Skip to main content

Advertisement

Log in

Low Dose CT Image Reconstruction Using Deep Convolutional Residual Learning Network

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

Abstract

Image reconstruction from computed tomography measurement is formulated as a thought-provoking statistical inverse problem. Deep learning algorithms are best for ill-posed statistical inverse problems that presently achieve state-of-art reconstruction results. The challenging task is to lower the potentially harmful radiation a patient is exposed to during the CT scan. In recently available CT Scanners, Low-Dose CT (LDCT) reconstruction is presented with a post-processing approach, which uses deep learning-based medical image reconstruction methods to reduce the dose level without compromising the image quality. Therefore, this paper proposes a deep learning-based post-processing method called Deep Convolutional Neural Network with Residual Learning (DCNN-RL). The method trains the network on a newly available low-dose CT benchmark dataset (LoDoPaB-CT). It also enables to compare with other benchmark CT datasets such as AAPM LDCT and COVIDx-CT. The proposed architecture optimizes the filtering part to minimize the error function. It learns the parameters of the residual network via numerous training to maximize the efficiency of production. This paper compares noise methods on DCNN-RL using various LDCT datasets of the same domain (human being's chest CT scan) to analyze the image quality. The experiment findings suggest that the Adagrad optimizer is the best for LDCT images. Gaussian noise with a minor variance outperforms the medical image reconstruction task. Here, it has been demonstrated that this approach with these benchmark datasets drastically improves the medical CT image quality, shown through qualitative and quantitative outcomes.

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

Access this article

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.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

Similar content being viewed by others

Data availability

The dataset can be downloaded from the Zenodo website (https://zenodo.org/record/3384092).

References

  1. Moen TR, Chen B, Holmes DR III, Duan X, Yu Z, Yu L, Leng S, Fletcher JG, McCollough CH. Low-dose ct image and projection dataset. Med Phys. 2021;48:902–11.

    Article  Google Scholar 

  2. G. T. Herman, Image reconstruction from projections. Fund Comp Tomog (1980);260–276.

  3. Nishi SP, Zhou J, Okereke I, Kuo Y-F, Goodwin J. Use of imaging and diagnostic procedures after low-dose ct screening for lung cancer. Chest. 2020;157:427–34.

    Article  Google Scholar 

  4. Pinsky PF, Lynch DA, Gierada DS. Incidental findings on lowdose ct lung cancer screenings and deaths from respiratory diseases. Chest. 2021;161:1092.

    Article  Google Scholar 

  5. Yoo S, Yin F-F. Dosimetric feasibility of cone-beam ct-based treatment planning compared to ct-based treatment planning. Int J Rad Oncol Biol Phys. 2006;66:1553–61.

    Article  Google Scholar 

  6. Wang G, Ye JC, De Man B. Deep learning for tomographic image reconstruction, Nature. Mach Intel. 2020;2:737–48.

    Article  Google Scholar 

  7. Zhang J, Zuo H. A deep rnn for ct image reconstruction in Medical Imaging 2020 Physics of Medical Imaging. Int Soc Opt Phot. 2020;11312:113124.

    Google Scholar 

  8. S. Kuanar, V. Athitsos, D. Mahapatra, K. Rao, Z. Akhtar, D. Dasgupta, Low dose abdominal ct image reconstruction An unsupervised learning-based approach in 2019 IEEE International Conference on Image Processing (ICIP). IEEE. 2019; 1351–1355.

  9. Shan H, Kruger U, Wang G. A novel transfer learning framework for low-dose ct, in 15th international meeting on fully three-dimensional image reconstruction in radiology and nuclear medicine. Int Soc Opt Phot. 2019;11072:110722.

    Google Scholar 

  10. Xie Y, Zhang J, Xia Y. Semi-supervised adversarial model for benign-malignant lung nodule classification on chest ct. Med Image Anal. 2019;57:237–48.

    Article  Google Scholar 

  11. Shan H, Zhang Y, Yang Q, Kruger U, Kalra MK, Sun L, Cong W, Wang G. 3-d convolutional encoder-decoder network for low-dose ct via transfer learning from a 2-d trained network. IEEE Trans Med Imag. 2018;37:1522–34.

    Article  Google Scholar 

  12. Wang G, Ye JC, Mueller K, Fessler JA. Image reconstruction is a new frontier of machine learning. IEEE Trans Med Imaging. 2018;37:1289–96.

    Article  Google Scholar 

  13. O. Ronneberger, P. Fischer, T. Brox, U-net: Convolutional networks for biomedical image segmentation, in International Conference on Medical image computing and computer-assisted intervention. Springer. 2015; 234–241.

  14. McCollough C. Tu-fg-207a-04: overview of the low dose ct grand challenge. Med Phys. 2016;43:3759–60.

    Google Scholar 

  15. Leuschner J, Schmidt M, Baguer DO, Maass P. Lodopab-ct, a benchmark dataset for low-dose computed tomography reconstruction. Sci Data. 2021;8:1–12.

    Article  Google Scholar 

  16. Zhang K, Liu X, Shen J, Li Z, Sang Y, Wu X, Zha Y, Liang W, Wang C, Wang K, et al. Clinically applicable ai system for accurate diagnosis, quantitative measurements, and prognosis of covid-19 pneumonia using computed tomography. Cell. 2020;181:1423–33.

    Article  Google Scholar 

  17. Samuel Armato G, Mclennan G, Bidaut L, et al. The lung image database consortium (lidc) and image database resource initiative (idri) a completed reference database of lung nodules on ct scans. Med phys. 2011;38:915–31.

    Article  Google Scholar 

  18. Masoudi M, Pourreza H-R, Saadatmand-Tarzjan M, Eftekhari N, Zargar FS, Rad MP. A new dataset of computed-tomography angiography images for computer-aided detection of pulmonary embolism. Sci data. 2018;5:1–9.

    Article  Google Scholar 

  19. Junji S, Shigehiko K, Junpei I, Tsuneo M, Takeshi K, Ken-ichi K, Mitate M, Hiroshi F, Yoshie K, Kunio D. Development of a digital image database for chest radiographs with and without a lung nodule: receiver operating characteristic analysis of radiologists’ detection of pulmonary nodules. Am J Roentgenol. 2000;174:71–4.

    Article  Google Scholar 

  20. Clark KW, Gierada DS, Moore SM, Mafftt DR, Koppel P, Phillips SR, Prior FW. Creation of a ct image library for the lung screening study of the national lung screening trial. J Digit Imaging. 2007;20:23–31.

    Article  Google Scholar 

  21. Denker A, Schmidt M, Leuschner J, Maass P. Conditional invertible neural networks for medical imaging. J Imaging. 2021;7:243.

    Article  Google Scholar 

  22. Ulyanov D, Vedaldi A, Lempitsky V, Deep image prior, in: Proceedings of the IEEE conference on computer vision and pattern recognition, 2018; 9446–9454.

  23. Baguer DO, Leuschner J, Schmidt M. Computed tomography reconstruction using deep image prior and learned reconstruction methods. Inverse Prob. 2020;36:094004.

    Article  MathSciNet  MATH  Google Scholar 

  24. Yungang Z, Benshun Y, Chenyue W, Yu F. Low-dose ct image denoising method based on convolutional neural network. Acta Optica Sinica. 2018;38:0410003.

    Article  Google Scholar 

  25. Unal MO, Ertas M, Yildirim I, Self-supervised training for lowdose ct reconstruction, in: 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI). IEEE. 2021; 69-72

  26. Arridge S, Maass P, Oktem O, Schonlieb C-B. Solving inverse problems using data-driven models. Acta Numer. 2019;28:1–174.

    Article  MathSciNet  MATH  Google Scholar 

  27. Chen H, Zhang Y, Kalra MK, Lin F, Chen Y, Liao P, Zhou J, Wang G. Low-dose ct with a residual encoder-decoder convolutional neural network. IEEE Trans Med Imaging. 2017;36:2524–35.

    Article  Google Scholar 

  28. He J, Wang Y, Ma J. Radon inversion via deep learning. IEEE Trans Med Imaging. 2020;39:2076–87.

    Article  Google Scholar 

  29. Adler J, Oktem O. Solving ill-posed inverse problems using iterative deep neural networks. Inverse Prob. 2017;33:124007.

    Article  MathSciNet  MATH  Google Scholar 

  30. Zhang K, Zuo W, Chen Y, Meng D, Zhang L. Beyond a gaussian denoiser: Residual learning of deep cnn for image denoising. IEEE Trans Image Process. 2017;26:3142–55.

    Article  MathSciNet  MATH  Google Scholar 

  31. Zhang K, Zuo W, Gu S, Zhang L, Learning deep cnn denoiser prior for image restoration, In: Proceedings of the IEEE conference on computer vision and pattern recognition, 2017; 3929–3938.

  32. Batson J, Royer L, Noise 2 self: Blind denoising by self-supervision. In: International Conference on Machine Learning. PMLR. 2019; 524–533.

  33. Ding Q, Ji H, Quan Y, Zhang X. Dataset-free deep learning method for low-dose ct image reconstruction. ArXiv preprint. 2022;2205:00463.

    MATH  Google Scholar 

  34. Yang W, Zhang H, Yang J, Wu J, Yin X, Chen Y, Shu H, Luo L, Coatrieux G, Gui Z, et al. Improving low-dose ct image using residual convolutional network, Ieee. Access. 2017;5:24698–705.

    Article  Google Scholar 

  35. Jifara W, Jiang F, Rho S, Cheng M, Liu S. Medical image denoising using convolutional neural network: a residual learning approach. J Supercomput. 2019;75:704–18.

    Article  Google Scholar 

  36. Rawat S, Rana K, Kumar V. A novel complex-valued convolutional neural network for medical image denoising. Biomed Signal Process Control. 2021;69:102859.

    Article  Google Scholar 

  37. Dabov K, Foi A, Katkovnik V, Egiazarian K. Image denoising by sparse 3-d transform-domain collaborative filtering. IEEE Trans Image Process. 2007;16:2080–95.

    Article  MathSciNet  Google Scholar 

  38. S. Z. Li, Markov random field modeling in image analysis. Spr Sci Bus Med. 2009

  39. Liu Y, A method of ct image denoising based on residual encoderdecoder network. J Healthcare Eng. (2021); 2021

  40. Huang L, Jiang H, Li S, Bai Z, Zhang J. Two stage residual cnn for texture denoising and structure enhancement on lowdose ct image. Comput Methods Programs Biomed. 2020;184:105115.

    Article  Google Scholar 

  41. Ataei S, Alirezaie J, Babyn P, Cascaded convolutional neural networks with perceptual loss for low dose ct denoising In: 2020 International Joint Conference on Neural Networks (IJCNN). IEEE. 2020; 1–5.

  42. He K, Zhang X, Ren S, Sun J, Deep residual learning for image recognition, In: Proceedings of the IEEE conference on computer vision and pattern recognition. 2016; 770–778.

  43. Gunraj H, Wang L, Wong A, Covidnet-ct: A tailored deep convolutional neural network design for detection of covid-19 cases from chest ct images. Front Med (2020); 1025.

  44. Chervyakov N, Lyakhov P, Nagornov N. Analysis of the quantization noise in discrete wavelet transform filters for 3d medical imaging. Appl Sci. 2020;10:1223.

    Article  Google Scholar 

  45. Wang Z, Bovik AC, Sheikh HR, Simoncelli EP, Image quality assessment: From error measurement to structural similarity. IEEE Trans Image Proc. (2004); 13

  46. Muhammad NA, Kayun Z, Abu Hassan H, Ding Wong JH, Ng KH, Karim MKA. Evaluation of organ dose and image quality metrics of pediatric ct chest-abdomen-pelvis (cap) examination: an anthropomorphicphantom study. Appl Sci. 2021;11:2047.

    Article  Google Scholar 

  47. Joemai RM, Geleijns J. Assessment of structural similarity in ct using _ltered backprojection and iterative reconstruction: a phantom study with 3d printed lung vessels. Br J Radiol. 2017;90:20160519.

    Article  Google Scholar 

  48. Jin KH, McCann MT, Froustey E, Unser M. Deep convolutional neural network for inverse problems in imaging. IEEE Trans Image Proce. 2017;26:4509–22.

    Article  MathSciNet  MATH  Google Scholar 

  49. Yang Q, Yan P, Zhang Y, Yu H, Shi Y, Mou X, Kalra MK, Zhang Y, Sun L, Wang G. Low-dose ct image denoising using a generative adversarial network with wasserstein distance and perceptual loss. IEEE Trans Med Imaging. 2018;37:1348–57.

    Article  Google Scholar 

  50. Mason D. Su-e-t-33: pydicom: an open source dicom library. Med Phys. 2011;38:3493–3493.

    Article  Google Scholar 

  51. Tocknell J. h5preserve: Thin wrapper around h5py, inspired by camel. J Open Source Soft. 2018;3:581.

    Article  Google Scholar 

  52. Bishop CM, Nasrabadi NM, Pattern recognition and machine learning. Springer. 2006; 4

  53. Adler J, Oktem O. Learned primal-dual reconstruction. IEEE Trans Med Imaging. 2018;37:1322–32.

    Article  Google Scholar 

  54. Gravel P, Beaudoin G, De Guise JA. A method for modeling noise in medical images. IEEE Trans Med Imaging. 2004;23:1221–32.

    Article  Google Scholar 

  55. Diwakar M, Kumar M. A review on ct image noise and its denoising. Biomed Signal Process Control. 2018;42:73–88.

    Article  Google Scholar 

  56. Vegas-Sanchez-Ferrero G, Ledesma-Carbayo MJ, Washko GR, Estepar RSJ. Statistical characterization of noise for spatial standardization of ct scans: enabling comparison with multiple kernels and doses. Med Image Anal. 2017;40:44–59.

    Article  Google Scholar 

  57. Mason J, Rioux SE, Clarke A, Costa M, Schmidt V, Keough T, Huynh S. Beyea, Comparison of objective image quality metrics to expert radiologists’ scoring of diagnostic quality of mr images. IEEE Trans Med Imaging. 2019;39:1064–72.

    Article  Google Scholar 

  58. Coban SB, Lionheart WR, Withers PJ. Assessing the efficacy of tomographic reconstruction methods through physical quantification techniques. Meas Sci Technol. 2021;32:075404.

    Article  Google Scholar 

  59. Lei Y, Tian Y, Shan H, Zhang J, Wang G, Kalra MK. Shape and margin-aware lung nodule classification in low-dose ct images via soft activation mapping. Med Image Anal. 2020;60:101628.

    Article  Google Scholar 

  60. Ramanathan S, Ramasundaram M. Alzheimer’s Disease Shape Detection Model in Brain Magnetic Resonance Images Via Whale Optimization with Kernel Support Vector Machine. J Electr Eng Technol. 2023;18:2287–96.

    Article  Google Scholar 

  61. Yu Y, Acton ST. Speckle reducing anisotropic diffusion. IEEE Trans Image Proc. 2002;11:1260–70.

    Article  MathSciNet  Google Scholar 

  62. Wang T, Lei Y, Tian Z, Dong X, Liu Y, Jiang X, Curran WJ, Liu T, Shu H-K, Yang X. Deep learning-based image quality improvement for low-dose computed tomography simulation in radiation therapy. J Med Imag. 2019;6:043504.

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Shalini Ramanathan.

Ethics declarations

Conflict of Interest

The authors have no conflict of interest.

Ethical Approval

This research study was conducted retrospectively using human subject data made available in open access [14, 15, 43]. Ethical approval was not required as confirmed by the license attached with the open-access data.

Additional information

Publisher's Note

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

This article is part of the topical collection “Research Trends in Computational Intelligence” guest edited by Anshul Verma, Pradeepika Verma, Vivek Kumar Singh and S. Karthikeyan.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Ramanathan, S., Ramasundaram, M. Low Dose CT Image Reconstruction Using Deep Convolutional Residual Learning Network. SN COMPUT. SCI. 4, 720 (2023). https://doi.org/10.1007/s42979-023-02210-4

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s42979-023-02210-4

Keywords

Navigation