Abstract
Objective
Recently, generative adversarial networks began to be actively studied in the field of medical imaging. These models are used for augmenting the variation of images to improve the accuracy of computer-aided diagnosis. In this paper, we propose an alternative new image generative model based on transformer decoder blocks and verify the performance of our model in generating SPECT images that have characteristics of Parkinson’s disease patients.
Methods
Firstly, we proposed a new model architecture that is based on a transformer decoder block and is extended to generate slice images. From few superior slices of 3D volume, our model generates the rest of the inferior slices sequentially. Our model was trained by using [123I]FP-CIT SPECT images of Parkinson's disease patients that originated from the Parkinson’s Progression Marker Initiative database. Pixel values of SPECT images were normalized by the specific/nonspecific binding ratio (SNBR). After training the model, we generated [123I]FP-CIT SPECT images. The transformation of images of the healthy control case SPECT images into PD-like images was also performed. Generated images were visually inspected and evaluated using the mean absolute value and asymmetric index.
Results
Our model was successfully generated and transformed into PD-like SPECT images. The mean absolute SNBR was mostly less than 0.15 in absolute value. The variation of the obtained dataset images was confirmed by the analysis of the asymmetric index.
Conclusions
These results showed the potential ability of our new generative approach for SPECT images that the generative model based on the transformer realized both generation and transformation by a single model.
Similar content being viewed by others
Change history
06 January 2022
A Correction to this paper has been published: https://doi.org/10.1007/s12149-021-01714-4
References
Goodfellow Ian J, Pouget-Abadie J, Mirza M, Bing Xu, Warde-Farley D, Ozair S, et al. Generative adversarial nets. Adv Neural Inf Process Syst. 2014;3:2672–80.
Radford A, Metz L, and Chintal S. Unsupervised representation learning with deep convolutional generative adversarial networks. (2015).arXiv:1511.06434
Onishi Y, Teramoto A, Tsujimoto M, Tsukamoto T, Saito K, Toyama H, et al. Automated pulmonary nodule classification in computed tomography images using a deep convolutional neural network trained by generative adversarial networks. BioMed Red Int. 2019. https://doi.org/10.1155/2019/6051939.
Koshino K, Werner Rudolf A, Toriumi F, Javadi Mehrbod S, Pomper Martin G, Solnes Lilja B, et al. Generative adversarial networks for the creation of realistic artificial brain magnetic resonance images. Tomography. 2018;4(4):159.
Islam J, Zhang Y. GAN-based synthetic brain PET image generation. Brain Inform. 2020;7:1–12.
Frid-Adar M, Diamant I, Klang E, Amitai M, Goldberger J, Greenspan H. GAN-based synthetic medical image augmentation for increased CNN performance in liver lesion classification. Neurocomputing. 2018;321:321–31.
Mirza M and Osindero S. Conditional generative adversarial nets. (2014). arXiv:1411.1784
Zhu J-Y, Park T, Isola P, Efros AA. Unpaired image-to-image translation using cycle-consistent adversarial networks. IEEE international conference on computer vision, 2017. p. 2223–2232.
Xia T, Chartsias A, Tsaftaris SA. Consistent brain ageing synthesis. In: Medical image computing and computer-assisted intervention. Champaign: Springer; 2019. p. 750–758.
Ronneberger O, Fischer P, and Brox T. U-Net: convolutional networks for biomedical image segmentation. In: Medical image computing and computer-assisted intervention. Champaign: Springer; 2015. p. 234–241.
Kimura Y, Watanabe A, Yamada T, Watanabe S, Nagaoka T, Nemoto M, et al. AI approach of cycle-consistent generative adversarial networks to synthesize PET images to train computer-aided diagnosis algorithm for dementia. Ann Nucl Med. 2020. https://doi.org/10.1007/s12149-020-01468-5.
Wei J, Suriawinata A, Vaickus L, Ren Bing, Liu X, Wei J, et al. Generative Image Translation for Data Augmentation in Colorectal Histopathology Images. (2019). arXiv:1910.05827
Liyan S, Wang J, Huang Y, Ding X, Greenspan H, Paisley J (2020) An adversarial learning approach to medical image synthesis for lesion detection. IEEE J Biomed Health Inform 4: 2303–2314
Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez A N, et al. Attention is all you need. In: Advances in neural information processing systems. 2017. p. 5998–6008.
Cornia M, Stefanini M, Baraldi L, and Cucchiara R. Meshed-memory transformer for image captioning. In: Proceedings of the EEE Computer Society conference on computer vision and pattern recognition. 2020. p. 10578–10587.
Girdhar R, Carreira J, Doersch C, Zisserman A. Video action transformer network. In: Proceedings of the IEEE Computer Society conference on computer vision and pattern recognition. 2019. p. 244–253
Carion N, Massa F, Synnaeve G, Usunier N, Kirillov A, and Zagoruyko S. End-to-end object detection with transformers. (2020). arXiv:2005.12872
Parmar N, Vaswani A, Uszkoreit J, Kaiser Ł, Shazeer N, Ku A, et al. Image transformer. (2018). arXiv:1802.05751
Chen M, Radford A, Child R, Wu J, Jun H, Luan D, et al. Generative pretraining from pixels. In: Proceedings of the 37th international conference on machine learning. 2020.
Radford A, Wu J, Child R, Luan D, Amodei D, Sutskever I. Language models are unsupervised multitask learners. OpenAI Blog. 2019;1(8):9.
Devlin J, Chang M-W, Lee K, Toutanova K. BERT: pre-training of deep bidirectional transformers for language understanding. (2018). arXiv:1810.04805
Fragkiadaki K, Agrawal P, Levine S, and Malik J. Learning visual predictive models of physics for playing billiards. (2015). arXiv:1511.07404
Lotter W, Kreiman G, and Cox D. Deep predictive coding networks for video prediction and unsupervised learning. (2016). arXiv:1605.08104
Marek K, Jennings D, Lasch S, Siderowf A, Tanner C, Simuni T, et al. The parkinson progression marker initiative (PPMI). Prog Neurobiol. 2011;95:629–35.
Tossici-Bolt L, Hoffmann SMA, Kemp PM, Mehta RL, Fleming JS. Quantification of [123I]FP-CIT SPECT brain images: an accurate technique for measurement of the specific binding ratio. Eur Img J Nucl Med Mol. 2006;33:1491–9.
Xiong R, Yang Y, He D, Zheng K, Zheng S, Xing C, et al. On layer normalization in the transformer architecture. (2020). arXiv:2002.04745
Ba JL, Kiros JR, Hinton GE. Layer normalization. (2016). arXiv:1607.06450
Diganta M. Mish: A self regularized non-monotonic neural activation function. (2019). arXiv:1908.08681
Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R. Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res. 2014;15(1):1929–58.
Clevert D-A, Unterthiner T, and Hochreiter S. Fast and accurate deep network learning by exponential linear units (ELUs). (2015). arXiv:1511.07289
Kingma DP, Ba JL. Adam: a method for stochastic optimization. 2014. arXiv:1412.6980
Smith LN. Cyclical learning rates for training neural networks. In: IEEE winter conference on applications of computer vision. 2017. p. 464–472
Seide F, Agarwal A. CNTK: Microsoft's open-source deep-learning toolkit. In: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining. 2016. p. 2135–2135
Hayashi T, Mishina M, Sakamaki M, Sakamoto Y, Suda S, Kimura K. Effect of brain atrophy in quantitative analysis of 123I iofupane SPECT. Ann Nucl Med. 2019;33(8):579–85.
Acknowledgements
The data we used in training and validation in this study were obtained from the Parkinson’s Progression Marker Initiative (PPMI) database (https://www.ppmi-info.org/data). PPMI—a public private partnership—was funded by the Michael J. Fox Foundation for Parkinson’s Research and funding partners, including Abbvie, Avid, Biogen Idec, Bristol-Myers Squibb, Covance, GE Healthcare, Genentech, GlaxoSmithKline, Lilly, Lundbeck, Merck, Meso Scale Discovery, Pfizer, Piramal, Roche, and UCB.
The authors thank professor Nobukatsu Sawamoto (MD, neurologist) and Associate professor Koichi Ishizu (MD, radiologist) for reviewing generated SPECT images. Both belong to the Graduate School of Medicine, Kyoto University.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Watanabe, S., Ueno, T., Kimura, Y. et al. Generative image transformer (GIT): unsupervised continuous image generative and transformable model for [123I]FP-CIT SPECT images. Ann Nucl Med 35, 1203–1213 (2021). https://doi.org/10.1007/s12149-021-01661-0
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12149-021-01661-0