Skip to main content

Advertisement

Springer Nature Link
Log in

An Optimized MRI Contrast Enhancement Scheme Using Cycle Generative Adversarial Network

  • Original Research
  • Published:
SN Computer Science Aims and scope Submit manuscript

Abstract

The acquisition constraints in MRI images may affect the medical diagnosis and post-processing in the treatment, given to the patients. There is a need for enhancement in MRI images for the accurate diagnosis of disease. There are various image processing techniques available in the literature to enhance images for a particular optimization of a parameter. But such techniques not only fail to optimize all the parameters needed to enhance an image but also sometimes fail to preserve the edges. Therefore, to overcome such problems, one of the approaches is a machine learning-based network which helps to optimize all the parameters in one go. In this paper, a machine learning-based approach, based on Cycle Generative Adversarial Network is proposed to improve contrast of brain MRI images. The proposed model consists of two generators and a discriminator. The ‘Generator1’ maps the features of input image to corresponding high-contrast image. The generated image is passed to the discriminator for the classification. The ‘Generator 2’ reconstructs the input image back. It not only improves the information content by enhancing the contrast of MRI images but also preserves the necessary edges required for accurate diagnosis. In addition, the noise is easily removed while processing of images. We have derived the dataset of our own consisting of low- and high-contrast MRI images for training and testing purpose. This technique exhibits excellent results in comparison to other techniques available in the literature. Our model outperforms state-of-the-art methods with best performance parametric value in all aspects.

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

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

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

Similar content being viewed by others

Explore related subjects

Discover the latest articles and news from researchers in related subjects, suggested using machine learning.

References

  1. Greenspan H. Super-resolution in medical imaging. Comput J. 2009;52(1):43–62.

    Article  Google Scholar 

  2. Chen W-K. Linear networks and systems. Belmont: Wadsworth; 1993. p. 123–35.

    Google Scholar 

  3. Yu S, Zhang R, Wu S, Hu J, Xie Y. An edge-directed interpolation method for fetal spine MR images. BioMed Eng Online. 2013;12:102.

    Article  Google Scholar 

  4. Wang Y, Qiao J, Li J, Fu P, Chu S, Roddick JF. Sparse representation-based MRI super-resolution reconstruction. Measurement. 2014;47:946–53.

    Article  Google Scholar 

  5. Zhang D, He J, Zhao Y, Du M. MR image super-resolution reconstruction using sparse representation, nonlocal similarity and sparse derivative prior. Comput Boil Med. 2015;58:130–45.

    Article  Google Scholar 

  6. Lu X, Huang Z, Yuan Y. MR image super-resolution via manifold regularized sparse learning. Neurocomputing. 2015;162:96–104.

    Article  Google Scholar 

  7. Rueda A, Malpica N, Romero E. Single-image super-resolution of brain MR images using overcomplete dictionaries. Med Image Anal. 2013;17(1):113–32.

    Article  Google Scholar 

  8. Jafari-Khouzani K. MRI upsampling using feature-based nonlocal means approach. IEEE Trans Med Imaging. 2014;33(10):1969–85.

    Article  Google Scholar 

  9. Tourbier S, Bresson X, Hagmann P, Thiran J, Meuli R, Cuadra MB. An efficient total variation algorithm for super-resolution in fetal brain MRI with adaptive regularization. Neuroimage. 2015;118:584–97.

    Article  Google Scholar 

  10. Shi F, Cheng J, Wang L, Yap P, Shen D. LRTV: MR image super-resolution with low-rank and total variation regularizations. IEEE Trans Med Imaging. 2015;34(12):2459–66.

    Article  Google Scholar 

  11. Manjón JV, Coupé P, Buades A, Fonov V, Collins DL, Robles M. Non-local MRI upsampling. Med Image Anal. 2010;14(6):784–92.

    Article  Google Scholar 

  12. Jia Y, Gholipour A, He Z, Warfield SK. A new sparse representation framework for reconstruction of an isotropic high spatial resolution MR volume from orthogonal anisotropic resolution scans. IEEE Trans Med Imaging. 2017;36(5):1182–93.

    Article  Google Scholar 

  13. Hu C, Qu X, Guo D, Bao L, Chen Z. Wavelet-based edge correlation incorporated iterative reconstruction for undersampled MRI. Magn Reson Imaging. 2011;29(7):907–15.

    Article  Google Scholar 

  14. Lin S, Wong C, Jiang G, Rahman M, Ren T, Kwok N, Shi H, Yu Y-H, Wu T. Intensity and edge based adaptive unsharp masking filter for color image enhancement. Optik. 2016;127(1):407–14.

    Article  Google Scholar 

  15. Suresh S, Lal S, Reddy CS, Kiran MS. A novel adaptive cuckoo search algorithm for contrast enhancement of satellite images. IEEE J Sel Top Appl Earth Observ Remote Sens. 2017;10(8):3665–76.

    Article  Google Scholar 

  16. Wu Q, Li H, Meng F, Ngan KN, Zhu S. No reference image quality assessment metric via multi-domain structural information and piecewise regression. J Vis Commun Image Represent. 2015;32:205–16.

    Article  Google Scholar 

  17. Celik T, Tjahjadi T. Automatic image equalization and contrast enhancement using Gaussian mixture modeling. IEEE Trans Image Process. 2012;21(1):145–56.

    Article  MathSciNet  MATH  Google Scholar 

  18. Shi H, Kwok N, Fang G, Lin SC-F, Lee A, Li H, Yu Y-H. Gradient-guided color image contrast and saturation enhancement. Int J Adv Robot Syst. 2017. https://doi.org/10.1177/1729881417711683.

    Article  Google Scholar 

  19. Bryson M, Johnson M, Pizarro O, Williams SB. True color correction of autonomous underwater vehicle imagery. J Field Robot. 2016;33(6):853–74.

    Article  Google Scholar 

  20. Haware T, Gumble P. A review on underwater image scene enhancement and restoration using image processing. Int J Innov Res Electr Electron Instrum Control Eng. 2017;5(9):28–31.

    Google Scholar 

  21. Hiary H, Zaghloul R, Al-Adwan A, Al-Zoubi MB. Image contrast enhancement using geometric mean filter. London: Springer; 2016.

    Google Scholar 

  22. Celik T. Spatial entropy-based global and local image contrast enhancement. IEEE Trans Image Process. 2014;23(12):5298–308.

    Article  MathSciNet  MATH  Google Scholar 

  23. Fazli S, Samadi S, Nadirkhanlou P. A novel retinal vessel segmentation based on local adaptive histogram equalization. In: 2013 8th Iranian conference on machine vision and image processing (MVIP). 2013. p. 131–135

  24. Kim YT. Contrast enhancement using brightness preserving bi-histogram equalization. IEEE Trans Consum Electron. 1997;43(1):1–8.

    Article  Google Scholar 

  25. Ooi CH, Kong NSP, Ibrahim H. Bi-histogram with a plateau limit for digital image enhancement. IEEE Trans Consum Electron. 2009;55:2072–80.

    Article  Google Scholar 

  26. Ooi CH, Isa NAM. Adaptive contrast enhancement methods with brightness preserving. IEEE Trans Consum Electron. 2010;56(4):2543–51.

    Article  Google Scholar 

  27. Lidong H, We Z, Jun W, Zebin S. Combination of contrast limited adaptive histogram equalization and discrete wavelet transform for image enhancement. IET Image Process. 2015;9(10):908–15.

    Article  Google Scholar 

  28. Muniyappan S, Allirani A, Sarasvathi S. A novel approach to image enhancement by using contrast limited adaptive histogram equalization method. In: 2013 Fourth international conference on computing, communications, and networking technologies (ICCCNT). 2013. p. 1–6.

  29. Liu S, Rahman MA, Lin C-F, Wong CY, Jiang G, Liu SC, Kwok N, Shi H. Image contrast enhancement based on intensity expansion-compression. J Vis Commun Image Represent. 2017. https://doi.org/10.1016/j.jvcir.2017.05.011.

    Article  Google Scholar 

  30. Wan Y, Chen Q, Zhang BM. Image enhancement based on equal area dualistic sub-image histogram equalization method. IEEE Trans Consum Electron. 1999;45:68–75.

    Article  Google Scholar 

  31. Cao G, Huang L, Tian H, Huang X, Wang Y, Zhi R. Contrast Enhancement of brightness-distorted images by improved adaptive gamma correction. Comput Electr Eng. 2017;66:569–82.

    Article  Google Scholar 

  32. Goyal M, Bhushan B, Gupta S, Chawla R. Contrast enhancement technique based on lifting wavelet transform. Berlin: 3D Research Center, Kwangwoon University and Springer-Verlag GmbH Germany, part of Springer Nature; 2018.

    Book  Google Scholar 

  33. Chen SD, Ramli AR. Minimum mean brightness error bi-histogram equalization in contrast enhancement. IEEE Trans Consum Electron. 2003;49(4):1310–9.

    Article  Google Scholar 

  34. Poddar S, Tewary S, Sharma D, et al. Non-parametric modified histogram equalization for contrast enhancement. IET Image Process. 2013;7(7):641–52.

    Article  Google Scholar 

  35. Sim KS, Tso CP, Tan YY. Recursive sub-image histogram equalization applied to gray scale images. Pattern Recogn Lett. 2007;28(10):1209–21.

    Article  Google Scholar 

  36. Chen SD, Ramli AR. Contrast enhancement using recursive mean separate histogram equalization for scalable brightness preservation. IEEE Trans Consum Electron. 2003;49(4):1301–9.

    Article  Google Scholar 

  37. Park T, Efros AA, Zhang R, Zhu J-Y. Contrastive learning for unpaired image-to-image translation. In: European conference on computer vision. Cham: Springer; 2020. p. 319–345.

  38. Contrast-Mridata/low-high-contrast-mri dataset at github. https://github.com/CONTRAST-MRIDATA/low-high-contrast-mri.git.

  39. Lore KG, Akintayo A, Sarkar S. LLNet: A deep autoencoder approach to natural low-light image enhancement. Pattern Recogn. 2017;61:650–62.

    Article  Google Scholar 

  40. Wei C, Wang W, Yang W, Liu J. Deep retinex decomposition for low-light enhancement. 2018. arXiv preprint arXiv:1808.04560.

  41. Wang J, Tan W, Niu X, Yan B. Rdgan: Retinex decomposition based adversarial learning for low-light enhancement. In: 2019 IEEE international conference on multimedia and expo (ICME). IEEE; 2019. p. 1186–1191.

  42. Guo C, Li C, Guo J, Loy CC, Hou J, Kwong S, Cong R. Zeroreference deep curve estimation for low-light image enhancement. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 2020. p. 1780–1789.

  43. Jiang Y, Gong X, Liu D, Cheng Y, Fang C, Shen X, Yang J, Zhou P, Wang Z. Enlightengan: deep light enhancement without paired supervision. IEEE Trans Image Process. 2021;30:2340–9.

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. J C Bose University of Science and technology, YMCA, Faridabad, India

    Shikha Sharma, Vyoma Vaish & Shailender Gupta

  2. YMCA Sector-6, J C Bose University of Science and technology, ymca, Faridabad, India

    Shikha Sharma

Authors
  1. Shikha Sharma
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Vyoma Vaish
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Shailender Gupta
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Shailender Gupta.

Ethics declarations

Conflict of Interest

The authors have no conflict of interest. All the co-authors have seen and agreed to the content of the manuscript and there is no financial interest to report. We certify that the submission is original work and is not under review at any other publication.

Additional information

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

Sharma, S., Vaish, V. & Gupta, S. An Optimized MRI Contrast Enhancement Scheme Using Cycle Generative Adversarial Network. SN COMPUT. SCI. 3, 366 (2022). https://doi.org/10.1007/s42979-022-01261-3

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s42979-022-01261-3

Keywords