Huet P, Burg S, Le Guludec D. et al. Variability and uncertainty of 18F-FDG PET imaging protocols for assessing inflammation in atherosclerosis: suggestions for improvement. Journal of Nuclear Medicine 2015; 56 (04) 552-559
• 23 Lv J, Wang C, Yang G. PIC-GAN: a parallel imaging coupled generative adversarial network for accelerated multi-channel MRI reconstruction. Diagnostics 2021; 11 (01) 61
• 24 Zhang Z. editor. Improved adam optimizer for deep neural networks. 2018 IEEE/ACM 26th International Symposium on Quality of Service (IWQoS). Ieee; 2018
• 25 Hu X, Naiel MA, Wong A. et al editors. RUNet: A robust UNet architecture for image super-resolution. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. 2019
• 26 Hore A, Ziou D. editors. Image quality metrics: PSNR vs. SSIM. 2010 20th international conference on pattern recognition. IEEE; 2010
• 27 Sara U, Akter M, Uddin MS. Image quality assessment through FSIM, SSIM, MSE and PSNR—a comparative study. Journal of Computer and Communications 2019; 7 (03) 8-18
• 28 Chen T, Kornblith S, Swersky K. et al. Big self-supervised models are strong semi-supervised learners. Advances in neural information processing systems 2020; 33: 22243-22255
• 29 Kim P. Matlab deep learning with machine learning, neural networks and artificial intelligence. by Phil Kim, 2017