Downloads

doi: https://doi.org/10.53941/aim.2024.100007
Zhao, H., Qian, L., Zhu, Y., & Tian, D. Low Dose CT Image Denoising: A Comparative Study of Deep Learning Models and Training Strategies. AI Medicine. 2024, 1(1), 7. doi: https://doi.org/10.53941/aim.2024.100007
Volume 1, lssue 1, Dec 2024
Copyright (c) 2024 by the authors.
Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Article

Low Dose CT Image Denoising: A Comparative Study of Deep Learning Models and Training Strategies

Heng Zhao 1, Like Qian 1, Yaqi Zhu 1 and Dingcheng Tian 1,2,∗

1 Research Institute for Medical and Biological Engineering, Ningbo University, Ningbo 315211, China

2 College of Medicine and Biological Information Engineering, Northeastern University, Shenyang 110016, China

∗ Correspondence: 2310520@stu.neu.edu.cn

Received: 8 August 2024; Revised: 10 October 2024; Accepted: 14 October 2024; Published: 5 November 2024

 

Abstract: Low-dose computed tomography (LDCT) denoising is an important topic in CT image research. Compared with normal-dose CT images, LDCT can reduce the radiation dose of X-rays, decreasing the radiation burden on the human body, which is beneficial to human health. However, quantum noise caused by low-dose rays will reduce the quality of CT images, thereby decreasing the accuracy of clinical diagnosis. In recent years, deep learning-based denoising methods have shown promising advantages in this field. Researchers have proposed some optimized models for low-dose CT image denoising. These methods have enhanced the application of low-dose CT image denoising from different aspects. From the perspective of experimental research, this paper investigates and evaluates some top deep learning models proposed in the field of low-dose image denoising in recent years, with the aim of determining the best models and training strategies for this task. We conducted experiments on seven deep learning models (REDCNN, EDCNN, QAE, OCTNet, UNet, WGAN, CTformer) on the AAPM dataset and the Piglet dataset. Our research shows that UNet has the best denoising effect among the models, obtaining PSNR = 33.06 (AAPM dataset) and PSNR = 31.21 (Piglet dataset), and good generalization capacity is also observed. However, UNet has a large number of parameters, and the time it takes to process an image is about 8 ms, while EDCNN takes about 4.8 ms to process an image, and its average PSNR is ranked second after UNet. EDCNN strikes a balance between denoising performance and processing efficiency, making it ideal for low-dose CT image denoising tasks.

Keywords:

deep learning low dose CT image denoising convolutional neural network

References

  1. Zhang, Z.; Yu, L.; Liang, X.; Zhao, W.; Xing, L. TransCT: Dual-path transformer for low dose computed tomography. In Proceedings of the Medical Image Computing and Computer Assisted Intervention–MICCAI 2021: 24th International Conference, Strasbourg, France, 27 September–1 October 2021; Part VI 24, pp. 55–64. DOI: https://doi.org/10.1007/978-3-030-87231-1_6
  2. Jiang, H. Computed Tomography: Principles, Design, Artifacts, and Recent Advances; SPIE: Bellingham, WA, USA, 2009.
  3. Brenner, D.J.; Hall, E.J. Computed Tomography — An Increasing Source of Radiation Exposure. N. Engl. J. Med. 2007, 357, 2277–2284. DOI: https://doi.org/10.1056/NEJMra072149
  4. de Gonzalez, A.B.; Darby, S. Risk of cancer from diagnostic X-rays: Estimates for the UK and 14 other countries. Lancet 2004, 363, 345–351. DOI: https://doi.org/10.1016/S0140-6736(04)15433-0
  5. Naidich, D.P.; Marshall, C.H.; Gribbin, C.; Arams, R.S.; McCauley, D.I. Low-dose CT of the lungs: preliminary observations. Radiology 1990, 175, 729–731. DOI: https://doi.org/10.1148/radiology.175.3.2343122
  6. Yin, X.; Coatrieux, J.-L.; Zhao, Q.; Liu, J.; Yang, W.; Yang, J.; Quan, G.; Chen, Y.; Shu, H.; Luo, L. Domain Progressive 3D Residual Convolution Network to Improve Low-Dose CT Imaging. IEEE Trans. Med Imaging 2019, 38, 2903–2913. DOI: https://doi.org/10.1109/TMI.2019.2917258
  7. Han, Y.S.; Yoo, J.; Ye, J.C. Deep residual learning for compressed sensing CT reconstruction via persistent homology analysis. arXiv 2016, arXiv:1611.06391.
  8. Chen, Y.; Yin, X.; Shi, L.; Shu, H.; Luo, L.; Coatrieux, J.-L.; Toumoulin, C. Improving abdomen tumor low-dose CT images using a fast dictionary learning based processing. Phys. Med. Biol. 2013, 58, 5803–5820. DOI: https://doi.org/10.1088/0031-9155/58/16/5803
  9. Thanh, D.; Surya, P.; Hieu, L.M. A Review on CT and X-Ray Images Denoising Methods. Informatica 2019, 43, 151–159. DOI: https://doi.org/10.31449/inf.v43i2.2179
  10. Diwakar, M.; Kumar, M. A review on CT image noise and its denoising. Biomed. Signal Process. Control. 2018, 42, 73–88. DOI: https://doi.org/10.1016/j.bspc.2018.01.010
  11. Wang, H.; Chi, J.; Wu, C.; Yu, X.; Wu, H. Degradation adaption localto-global transformer for low-dose CT image denoising. J. Digit. Imaging 2023, 36, 1894–1909. DOI: https://doi.org/10.1007/s10278-023-00831-y
  12. Chen, Z.; Gao, Q.; Zhang, Y.; Shan, H. Ascon: Anatomy-aware supervised contrastive learning framework for low-dose CT denoising. In Proceedings of the International Conference on Medical Image Computing and Computer Assisted Intervention, Vancouver, BC, Canada, 8–12 October 2023; pp. 355–365. DOI: https://doi.org/10.1007/978-3-031-43999-5_34
  13. Manduca, A.; Yu, L.; Trzasko, J.D.; Khaylova, N.; Kofler, J.M.; McCollough, C.M.; Fletcher, J.G. Projection space denoising with bilateral filtering and CT noise modeling for dose reduction in CT. Med. Phys. 2009, 36, 4911–4919. DOI: https://doi.org/10.1118/1.3232004
  14. Kachelriess, M.; Watzke, O.; Kalender, W.A. Generalized multidimensional adaptive filtering for conventional and spiral single-slice, multi-slice, and cone-beam CT. Med. Phys. 2001, 28, 475–490. DOI: https://doi.org/10.1118/1.1358303
  15. Hsieh, J. Adaptive streak artifact reduction in computed tomography resulting from excessive X-ray photon noise. Med. Phys. 1998, 25, 2139–2147. DOI: https://doi.org/10.1118/1.598410
  16. Wang, J.; Li, T.; Lu, H.; Liang, Z. Penalized weighted least-squares approach to sinogram noise reduction and image reconstruction for low-dose X-ray computed tomography. IEEE Trans. Med. Imaging 2006, 25, 1272–1283. DOI: https://doi.org/10.1109/TMI.2006.882141
  17. Zeng, D.; Huang, J.; Bian, Z.; Niu, S.; Zhang, H.; Feng, Q.; Liang, Z.; Ma, J. A Simple Low-Dose X-Ray CT Simulation from High-Dose Scan. IEEE Trans. Nucl. Sci. 2015, 62, 2226–2233. DOI: https://doi.org/10.1109/TNS.2015.2467219
  18. Fletcher, J.G.; Grant, K.L.; Fidler, J.L.; Shiung, M.; Yu, L.; Wang, J.; Schmidt, B.; Allmendinger, T.; McCollough, C.H. Validation of dual source single-tube reconstruction as a method to obtain half-dose images to evaluate radiation dose and noise reduction: Phantom and human assessment using CT colonography and sinogram-affirmed iterative reconstruction (safire). J. Comput. Assist. Tomogr. 2012, 36, 560–569. DOI: https://doi.org/10.1097/RCT.0b013e318263cc1b
  19. Pickhardt, P.J.; Lubner, M.G.; Kim, D.H.; Tang, J.; Ruma, J.A.; del Rio, A.M.; Chen, G.-H. Abdominal CT with Model-Based Iterative Reconstruction (MBIR): Initial Results of a Prospective Trial Comparing Ultralow-Dose with Standard Dose Imaging. Am. J. Roentgenol. 2012, 199, 1266–1274. DOI: https://doi.org/10.2214/AJR.12.9382
  20. Litjens, G.; Kooi, T.; Bejnordi, B.E.; Setio, A.A.A.; Ciompi, F.; Ghafoorian, M.; van der Laak, J.A.W.M.; van Ginneken, B.; Sánchez, C.I. A survey on deep learning in medical image analysis. Med. Image Anal. 2017, 42, 60–88. DOI: https://doi.org/10.1016/j.media.2017.07.005
  21. Kaur, P.; Singh, G.; Kaur, P. A review of denoising medical images using machine learning approaches. Curr. Med. Imaging 2018, 14, 675–685. DOI: https://doi.org/10.2174/1573405613666170428154156
  22. Buades, A.; Coll, B.; Morel, J.M. A non-local algorithm for image denoising. In Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05), San Diego, CA, USA, 20–25 June 2005; Volume 2, pp. 60–65. DOI: https://doi.org/10.1109/CVPR.2005.38
  23. Balda, M.; Hornegger, J.; Heismann, B. Ray Contribution Masks for Structure Adaptive Sinogram Filtering. IEEE Trans. Med Imaging 2012, 31, 1228–1239. DOI: https://doi.org/10.1109/TMI.2012.2187213
  24. Mallat, S.G. A theory for multiresolution signal decomposition: The wavelet representation. IEEE Trans. Pattern Anal. Mach. Intell. 1989, 11, 674–693. DOI: https://doi.org/10.1109/34.192463
  25. Yu, F.; Chen, Y.; Luo, L. CT image denoising based on sparse representation using global dictionary. In Proceedings of the 2013 ICME International Conference on Complex Medical Engineering, Beijing, China, 25–28 May 2013; pp. 408–411. DOI: https://doi.org/10.1109/ICCME.2013.6548279
  26. Chen, Y.; Yang, Z.; Hu, Y.; Yang, G.; Zhu, Y.; Li, Y.; Luo, L.; Chen, W.; Toumoulin, C. Thoracic low-dose CT image processing using an artifact suppressed large-scale nonlocal means. Phys. Med. Biol. 2012, 57, 2667–2688. DOI: https://doi.org/10.1088/0031-9155/57/9/2667
  27. Dabov, K.; Foi, A.; Katkovnik, V.; Egiazarian, K. Image Denoising by Sparse 3-D Transform-Domain Collaborative Filtering. IEEE Trans. Image Process. 2007, 16, 2080–2095. DOI: https://doi.org/10.1109/TIP.2007.901238
  28. Hashemi, S.; Paul, N.S.; Beheshti, S.; Cobbold, R.S.C. Adaptively Tuned Iterative Low Dose CT Image Denoising. Comput. Math. Methods Med. 2015, 2015, 638568. DOI: https://doi.org/10.1155/2015/638568
  29. Ha, S.; Mueller, K. Low dose CT image restoration using a database of image patches. Phys. Med. Biol. 2015, 60, 869–882. DOI: https://doi.org/10.1088/0031-9155/60/2/869
  30. Zhang, Z.; Han, X.; Pearson, E.; Pelizzari, C.; Sidky, E.Y.; Pan, X. Artifact reduction in short-scan CBCT by use of optimization-based reconstruction. Phys. Med. Biol. 2016, 61, 3387–3406. DOI: https://doi.org/10.1088/0031-9155/61/9/3387
  31. Chen, H.; Zhang, Y.; Kalra, M.K.; 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, 2524–2535. DOI: https://doi.org/10.1109/TMI.2017.2715284
  32. Shan, H.; Padole, A.; Homayounieh, F.; Kruger, U.; Khera, R.D.; Nitiwarangkul, C.; Kalra, M.K.; Wang, G. Competitive performance of a modularized deep neural network compared to commercial algorithms for low-dose CT image reconstruction. Nat. Mach. Intell. 2019, 1, 269–276. DOI: https://doi.org/10.1038/s42256-019-0057-9
  33. Kang, E.; Chang, W.; Yoo, J.; Ye, J.C. Deep Convolutional Framelet Denosing for Low-Dose CT via Wavelet Residual Network. IEEE Trans. Med Imaging 2018, 37, 1358–1369. DOI: https://doi.org/10.1109/TMI.2018.2823756
  34. Chen, H.; Zhang, Y.; Zhang, W.; Liao, P.; Li, K.; Zhou, J.; Wang, G. Low dose CT denoising with convolutional neural network. In Proceedings of the 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017), Melbourne, VIC, Australia, 18–21 April 2017; pp. 143–146. DOI: https://doi.org/10.1109/ISBI.2017.7950488
  35. Zhang, Y.; Tian, Y.; Kong, Y.; Zhong, B.; Fu, Y. Residual dense network for image super-resolution. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 18–23 June 2018; pp. 2472–2481. DOI: https://doi.org/10.1109/CVPR.2018.00262
  36. Rai, S.; Bhatt, J.S.; Patra, S.K. Augmented Noise Learning Framework for Enhancing Medical Image Denoising. IEEE Access 2021, 9, 117153–117168. DOI: https://doi.org/10.1109/ACCESS.2021.3106707
  37. Rai, S.; Bhatt, J.S.; Patra, S.K. Accessible, affordable and low-risk lungs health monitoring in COVID-19: Deep cascade reconstruction from degraded lr-uldct. In Proceedings of the 2022 IEEE 19th International Symposium on Biomedical Imaging (ISBI), Kolkata, India, 28–31 March 2022; pp. 1–5. DOI: https://doi.org/10.1109/ISBI52829.2022.9761566
  38. Choi, K.; Vania, M.; Kim, S. Semi-supervised learning for lowdose CT image restoration with hierarchical deep generative adversarial network (hd-gan). In Proceedings of the 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Berlin, Germany, 23–27 July 2019; pp. 2683–2686. DOI: https://doi.org/10.1109/EMBC.2019.8857572
  39. Wang, L.; Gao, Q.; Meng, M.; Li, S.; Zhu, M.; Li, D.; Chen, G.; Zeng, D.; Xie, Q.; Zhao, Q.; et al. Semi-supervised noise distribution learning for low-dose CT restoration. Med. Imaging 2020 Phys. Med. Imaging 2020, 11312, 1026–1030. DOI: https://doi.org/10.1117/12.2548944
  40. Bizopoulos, P.; Vretos, N.; Daras, P. Comprehensive comparison of deep learning models for lung and COVID-19 lesion segmentation in CT scans. arXiv 2020, arXiv:2009.06412, 2020.
  41. Shahidi, F.; Daud, S.M.; Abas, H.; Ahmad, N.A.; Maarop, N. Breast Cancer Classification Using Deep Learning Approaches and Histopathology Image: A Comparison Study. IEEE Access 2020, 8, 187531–187552. DOI: https://doi.org/10.1109/ACCESS.2020.3029881
  42. Yi, X.; Babyn, P. Sharpness-Aware Low-Dose CT Denoising Using Conditional Generative Adversarial Network. J. Digit. Imaging 2018, 31, 655–669. DOI: https://doi.org/10.1007/s10278-018-0056-0
  43. Yang, Q.; Yan, P.; Zhang, Y.; Yu, H.; Shi, Y.; Mou, X.; Kalra, M.K.; 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, 1348–1357. DOI: https://doi.org/10.1109/TMI.2018.2827462
  44. Nishio, M.; Nagashima, C.; Hirabayashi, S.; Ohnishi, A.; Sasaki, K.; Sagawa, T.; Hamada, M.; Yamashita, T. Convolutional auto-encoder for image denoising of ultra-low-dose CT. Heliyon 2017, 3, e00393. DOI: https://doi.org/10.1016/j.heliyon.2017.e00393
  45. Liu, Y.; Zhang, Y. Low-dose CT restoration via stacked sparse denoising autoencoders. Neurocomputing 2018, 284, 80–89. DOI: https://doi.org/10.1016/j.neucom.2018.01.015
  46. Liu, H.; Liao, P.; Chen, H.; Zhang, Y. ERA-WGAT: Edge-enhanced residual autoencoder with a window-based graph attention convolutional network for low-dose CT denoising. Biomed. Opt. Express 2022, 13, 5775–5793. DOI: https://doi.org/10.1364/BOE.471340
  47. Wang, D.; Xu, Y.; Han, S.; Yu, H. Masked autoencoders for low-dose CT denoising. In Proceedings of the 2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI), Cartagena, Colombia, 18–21 April 2023; pp. 1–4. DOI: https://doi.org/10.1109/ISBI53787.2023.10230612
  48. Li, M.; Hsu, W.; Xie, X.; Cong, J.; Gao, W. SACNN: Self-Attention Convolutional Neural Network for Low-Dose CT Denoising With Self-Supervised Perceptual Loss Network. IEEE Trans. Med. Imaging 2020, 39, 2289–2301. DOI: https://doi.org/10.1109/TMI.2020.2968472
  49. Karimi, D.; Dou, H.; Warfield, S.K.; Gholipour, A. Deep learning with noisy labels: Exploring techniques and remedies in medical image analysis. Med. Image Anal. 2020, 65, 101759. DOI: https://doi.org/10.1016/j.media.2020.101759
  50. Vaswani, A.; Shazeer, N.; Parmar, N.; Uszkoreit, J.; Jones, L.; Gomez, A.N.; Kaiser, Ł.; Polosukhin, I. Attention is all you need. Adv. Neural Inf. Process. Syst. 2017, 30, 1–11.
  51. Luthra, A.; Sulakhe, H.; Mittal, T.; Iyer, A.; Yadav, S. Eformer: Edge enhancement based transformer for medical image denoising. arXiv 2021, arXiv:2109.08044.
  52. Yuan, J.; Zhou, F.; Guo, Z.; Li, X.; Yu, H. HCformer: Hybrid CNN-Transformer for LDCT Image Denoising. J. Digit. Imaging 2023, 36, 2290–2305. DOI: https://doi.org/10.1007/s10278-023-00842-9
  53. Chyophel Lepcha, D.; Goyal, B.; Dogra, A. Low-dose CT image denoising using sparse 3dD transformation with probabilistic non-local means for clinical applications. Imaging Sci. J. 2023, 71, 97–109. DOI: https://doi.org/10.1080/13682199.2023.2176809
  54. Othman, A.E.; Brockmann, C.; Yang, Z.; Kim, C.; Afat, S.; Pjontek, R.; Nikoubashman, O.; Brockmann, M.A.; Nikolaou, K.; Wiesmann, M.; et al. Impact of image denoising on image quality, quantitative parameters and sensitivity of ultra-low-dose volume perfusion CT imaging. Eur. Radiol. 2015, 26, 167–174. DOI: https://doi.org/10.1007/s00330-015-3853-6
  55. Kulathilake, K.A.S.H.; Abdullah, N.A.; Sabri, A.Q.M.; Lai, K.W. A review on Deep Learning approaches for low-dose Computed Tomography restoration. Complex Intell. Syst. 2021, 9, 2713–2745. DOI: https://doi.org/10.1007/s40747-021-00405-x
  56. Mück, J.; Reiter, E.; Klingert, W.; Bertolani, E.; Schenk, M.; Nikolaou, K.; Afat, S.; Brendlin, A.S. Towards safer imaging: A comparative study of deep learning-based denoising and iterative reconstruction in intraindividual low-dose CT scans using an in-vivo large animal model. Eur. J. Radiol. 2023, 171, 111267. DOI: https://doi.org/10.1016/j.ejrad.2023.111267
  57. Liang, T.; Jin, Y.; Li, Y.; Wang, T. Edcnn: Edge enhancement-based densely connected network with compound loss for low-dose CT denoising. In Proceedings of the 2020 15th IEEE International Conference on Signal Processing (ICSP), Beijing, China, 6–9 December 2020; Volume 1, pp. 193–198. DOI: https://doi.org/10.1109/ICSP48669.2020.9320928
  58. Fan, F.; Shan, H.; Kalra, M.K.; Singh, R.; Qian, G.; Getzin, M.; Teng, Y.; Hahn, J.; Wang, G. Quadratic Autoencoder (Q-AE) for Low-Dose CT Denoising. IEEE Trans. Med. Imaging 2019, 39, 2035–2050. DOI: https://doi.org/10.1109/TMI.2019.2963248
  59. Won, D.K.; An, S.; Park, S.H.; Ye, D.H. Low-dose CT denoising using octave convolution with high and low frequency bands. In Predictive Intelligence in Medicine: Third International Workshop, PRIME 2020, Held in Conjunction with MICCAI 2020, Lima, Peru, 8 October 2020; Springer: Cham, Switzerland, 2020; pp. 68–78. DOI: https://doi.org/10.1007/978-3-030-59354-4_7
  60. Wang, D.; Fan, F.; Wu, Z.; Liu, R.; Wang, F.; Yu, H. CTformer: convolution-free Token2Token dilated vision transformer for low-dose CT denoising. Phys. Med. Biol. 2023, 68, 065012. DOI: https://doi.org/10.1088/1361-6560/acc000
  61. AAPM. Low Dose CT Grand Challenge. 2017. Available online: http://www.aapm.org/grandchallenge/lowdosect/ (accessed on 2 August 2024 ).
  62. Yang, L.; Shangguan, H.; Zhang, X.; Wang, A.; Han, Z. High-Frequency Sensitive Generative Adversarial Network for Low-Dose CT Image Denoising. IEEE Access 2019, 8, 930–943. DOI: https://doi.org/10.1109/ACCESS.2019.2961983
  63. Lee, S.; Lee, M.S.; Kang, M.G. Poisson–Gaussian Noise Analysis and Estimation for Low-Dose X-ray Images in the NSCT Domain. Sensors 2018, 18, 1019. DOI: https://doi.org/10.3390/s18041019
  64. Liu, H.; Jin, X.; Liu, L. Low-Dose CT Image Denoising Based on Improved DD-Net and Local Filtered Mechanism. Comput. Intell. Neurosci. 2022, 2022, 2692301. DOI: https://doi.org/10.1155/2022/2692301
  65. Yu, X.; Wang, J.; Hong, Q.Q.; Teku, R.; Wang, S.H.; Zhang, Y.D. Transfer learning for medical images analyses: A survey. Neurocomputing 2022, 489, 230–254. DOI: https://doi.org/10.1016/j.neucom.2021.08.159
  66. Huang, C.; Wang, J.; Wang, S.H.; Zhang, Y.D. Applicable artificial intelligence for brain disease: A survey. Neurocomputing 2022, 504, 223–239. DOI: https://doi.org/10.1016/j.neucom.2022.07.005
  67. Tian, D.; Zhu, B.; Wang, J.; Kong, L.; Gao, B.; Wang, Y.; Xu, D.; Zhang, R.; Yao, Y. Brachial plexus nerve trunk recognition from ultrasound images: A comparative study of deep learning models. IEEE Access 2022, 10, 82003–82014. DOI: https://doi.org/10.1109/ACCESS.2022.3196356