Realizing 32-time Scan Duration Reduction of 18F-FDG PET Using Deep Learning Model with Image Augmentation
,
Abstract
Purpose: 32-time scan duration reduction of 18F-FDG Positron Emission Tomography (PET) images through the generation of standard scan duration images using a multi-slice cycle-consistent Generative Adversarial Network (cycle-GAN) was studied. Also, the effect of the image augmentation methods on the performance of the cycle-GAN model was evaluated.
Materials and Methods: Four subsets of standard and 32-time short scan duration PET image pairs, each contacting image data of 10 patients were used to train and test (80 percent for training and 20 percent for testing) a multi-slice cycle-GAN separately. Another patient’s image data was used as the validation dataset for different training subsets. When training the cycle-GAN model for each subset, two approaches were followed: with and without image augmentation. Common image quality metrics of PSNR, SSIM, and NRMSE were used to assess the generation performance of the cycle-GAN model. Paired sample t-test statistical testing with a confidence interval of 0.95 was used to determine whether the differences between approaches were statistically significant or not.
Results: For subsets 1-3, both training approaches improved the image quality of the short scan duration inputs (p<0.001) while for subset 4 only the training approach with image augmentation was capable of improving the image quality. However, the training approach with image augmentation offered better results than the approach without image augmentation (p<0.001).
Conclusion: Employing the training approach with image augmentation, the cycle-GAN model was capable of improving the image quality of 1/32nd short scan duration images through the generation of synthetic standard scan duration images. In the case of the training approach without image augmentation, except for subset 4, the model trained on all subsets 1-3 was capable of improving the image quality. Image augmentation does indeed improve the performance of the cycle-GAN model, especially in the case of insufficient available training datasets.
2- Roger N Gunn, Mark Slifstein, Graham E Searle, and Julie C Price, "Quantitative imaging of protein targets in the human brain with PET." Physics in Medicine & Biology, Vol. 60 (No. 22), p. R363, (2015).
3- Josef Machac, "Cardiac positron emission tomography imaging." in Seminars in nuclear medicine, (2005), Vol. 35 (No. 1): Elsevier, pp. 17-36.
4- Hengzhi Xue et al., "LCPR-Net: low-count PET image reconstruction using the domain transform and cycle-consistent generative adversarial networks." Quantitative Imaging in Medicine and Surgery, Vol. 11 (No. 2), p. 749, (2021).
5- Junichi Tsuchiya et al., "Deep learning-based image quality improvement of 18F-fluorodeoxyglucose positron emission tomography: a retrospective observational study." EJNMMI physics, Vol. 8 (No. 1), pp. 1-12, (2021).
6- Richard L. Wagner Henry N. Ovid Technologies Inc Wahl, "Principles and practice of PET and PET/CT." (in English), (2009).
7- Nicolas A Karakatsanis, Eleni Fokou, and Charalampos Tsoumpas, "Dosage optimization in positron emission tomography: state-of-the-art methods and future prospects." American journal of nuclear medicine and molecular imaging, Vol. 5 (No. 5), p. 527, (2015).
8- Soo Mee Kim, Adam M Alessio, Bruno De Man, and Paul E Kinahan, "Direct Reconstruction of CT-Based Attenuation Correction Images for PET With Cluster-Based Penalties." IEEE transactions on nuclear science, Vol. 64 (No. 3), pp. 959-68, (2017).
9- Azar Amir Sorayaie et al., "Covidense: Providing a Suitable Solution for Diagnosing Covid-19 Lung Infection Based on Deep Learning from Chest X-Ray Images of Patients." (2021).
10- Motonori Akagi et al., "Deep learning reconstruction improves image quality of abdominal ultra-high-resolution CT." European radiology, Vol. 29 (No. 11), pp. 6163-71, (2019).
11- Kuang Gong, Jiahui Guan, Chih-Chieh Liu, and Jinyi Qi, "PET image denoising using a deep neural network through fine tuning." IEEE Transactions on Radiation and Plasma Medical Sciences, Vol. 3 (No. 2), pp. 153-61, (2018).
12- Andreas Hauptmann, Simon Arridge, Felix Lucka, Vivek Muthurangu, and Jennifer A Steeden, "Real‐time cardiovascular MR with spatio‐temporal artifact suppression using deep learning–proof of concept in congenital heart disease." Magnetic resonance in medicine, Vol. 81 (No. 2), pp. 1143-56, (2019).
13- Zhanli Hu et al., "Obtaining PET/CT images from non-attenuation corrected PET images in a single PET system using Wasserstein generative adversarial networks." Physics in Medicine & Biology, Vol. 65 (No. 21), p. 215010, (2020).
14- Zhanli Hu et al., "DPIR-Net: Direct PET image reconstruction based on the Wasserstein generative adversarial network." IEEE Transactions on Radiation and Plasma Medical Sciences, Vol. 5 (No. 1), pp. 35-43, (2020).
15- Masafumi Kidoh et al., "Deep learning based noise reduction for brain MR imaging: tests on phantoms and healthy volunteers." Magnetic Resonance in Medical Sciences, Vol. 19 (No. 3), p. 195, (2020).
16- Juan Liu, Masoud Malekzadeh, Niloufar Mirian, Tzu-An Song, Chi Liu, and Joyita Dutta, "Artificial intelligence-based image enhancement in pet imaging: Noise reduction and resolution enhancement." PET clinics, Vol. 16 (No. 4), pp. 553-76, (2021).
17- Fuminari Tatsugami et al., "Deep learning–based image restoration algorithm for coronary CT angiography." European radiology, Vol. 29 (No. 10), pp. 5322-29, (2019).
18- Ge Wang, "A perspective on deep imaging." IEEE access, Vol. 4pp. 8914-24, (2016).
19- Junshen Xu, Enhao Gong, John Pauly, and Greg Zaharchuk, "200x low-dose PET reconstruction using deep learning." arXiv preprint arXiv:1712.04119, (2017).
20- Qiyang Zhang et al., "PET image reconstruction using a cascading back-projection neural network." IEEE Journal of Selected Topics in Signal Processing, Vol. 14 (No. 6), pp. 1100-11, (2020).
21- Kui Zhao et al., "Study of low-dose PET image recovery using supervised learning with CycleGAN." Plos one, Vol. 15 (No. 9), p. e0238455, (2020).
22- Ian Goodfellow et al., "Generative adversarial nets." Advances in neural information processing systems, Vol. 27(2014).
23- Jyoti Islam and Yanqing Zhang, "GAN-based synthetic brain PET image generation." Brain informatics, Vol. 7 (No. 1), pp. 1-12, (2020).
24- Young Jin Jeong et al., "Restoration of amyloid PET images obtained with short-time data using a generative adversarial networks framework." Scientific reports, Vol. 11 (No. 1), pp. 1-11, (2021).
25- Jiahong Ouyang, Kevin T Chen, Enhao Gong, John Pauly, and Greg Zaharchuk, "Ultra‐low‐dose PET reconstruction using generative adversarial network with feature matching and task‐specific perceptual loss." Medical physics, Vol. 46 (No. 8), pp. 3555-64, (2019).
26- Amirhossein Sanaat, Isaac Shiri, Hossein Arabi, Ismini Mainta, René Nkoulou, and Habib Zaidi, "Deep learning-assisted ultra-fast/low-dose whole-body PET/CT imaging." European journal of nuclear medicine and molecular imaging, Vol. 48 (No. 8), pp. 2405-15, (2021).
27- Yan-Ran Joyce Wang et al., "Artificial intelligence enables whole-body positron emission tomography scans with minimal radiation exposure." European journal of nuclear medicine and molecular imaging, Vol. 48 (No. 9), pp. 2771-81, (2021).
28- Long Zhou, Joshua D Schaefferkoetter, Ivan WK Tham, Gang Huang, and Jianhua Yan, "Supervised learning with cyclegan for low-dose FDG PET image denoising." Medical image analysis, Vol. 65p. 101770, (2020).
29- Yang Lei et al., "Whole-body PET estimation from low count statistics using cycle-consistent generative adversarial networks." Physics in Medicine & Biology, Vol. 64 (No. 21), p. 215017, (2019).
30- Eunhee Kang, Hyun Jung Koo, Dong Hyun Yang, Joon Bum Seo, and Jong Chul Ye, "Cycle‐consistent adversarial denoising network for multiphase coronary CT angiography." Medical physics, Vol. 46 (No. 2), pp. 550-62, (2019).
31- Jun-Yan Zhu, Taesung Park, Phillip Isola, and Alexei A Efros, "Unpaired image-to-image translation using cycle-consistent adversarial networks." in Proceedings of the IEEE international conference on computer vision, (2017), pp. 2223-32.
32- Zhou Wang, Alan C Bovik, Hamid R Sheikh, and Eero P Simoncelli, "Image quality assessment: from error measurement to structural similarity." IEEE transactions on image processing, Vol. 13 (No. 1), (2004).
| Files | ||
| Issue | Vol 10 No 2 (2023) | |
| Section | Original Article(s) | |
| DOI | https://doi.org/10.18502/fbt.v10i2.12224 | |
| Keywords | ||
| Image Augmentation 18F-Fluorodeoxyglucose Positron Emission Tomography Deep Learning | ||
| Rights and permissions | |
|
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
