Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Skip to main content
Springer Nature Link
Log in

Deep residual neural network based image enhancement algorithm for low dose CT images

  • 1210: Computer Vision for Clinical Images
  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

Current deep learning based image enhancement algorithms attempt to learn the mapping relationship between degraded images and clear images directly. These algorithms often ignore the fidelity constraint of the observational model. In order to improve the image enhancement performance, an improved deep residual neural network based image enhancement algorithm (DRNN-IE) for low dose CT images is proposed in this paper. DRNN-IE embeds the image enhancement task into a deep neural network, and achieves data consistency using multiple enhancement modules and back-projection modules. The enhancement modules in DRNN-IE produce new features through fusing low-level and high-level features. In order to improve the algorithm’s generalization ability, a dual-parameter loss function is adopted to train and optimize the neural network. Experiments on real CT images show that the proposed algorithm has excellent enhancement performance and retains detailed information of low-dose CT images.

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

Similar content being viewed by others

References

  1. Ahn CK, Jin H, Heo C, Kim JH (2019) Combined low-dose simulation and deep learning for CT denoising: application of ultra-low-dose cardiac CTA. Proceedings of the Medical Imaging 2019: Physics of Medical Imaging. 1094846 110500E, San Diego, United States https://doi.org/10.1117/12.2513144

  2. Amid E, Warmuth MKK, Anil R (2019) Robust Bi-tempered logistic loss based on bregman divergences. Proceedings of the Advances in Neural Information Processing Systems 2019, Vancouver, Canada, 14987-14996

  3. Chen Y, Sun P (2017) The research and practice of medical image enhancement and 3D reconstruction system. Proceedings of 2017 International conference on Robots & Intelligent System (ICRIS), 350–353, Huai’an. https://doi.org/10.1109/ICRIS.2017.94

  4. Chen LL, Gou SP, Yao Y, Bai J, Jiao L, Sheng K (2016) Denoising of low dose CT image with context-based BM3D. Proceedings of the 2016 IEEE Region 10 Conference (TENCON). IEEE, 682-685

  5. Cheng J, Tian S, Yua L, Ma X, Xing Y (2020) A deep learning algorithm using contrast-enhanced computed tomography (CT) images for segmentation and rapid automatic detection of aortic dissection. Biomed Signal Process Control 62(9):102145

    Article  Google Scholar 

  6. Chi J, Zhang Y, Yu X, Wang Y, Wu C (2019) Computed tomography (CT) image quality enhancement via a uniform framework integrating noise estimation and super-resolution networks. Sensors. 19(15):3348

    Article  Google Scholar 

  7. Chu J, Zhang J, Lu W, Huang X (2018) A novel multiconnected convolutional network for super-resolution. IEEE Signal Process Lett 25(7):946–950

    Article  Google Scholar 

  8. Dong W, Wang P, Yin W, Shi G, Wu F, Lu X (2019) Denoising prior driven deep neural network for image restoration. IEEE Trans Pattern Anal Mach Intell 41(10):2308–2318

    Article  Google Scholar 

  9. Fadden C, Srinivasan V, Kothapalli SR (2019) Single simulation platform for both optical and radio frequency induced thermoacoustic tomography. Proceedings of the Photons Plus Ultrasound: Imaging and Sensing 2019. 10878O, San Francisco, United States https://doi.org/10.1117/12.2510607

  10. Gu P, Jiang C, Ji M, Zhang Q, Ge Y, Liang D, Liu X, Yang Y, Zheng H, Hu Z (2019) Low-dose computed tomography image super-resolution reconstruction via random forests. Sensors 19(1):207

    Article  Google Scholar 

  11. Gu P, Jiang C, Ji M, Zhang Q, Ge Y, Liang D, Liu X, Yang Y, Zheng H, Hu Z (2019) Deep iterative reconstruction estimation (DIRE): approximate iterative reconstruction estimation for low dose CT imaging. Phys Med Biol 64(13):135007

    Article  Google Scholar 

  12. Helland IS, Saeb S, Almy T, Rimal R (2018) Model and estimators for partial least squares regression. J Chemom 32(9):e3044

    Article  Google Scholar 

  13. Higaki T, Nishimaru E, Nakamura Y, Tatsugami F, Yu Z, Zhou J, Verleker AP, Akino N, Awai K (2018) Radiation dose reduction in CT using Deep Learning based Reconstruction (DLR): A phantom study. Proceeding of the 24th European congress of radiology. 1-12, Vienna, Austria, https://doi.org/10.1594/ecr2018/C-1656

  14. Jeon J, Lee S (2018) Reconstruction-based pairwise depth dataset for depth image enhancement using CNN, Proceedings of 2018 European Conference on Computer Vision, Munich, Germany, 438–454

  15. Lim B, Son S, Kim H, Nah S, Lee KM (2017) Enhanced deep residual networks for single image super-resolution. Proceedings of the 2017 IEEE conference on computer vision and pattern recognition workshops (CVPRW). Honolulu, USA, 136-144

  16. Lin T, Ma S, Zhangl S (2015) On the global linear convergence of the ADMM with multiblock variables. SIAM J Optim 24(6):108–115

    MathSciNet  Google Scholar 

  17. Liu P, Wu B, Ma H, Chundi PK, Seok M (2019) MemNet: memory-efficiency guided neural architecture search with augment-trim learning. arXiv preprint arXiv: 1907.09569.

  18. Lyu Q, You C, Shan H, Zhang Y, Wang G (2019) Super-resolution MRI and CT through GAN-circle. Proceedings of the Developments in X-Ray Tomography XII 11113, 111130X

  19. Lyu Q, You C, Shan H, Zhang Y, Wang G (2019) Lightweight feature fusion network for single image super-resolution. IEEE Signal Process Lett 26(4):538–542

    Article  Google Scholar 

  20. MacRedmond R, Logan PM, Lee M, Kenny D, Foley C, Costello RW (2004) Screening for lung cancer using low dose CT scanning. Thorax 59(3):237–241

    Article  Google Scholar 

  21. Marshall CH, Gribbin C, Arams RS, McCauley DI (1990) Low-dose CT of the lungs: preliminary observations. Radiology 175(3):729–731

    Article  Google Scholar 

  22. Matsuura M, Zhou J, Akino N, Yu Z (2019) Feature aware deep learning CT image reconstruction. Proceedings of the 15th International Meeting on Fully Three-Dimensional Image Reconstruction in Radiology and Nuclear Medicine. 110721B Philadelphia, United States. https://doi.org/10.1117/12.2534614.

  23. Mohammadi S, Leventouri T (2019) A study of wavelet-based denoising and a new shrinkage function for low-dose CT scans. Biomedical Physics & Engineering Express 5(3):035018

    Article  Google Scholar 

  24. Pan X, Sidky EY, Vannier M (2009) Why do commercial CT scanners still employ traditional, filtered back-projection for image reconstruction? Inverse Prob 25(12):1230009

    Article  MathSciNet  MATH  Google Scholar 

  25. Pinheiro PO, Lin TY, Collobert R (2016) Learning to refine object segments. Proceedings of the European Conference on Computer Vision 2016. Amsterdam, Netherlands, 75-91. https://doi.org/10.1007/978-3-319-46448-0_5

  26. Qian P, Zhou J, Jiang Y, Liang F, Zhao K, Wang S, Su KH, Jr Muzic RF (2018) Multi-view maximum entropy clustering by jointly leveraging inter-view collaborations and intra-view-weighted attributes. IEEE Access 6:28594–28610

    Article  Google Scholar 

  27. Rakêt LL, Nielsen, M (2012) A splitting algorithm for directional regularization and sparsification. Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012), Tsukuba, Japan, 10232–10236.

  28. Sagara Y, Hara AK, Pavlicek W, Silva AC, Paden RG, Wu Q (2010) Abdominal CT: comparison of low-dose CT with adaptive statistical iterative reconstruction and routine-dose CT with filtered back projection in 53 patients. Am J Roentgenol 195(3):713–719

    Article  Google Scholar 

  29. Seo H, Huang C, Bassenne M (2020) Modified U-net (mU-net) with incorporation of object-dependent high level features for improved liver and liver-tumor segmentation in CT images. IEEE Trans Med Imaging 39(5):1316–1325

    Article  Google Scholar 

  30. Shi W, Caballero J, Huszár F, Totz J, Aitken AP, Bishop R, Rueckert D, Wang Z (2016) Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. Proceedings of the IEEE conference on computer vision and pattern recognition 2016, 1874–1883, Las Vegas, USA.

  31. Shukla AK, Pandey RK, Yadav S (2020) Adaptive fractional masks and super resolution based approach for image enhancement. Multim Tools Appl. Online. https://doi.org/10.1007/s11042-020-08968-6

  32. Singh S, Kalra MK, Hsieh J, Licato PE, Do S, Pien HH, Blake MA (2011) Abdominal CT: comparison of adaptive statistical iterative and filtered back projection reconstruction techniques. Radiology 257(2):373–383

  33. Tang Z, Wang S, Huo J (2017) Bayesian framework with non-local and low-rank constraint for image reconstruction. J Phys Conf Ser 787:012008. https://doi.org/10.1088/1742-6596/787/1/012008

    Article  Google Scholar 

  34. Tang C, Li J, Wang L, Li Z, Jiang L, Cai A, Zhang W, Liang N, Li L, Yan B (2019) Unpaired low-dose CT denoising network based on cycle-consistent generative adversarial network with prior image information. Comput Math Methods Med 2019:8639825–8639811. https://doi.org/10.1155/2019/8639825

    Article  MATH  Google Scholar 

  35. Thillaikkarasi R, Saravanan S (2019) An enhancement of deep learning algorithm for brain tumor segmentation using kernel based CNN with M-SVM. J Med Syst 43(4):84

    Article  Google Scholar 

  36. Wang Y, Song W, Fortino G, Qi L, Zhang W, Liotta A (2019) An experimental-based review of image enhancement and image restoration methods for underwater imaging. IEEE Access 85(4):92–108

    Google Scholar 

  37. Watanabe H, Kanematsu M, Miyoshi T, Goshima S, Kondo H, Moriyama N, Bae KT (2010) Improvement of image quality of low radiation dose abdominal CT by increasing contrast enhancement. Am J Roentgenol 195(4):986–992

    Article  Google Scholar 

  38. Xiao ZZ, Zhou P (2019) Digital measurement of 2D and 3D cracks in sandstones through improved pseudo color image enhancement and 3D reconstruction method. Int J Numer Anal Methods Geomech 43(16):2565–2584

    Article  Google Scholar 

  39. Xie Y, He Y, Cheng A, Zhang J (2016) Study on medical image enhancement based on IFOA improved grayscale image adaptive enhancement. Multimed Tools Appl 75(11):14367–14379

    Article  Google Scholar 

  40. Xu C, Cui Y, Zhang Y, Gao P, Xu J (2020) Image enhancement algorithm based on generative adversarial network in combination of improved game adversarial loss mechanism. Multimed Tools Appl 79(13):9435–9450

    Article  Google Scholar 

  41. Zhao T, Hoffman J, McNitt-Gray M, Ruan D (2019) Ultra-low-dose CT image denoising using modified BM3D scheme tailored to data statistics. Med Phys 46(1):190–198

    Article  Google Scholar 

  42. Zhao W, Lv T, Chen Y, Xing L (2020) Dual-energy CT imaging using a single-energy CT data via deep learning: a contrast-enhanced CT study. Int J Radiat Oncol Biol Phys 108(3):S43

    Article  Google Scholar 

  43. Zhu H, Tong D, Zhang L, Wang S, Wu W, Tang H, Chen Y, Luo L, Zhu J, Li B (2020) Temporally downsampled cerebral CT perfusion image restoration using deep residual learning. Int J Comput Assist Radiol Surg 15(2):193–201

    Article  Google Scholar 

Download references

Acknowledgements

This work was supported in part by the Jiangsu Committee of Health under Grant H2018071, Changshu Committee of Health under Grant csws201820, National Natural Science Foundation of China under Grants 61806026, and Natural Science Foundation of Jiangsu Province under Grant BK 20180956.

Author information

Authors and Affiliations

  1. Affiliated Changshu Hospital of Soochow University (Changshu No.1 people’s Hospital), Changshu, 215500, Jiangsu, China

    Kaijian Xia & Bo Chen

  2. Jiangsu Key Laboratory of Media Design and Software Technology, Jiangnan University, Wuxi, 214122, Jiangsu, China

    Kaijian Xia & Yizhang Jiang

  3. Department of Informatics, University of Leicester, Leicester, LE1 7RH, UK

    Qinghua Zhou

  4. School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, 214122, Jiangsu, China

    Yizhang Jiang

  5. School of Information Science and Engineering, Changzhou University, Changzhou, 213164, Jiangsu, China

    Xiaoqing Gu

Authors
  1. Kaijian Xia
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Qinghua Zhou
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yizhang Jiang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Bo Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Xiaoqing Gu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Xiaoqing Gu.

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

Xia, K., Zhou, Q., Jiang, Y. et al. Deep residual neural network based image enhancement algorithm for low dose CT images. Multimed Tools Appl 81, 36007–36030 (2022). https://doi.org/10.1007/s11042-021-11024-6

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-021-11024-6

Keywords

Search

Navigation