Abstract
Cardiovascular disease (CVD) is the leading cause of death worldwide, and myocardial perfusion imaging using SPECT has been widely used in the diagnosis of CVDs. The GE 530/570c dedicated cardiac SPECT scanners adopt a stationary geometry to simultaneously acquire 19 projections to increase sensitivity and achieve dynamic imaging. However, the limited amount of angular sampling negatively affects image quality. Deep learning methods can be implemented to produce higher-quality images from stationary data. This is essentially a few-view imaging problem. In this work, we propose a novel 3D transformer-based dual-domain network, called TIP-Net, for high-quality 3D cardiac SPECT image reconstructions. Our method aims to first reconstruct 3D cardiac SPECT images directly from projection data without the iterative reconstruction process by proposing a customized projection-to-image domain transformer. Then, given its reconstruction output and the original few-view reconstruction, we further refine the reconstruction using an image-domain reconstruction network. Validated by cardiac catheterization images, diagnostic interpretations from nuclear cardiologists, and defect size quantified by an FDA 510(k)-cleared clinical software, our method produced images with higher cardiac defect contrast on human studies compared with previous baseline methods, potentially enabling high-quality defect visualization using stationary few-view dedicated cardiac SPECT scanners.
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
References
Bocher, M., Blevis, I., Tsukerman, L., Shrem, Y., Kovalski, G., Volokh, L.: A fast cardiac gamma camera with dynamic SPECT capabilities: design, system validation and future potential. Eur. J. Nucl. Med. Mol. Imaging 37(10), 1887–1902 (2010). https://doi.org/10.1007/s00259-010-1488-z
Dosovitskiy, A., et al.: An image is worth 16 \(\times \) 16 words: transformers for image recognition at scale. arXiv:2010.11929 [cs], June 2021. http://arxiv.org/abs/2010.11929
Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: Teh, Y.W., Titterington, M. (eds.) Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics. Proceedings of Machine Learning Research, vol. 9, pp. 249–256. PMLR, Chia Laguna Resort, Sardinia, Italy, 13–15 May 2010 (2010). http://proceedings.mlr.press/v9/glorot10a.html
Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., Courville, A.: Improved training of Wasserstein GANs. In: Advances in Neural Information Processing Systems, vol. 30. Curran Associates, Inc. (2017)
He, J., Wang, Y., Ma, J.: Radon inversion via deep learning. IEEE Trans. Med. Imaging 39(6), 2076–2087 (2020). https://doi.org/10.1109/TMI.2020.2964266
Li, Y., Li, K., Zhang, C., Montoya, J., Chen, G.: Learning to reconstruct computed tomography (CT) images directly from sinogram data under a variety of data acquisition conditions. IEEE Trans. Med. Imaging 39, 2469–2481 (2019). https://doi.org/10.1109/TMI.2019.2910760
Liu, Y., Sinusas, A., DeMan, P., Zaret, B., Wackers, F.: Quantification of SPECT myocardial perfusion images: methodology and validation of the Yale-CQ method. J. Nucl. Cardiol. 6(2), 190–204 (1999). https://doi.org/10.1016/s1071-3581(99)90080-6
PK, D., B, J.: Adam: a method for stochastic optimization. In: 3rd International Conference on Learning Representations, ICLR 2015, Conference Track Proceedings, San Diego, CA, USA, 7–9 May 2015 (2015). http://arxiv.org/abs/1412.6980
Segars, W., Sturgeon, G., Mendonca, S., Grimes, J., Tsui, B.: 4D XCAT phantom for multimodality imaging research. Med. Phys. 37(9), 4902–4915 (2010). https://doi.org/10.1118/1.3480985. https://aapm.onlinelibrary.wiley.com/doi/abs/10.1118/1.3480985
Würfl, T., et al.: Deep learning computed tomography: learning projection-domain weights from image domain in limited angle problems. IEEE Trans. Med. Imaging 37(6), 1454–1463 (2018). https://doi.org/10.1109/TMI.2018.2833499
Xie, H., et al.: Deep efficient end-to-end reconstruction (DEER) network for few-view breast CT image reconstruction. IEEE Access 8, 196633–196646 (2020). https://doi.org/10.1109/ACCESS.2020.3033795
Xie, H., et al.: Increasing angular sampling through deep learning for stationary cardiac SPECT image reconstruction. J. Nucl. Cardiol. 30, 86–100 (2022). https://doi.org/10.1007/s12350-022-02972-z
Xie, H., et al.: Deep learning based few-angle cardiac SPECT reconstruction using transformer. IEEE Trans. Radiat. Plasma Med. Sci. 7, 33–40. https://doi.org/10.1109/TRPMS.2022.3187595
Zhu, B., Liu, J.Z., Cauley, S.F., Rosen, B.R., Rosen, M.S.: Image reconstruction by domain-transform manifold learning. Nature 555(7697), 487–492 (2018). https://doi.org/10.1038/nature25988
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Xie, H. et al. (2023). Transformer-Based Dual-Domain Network for Few-View Dedicated Cardiac SPECT Image Reconstructions. In: Greenspan, H., et al. Medical Image Computing and Computer Assisted Intervention – MICCAI 2023. MICCAI 2023. Lecture Notes in Computer Science, vol 14229. Springer, Cham. https://doi.org/10.1007/978-3-031-43999-5_16
Download citation
DOI: https://doi.org/10.1007/978-3-031-43999-5_16
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-43998-8
Online ISBN: 978-3-031-43999-5
eBook Packages: Computer ScienceComputer Science (R0)
