Skip to content
Licensed Unlicensed Requires Authentication Published by De Gruyter March 26, 2021

A data and knowledge driven approach for SPECT using convolutional neural networks and iterative algorithms

  • Wenqi Ao , Wenbin Li EMAIL logo and Jianliang Qian

Abstract

We propose a data and knowledge driven approach for SPECT by combining a classical iterative algorithm of SPECT with a convolutional neural network. The classical iterative algorithm, such as ART and ML-EM, is employed to provide the model knowledge of SPECT. A modified U-net is then connected to exploit further features of reconstructed images and data sinograms of SPECT. We provide mathematical formulations for the architecture of the proposed networks. The networks are trained by supervised learning using the technique of mini-batch optimization. We apply the trained networks to the problems of simulated lung perfusion imaging and simulated myocardial perfusion imaging, and numerical results demonstrate their effectiveness of reconstructing source images from noisy data measurements.

MSC 2010: 65R32; 92C55

Award Identifier / Grant number: 41804096

Award Identifier / Grant number: 2018A030313341

Award Identifier / Grant number: JCYJ20190806144005645

Funding statement: Wenbin Li is supported by NSFC (grant no. 41804096), Natural Science Foundation of Guangdong Province (grant no. 2018A030313341), and Natural Science Foundation of Shenzhen (grant no. JCYJ20190806144005645). Qian’s research is partially supported by NSF.

References

[1] J. Adler and O. Öktem, Solving ill-posed inverse problems using iterative deep neural networks, Inverse Problems 33 (2017), no. 12, Article ID 124007. 10.1088/1361-6420/aa9581Search in Google Scholar

[2] J. Adler and O. Öktem, Learned primal-dual reconstruction, IEEE Trans. Med. Imag. 37 (2018), no. 6, 1322–1332. 10.1109/TMI.2018.2799231Search in Google Scholar

[3] E. V. Arbuzov, A. L. Bukhgeĭm and S. G. Kazantsev, Two-dimensional tomography problems and the theory of 𝐴-analytic functions, Siberian Adv. Math. 8 (1998), no. 4, 1–20. Search in Google Scholar

[4] A. Beck and M. Teboulle, A fast iterative shrinkage-thresholding algorithm for linear inverse problems, SIAM J. Imaging Sci. 2 (2009), no. 1, 183–202. 10.1137/080716542Search in Google Scholar

[5] J. Brownlee, A gentle introduction to mini-batch gradient descent and how to configure batch size, preprint (2017), https://machinelearningmastery.com/gentle-introduction-mini-batch-gradient-descent-configure-batch-size/. Search in Google Scholar

[6] L.-C. Chen, G. Papandreou, I. Kokkinos, K. Murphy and A. L. Yuille, Semantic image segmentation with deep convolutional nets and fully connected crfs, preprint (2014), https://arxiv.org/abs/1412.7062. Search in Google Scholar

[7] M. M. A. Dietze, W. Branderhorst, B. Kunnen, M. A. Viergever and H. W. A. M. de Jong, Accelerated SPECT image reconstruction with FBP and an image enhancement convolutional neural network, EJNMMI Phys. 6 (2019), Paper No. 14. 10.1186/s40658-019-0252-0Search in Google Scholar

[8] D. V. Finch, The attenuated x-ray transform: recent developments, Inside Out: Inverse Problems and Applications, Math. Sci. Res. Inst. Publ. 47, Cambridge University, Cambridge (2003), 47–66. Search in Google Scholar

[9] R. Gordon, R. Bender and G. T. Herman, Algebraic reconstruction techniques (ART) for three-dimensional electron microscopy and X-ray photography, J. Theoret. Biol. 29 (1970), no. 3, 471–481. 10.1016/0022-5193(70)90109-8Search in Google Scholar

[10] K. He, X. Zhang, S. Ren and J. Sun, Deep residual learning for image recognition, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, IEEE Press, Piscataway (2016), 770–778. 10.1109/CVPR.2016.90Search in Google Scholar

[11] H. M. Hudson and R. S. Larkin, Accelerated image reconstruction using ordered subsets of projection data, IEEE Trans. Med. Imag. 13 (1994), no. 4, 601–609. 10.1109/42.363108Search in Google Scholar PubMed

[12] S. Ioffe and C. Szegedy, Batch normalization: Accelerating deep network training by reducing internal covariate shift, preprint (2015), https://arxiv.org/abs/1502.03167. Search in Google Scholar

[13] K. H. Jin, M. T. McCann, E. Froustey and M. Unser, Deep convolutional neural network for inverse problems in imaging, IEEE Trans. Image Process. 26 (2017), no. 9, 4509–4522. 10.1109/TIP.2017.2713099Search in Google Scholar PubMed

[14] D. P. Kingma and J. Ba, Adam: A method for stochastic optimization, preprint (2014), https://arxiv.org/abs/1412.6980. Search in Google Scholar

[15] A. Krizhevsky, I. Sutskever and G. E. Hinton, Imagenet classification with deep convolutional neural networks, Advances in Neural Information Processing Systems, Springer, New York (2012), 1097–1105. 10.1145/3065386Search in Google Scholar

[16] D. S. Lalush and B. M. W. Tsui, A generalized gibbs prior for maximum a posteriori reconstruction in SPECT, Phys. Med. Biol. 38 (1993), no. 6, Paper No. 729. 10.1088/0031-9155/38/6/007Search in Google Scholar PubMed

[17] S. Luo, J. Qian and P. Stefanov, Adjoint state method for the identification problem in SPECT: Recovery of both the source and the attenuation in the attenuated X-ray transform, SIAM J. Imaging Sci. 7 (2014), no. 2, 696–715. 10.1137/130939559Search in Google Scholar

[18] R. G. Novikov, An inversion formula for the attenuated X-ray transformation, Ark. Mat. 40 (2002), no. 1, 145–167. 10.1007/BF02384507Search in Google Scholar

[19] O. Ronneberger, P. Fischer and T. Brox, U-net: Convolutional networks for biomedical image segmentation, International Conference on Medical Image Computing and Computer-Assisted Intervention, Springer, Cham (2015), 234–241. 10.1007/978-3-319-24574-4_28Search in Google Scholar

[20] O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla and M. Bernstein, Imagenet large scale visual recognition challenge, Int. J. Comput. Vis. 115 (2015), no. 3, 211–252. 10.1007/s11263-015-0816-ySearch in Google Scholar

[21] L. A. Shepp and Y. Vardi, Maximum likelihood reconstruction for emission tomography, IEEE Trans. Med. Imag. 1 (1982), no. 2, 113–122. 10.1109/TMI.1982.4307558Search in Google Scholar PubMed

[22] D. Strong and T. Chan, Edge-preserving and scale-dependent properties of total variation regularization, Inverse Problems 19 (2003), no. 6, S165–S187. 10.1088/0266-5611/19/6/059Search in Google Scholar

[23] B. Wahlberg, S. Boyd, M. Annergren and Y. Wang, An ADMM algorithm for a class of total variation regularized estimation problems, IFAC Proc. 45 (2012), no. 16, 83–88. 10.3182/20120711-3-BE-2027.00310Search in Google Scholar

[24] X. Zhang, M. Burger and S. Osher, A unified primal-dual algorithm framework based on Bregman iteration, J. Sci. Comput. 46 (2011), no. 1, 20–46. 10.1007/s10915-010-9408-8Search in Google Scholar

Received: 2020-05-17
Accepted: 2021-01-03
Published Online: 2021-03-26
Published in Print: 2021-08-01

© 2021 Walter de Gruyter GmbH, Berlin/Boston

Downloaded on 29.3.2024 from https://www.degruyter.com/document/doi/10.1515/jiip-2020-0056/html
Scroll to top button