Abstract
Synthesis of images has recently seen many works that produce high-quality real world images. In the domain of medical imaging the application of deep generative models especially Generative Adversarial Networks (GANs) can be applied to many different tasks. Under the premise of the generation of high-quality images that match the distribution of the original data, the synthesized data can be used to increase the size of small datasets, or in combination with conditioning on meta data, to increase the size of underrepresented classes in the dataset. In this work we propose a model that generates 3D medical images. The model can easily be conditioned on meta data, for example available patient information. We evaluate the quality of the generated images and compare our model against the 3D-StyleGAN model which is also designed for 3D medical image synthesis.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Bamberg, F., et al.: Whole-body MR imaging in the German national cohort: rationale, design, and technical background. Radiology 277(1), 206–220 (2015)
Bergen, R.V., Rajotte, J.F., Yousefirizi, F., Klyuzhin, I.S., Rahmim, A., Ng, R.T.: 3D PET image generation with tumour masks using TGAN. In: Medical Imaging 2022: Image Processing, vol. 12032, p. 120321P (2022). https://doi.org/10.1117/12.2611292
Dauphin, Y.N., Fan, A., Auli, M., Grangier, D.: Language modeling with gated convolutional networks. arXiv (2016)
Feng, R., Zhao, D., Zha, Z.: On noise injection in generative adversarial networks. arXiv (2020)
Granstedt, J.L., Kelkar, V.A., Zhou, W., Anastasio, M.A.: SlabGAN: a method for generating efficient 3D anisotropic medical volumes using generative adversarial networks. In: Medical Imaging 2021: Image Processing, vol. 11596, p. 1159617 (2021). https://doi.org/10.1117/12.2581380
Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local Nash equilibrium. arXiv (2017)
Hong, S., et al.: 3D-StyleGAN: a style-based generative adversarial network for generative modeling of three-dimensional medical images. arXiv (2021)
Karras, T., Aittala, M., Hellsten, J., Laine, S., Lehtinen, J., Aila, T.: Training generative adversarial networks with limited data. arXiv (2020)
Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. arXiv (2018)
Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., Aila, T.: Analyzing and improving the image quality of StyleGAN. arXiv (2019)
Kwon, G., Han, C., Kim, D.S.: Generation of 3D brain MRI using auto-encoding generative adversarial networks. arXiv (2019)
Lemay, A., Gros, C., Vincent, O., Liu, Y., Cohen, J.P., Cohen-Adad, J.: Benefits of linear conditioning with metadata for image segmentation. arXiv (2021)
Lim, J.H., Ye, J.C.: Geometric GAN (2017). https://doi.org/10.48550/ARXIV.1705.02894, https://arxiv.org/abs/1705.02894
Liu, B., Zhu, Y., Song, K., Elgammal, A.: Towards faster and stabilized GAN training for high-fidelity few-shot image synthesis. arXiv (2021)
Perez, E., Strub, F., Vries, H.D., Dumoulin, V., Courville, A.: FiLM: visual reasoning with a general conditioning layer. arXiv (2017)
Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv (2015)
Ulyanov, D., Vedaldi, A., Lempitsky, V.S.: Instance normalization: The missing ingredient for fast stylization. CoRR abs/1607.08022 (2016), http://arxiv.org/abs/1607.08022
Volokitin, A., et al.: Modelling the distribution of 3D brain MRI using a 2D slice VAE. arXiv (2020)
Yazıcı, Y., Foo, C.S., Winkler, S., Yap, K.H., Piliouras, G., Chandrasekhar, V.: The unusual effectiveness of averaging in GAN training. arXiv (2018)
Acknowledgement
We received grant money from the U Bremen Research Alliance/AI Center for Health Care, financially supported by the Federal State of Bremen.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Mensing, D., Hirsch, J., Wenzel, M., Günther, M. (2022). 3D (c)GAN for Whole Body MR Synthesis. In: Mukhopadhyay, A., Oksuz, I., Engelhardt, S., Zhu, D., Yuan, Y. (eds) Deep Generative Models. DGM4MICCAI 2022. Lecture Notes in Computer Science, vol 13609. Springer, Cham. https://doi.org/10.1007/978-3-031-18576-2_10
Download citation
DOI: https://doi.org/10.1007/978-3-031-18576-2_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-18575-5
Online ISBN: 978-3-031-18576-2
eBook Packages: Computer ScienceComputer Science (R0)
