Skip to main content
SpringerLink
Log in

RecDNN: deep neural network for image reconstruction from limited view projection data

  • Methodologies and Application
  • Published:
Soft Computing Aims and scope Submit manuscript

Abstract

Improving the quality of reconstruction, even in a limited projection view, has become one of the prime objectives in computed tomography. Projection data over 180\(^{\circ }\) are always not practicable in many practical applications including medical imaging. Iterative approaches, such as algebraic reconstruction techniques (ART), are useful in the limited view scenarios; however, these approaches resulted in the streaking artifacts. Deep learning has paved a path to achieve high efficiency and accuracy for reconstruction with limited view projection data. Convolutional neural networks such as U-Net, residual neural networks and adversarial neural networks are being widely used for image reconstruction. U-Net and residual neural network for limited projection views have been found compute intensive and also produces a noisy image. The convergence of the adversarial neural network in case of the inverse problem is very slow; hence, the training is compute intensive. A deep neural network for image reconstruction (RecDNN) is proposed in this manuscript for a limited view case. The proposed architecture is designed to give reconstruction with minimal artifacts. The objective is to give a good quality of textural and contrast information about the reconstructed object. The image reconstruction has been addressed as inverse problem as well as optimization problem. The stochastic gradient method is applied to achieve image reconstruction. The proposed approach has been compared to the traditional transform-based approaches as well as the current deep learning methods for image reconstruction. Experimental results show that the proposed architecture is performing better than the existing approaches, as well as the state-of-the-art architectures available for image reconstruction. Experimental results also show that for the same number of projection views, the proposed architecture reconstructs the object with higher quality as compared to existing architectures for image reconstruction.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14

Similar content being viewed by others

References

  • Andersen AH, Kak AC (1984) Simultaneous algebraic reconstruction technique (sart): a superior implementation of the art algorithm. Ultrason Imaging 6(1):81–94

    Google Scholar 

  • Bajpai M, Gupta P, Munshi P, Titarenko V, Withers P (2013a) A graphical processing unit-based parallel implementation of multiplicative algebraic reconstruction technique algorithm for limited view tomography. Res Nondestruct Eval 24(4):211–222

    Google Scholar 

  • Bajpai M, Schorr C, Maisl M, Gupta P, Munshi P (2013b) High resolution 3d image reconstruction using the algebraic method for cone-beam geometry over circular and helical trajectories. NDT E Int 60:62–69

    Google Scholar 

  • Bajpai M, Gupta P, Munshi P (2015) Fast multi-processor multi-gpu based algorithm of tomographic inversion for 3d image reconstruction. Int J Perform Comput Appl 29(1):64–72

    Google Scholar 

  • Bansal S (2019) A comparative study of nature-inspired metaheuristic algorithms in search of near-to-optimal golomb rulers for the fwm crosstalk elimination in wdm systems. Appl Artif Intell 33(14):1199–1265

    Google Scholar 

  • Bansal S, Gupta N, Singh AK (2017) Nature-inspired metaheuristic algorithms to find near-ogr sequences for wdm channel allocation and their performance comparison. Open Math 15(1):520–547

    MathSciNet  MATH  Google Scholar 

  • Bara N, Murata K (1981) Maximum entropy image reconstruction from projections. Opt Commun 38(2):91–95

    Google Scholar 

  • Boublil D, Elad M, Shtok J, Zibulevsky M (2015) Spatially-adaptive reconstruction in computed tomography using neural networks. IEEE Trans Med Imag 34(7):1474–1485

    Google Scholar 

  • Chen H, Zhang Y, Kalra MK, Lin F, Chen Y, Liao P, Zhou J, Wang G (2017) Low-dose ct with a residual encoder-decoder convolutional neural network. IEEE Trans Med Imaging 36(12):2524–2535

    Google Scholar 

  • Chen Y, Yu F, Luo L, Toumoulin C (2013) Improving abdomen tumor low-dose ct images using dictionary learning based patch processing and unsharp filtering. In: 2013 35th annual international conference of the ieee engineering in medicine and biology society (EMBC), IEEE, pp 4014–4017

  • Chen Y, Shi L, Feng Q, Yang J, Shu H, Luo L, Coatrieux JL, Chen W (2014) Artifact suppressed dictionary learning for low-dose ct image processing. IEEE Trans Med Imaging 33(12):2271–2292

    Google Scholar 

  • Chollet F (2018) Deep learning mit python und keras: das praxis-handbuch vom entwickler der keras-bibliothek. MITP-Verlags GmbH & Co, KG

    Google Scholar 

  • Dai X, Shu H, Luo L, Han GN, Coatrieux JL (2010) Reconstruction of tomographic images from limited range projections using discrete radon transform and tchebichef moments. Pattern Recognit 43(3):1152–1164

    MATH  Google Scholar 

  • Gilbert P (1972) Iterative methods for the three-dimensional reconstruction of an object from projections. J Theor Biol 36(1):105–117

    Article  Google Scholar 

  • Glorot X, Bengio Y (2010) Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the thirteenth international conference on artificial intelligence and statistics, pp 249–256

  • Gordon R (1974) A tutorial on art (algebraic reconstruction techniques). IEEE Trans Nucl Sci 21(3):78–93

    Article  Google Scholar 

  • Gordon R, Bender R, Herman GT (1970) Algebraic reconstruction techniques (art) for three-dimensional electron microscopy and x-ray photography. J Theor Biol 29(3):471–481

    Article  Google Scholar 

  • Gowthami S, Harikumar R (2020) Conventional neural network for blind image blur correction using latent semantics. Soft Comput 1–15

  • Gürsoy D, De Carlo F, Xiao X, Jacobsen C (2014) Tomopy: a framework for the analysis of synchrotron tomographic data. J Synch Radiat 21(5):1188–1193

    Article  Google Scholar 

  • Häggström I, Schmidtlein CR, Campanella G, Fuchs TJ (2019) Deeppet: a deep encoder-decoder network for directly solving the pet image reconstruction inverse problem. Med Image Anal 54:253–262

    Google Scholar 

  • Herman GT (2009) Fundamentals of computerized tomography: image reconstruction from projections. Springer, Berlin

    MATH  Google Scholar 

  • Hyun CM, Kim HP, Lee SM, Lee S, Seo JK (2018) Deep learning for undersampled mri reconstruction. Phys Med Biol 63(13):135007

    Google Scholar 

  • Jin KH, McCann MT, Froustey E, Unser M (2017) Deep convolutional neural network for inverse problems in imaging. IEEE Trans Image Process 26(9):4509–4522

    MathSciNet  MATH  Google Scholar 

  • LeCun YA, Bottou L, Orr GB, Müller KR (2012) Efficient backprop. In: Neural networks: tricks of the trade, Springer, pp 9–48

  • Natterer F, Wübbeling F (2001) Mathematical methods in image reconstruction, vol 5. SIAM, New Delhi

    MATH  Google Scholar 

  • Pelt DM, Batenburg KJ (2013) Fast tomographic reconstruction from limited data using artificial neural networks. IEEE Trans Image Process 22(12):5238–5251

    Google Scholar 

  • Ronneberger O, Fischer P, Brox T (2015) U-net: convolutional networks for biomedical image segmentation. In: International conference on medical image computing and computer-assisted intervention, Springer, pp 234–241

  • Schlemper J, Caballero J, Hajnal JV, Price AN, Rueckert D (2017) A deep cascade of convolutional neural networks for dynamic mr image reconstruction. IEEE Trans Med Imaging 37(2):491–503

    Google Scholar 

  • Shan H, Zhang Y, Yang Q, Kruger U, Kalra MK, Sun L, Cong W, Wang G (2018) 3-d convolutional encoder-decoder network for low-dose ct via transfer learning from a 2-d trained network. IEEE Trans Med Imaging 37(6):1522–1534

    Google Scholar 

  • Shu H, Zhou J, Han GN, Luo LM, Coatrieux JL (2007) Image reconstruction from limited range projections using orthogonal moments. Pattern Recognit 40(2):670–680

    MATH  Google Scholar 

  • Sun Y, Zhang X, Jian M, Wang S, Wu Z, Su Q, Chen B (2018) An improved genetic algorithm for three-dimensional reconstruction from a single uniform texture image. Soft Comput 22(2):477–486

    Google Scholar 

  • Wang TJ, Sze T (2001) The image moment method for the limited range ct image reconstruction and pattern recognition. Pattern Recognit 34(11):2145–2154

    MATH  Google Scholar 

  • Wolterink JM, Leiner T, Viergever MA, Išgum I (2017) Generative adversarial networks for noise reduction in low-dose ct. IEEE Trans Med Imaging 36(12):2536–2545

    Google Scholar 

  • Würfl T, Ghesu FC, Christlein V, Maier A (2016) Deep learning computed tomography. In: International conference on medical image computing and computer-assisted intervention, Springer, pp 432–440

  • Yang Q, Yan P, Zhang Y, Yu H, Shi Y, Mou X, Kalra MK, Zhang Y, Sun L, Wang G (2018a) Low-dose ct image denoising using a generative adversarial network with wasserstein distance and perceptual loss. IEEE Trans Med Imaging 37(6):1348–1357

    Google Scholar 

  • Yang X, Wu W, Liu K, Chen W, Zhou Z (2018b) Multiple dictionary pairs learning and sparse representation-based infrared image super-resolution with improved fuzzy clustering. Soft Comput 22(5):1385–1398

    Google Scholar 

  • Yang Z, Chai Y, Chen T, Qu J (2017) Smoothed \({\ell }\_{1}\) regularization-based line search for sparse signal recovery. Soft Comput 21(16):4813–4828

    MATH  Google Scholar 

  • Yu H, Wang G (2010) A soft-threshold filtering approach for reconstruction from a limited number of projections. Phys Med Biol 55(13):3905

    Article  Google Scholar 

Download references

Acknowledgements

Ministry of Electronics and Information Technology (MEITY), Government of India, has supported this work under Visvesvaraya PhD scheme. The authors would like to thank MEITY for providing a PhD fellowship under Visvesvaraya PhD scheme.

Author information

Authors and Affiliations

  1. Computer Science and Engineering Discipline, Indian Institute of Information Technology Design and Manufacturing Jabalpur, Jabalpur, India

    Kailash Wamanrao Kalare & Manish Kumar Bajpai

Authors
  1. Kailash Wamanrao Kalare
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Manish Kumar Bajpai
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Kailash Wamanrao Kalare.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Additional information

Communicated by V. Loia.

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Kalare, K.W., Bajpai, M.K. RecDNN: deep neural network for image reconstruction from limited view projection data. Soft Comput 24, 17205–17220 (2020). https://doi.org/10.1007/s00500-020-05013-4

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00500-020-05013-4

Keywords

Search

Navigation