WoS

Low-dose CT image denoising using Deep Convolutional Neuaral Networks With Extended Receptive Fields

Năm XB 2022 Tạp chí / Hội thảo Journal of Signal, Image and Video Processing 16, 8, 1963-1976 Đơn vị ĐTTT DOI / Link https://doi.org/10.1007/s11760-022-02157-8 ↗

Tác giả

Nguyen Thanh-Trung, Dinh-Hoan Trinh, Nguyen Linh-Trung, Marie-Luong

Tóm tắt

How to reduce dose radiation while preserving the image quality as when using standard dose is one of the most important topics in the Computed Tomography (CT) imaging domain due to quality of low dose CT (LDCT) images is often strongly affected by noise and artifacts. Recently there has been considerable interest in using deep learning as a post-processing step to improve the quality of reconstructed LDCT images. This paper first gives an overview of learning-based LDCT image denoising methods from patch-based early learning methods to state-of-the-art CNN-based ones, and then a novel CNN-based method is presented. In the proposed method, preprocessing and post-processing techniques are integrated into a dilated convolutional neural network to extend receptive fields. Hence, large distance pixels in input images will participate in enriching feature maps of the learned model and thus effectively denoises. Experimental results showed that the proposed method is light while its denoising effectiveness is competitive with well-known CNN-based models.

Tài liệu tham khảo

[1] Hounsfield, G.N.: Computerized transverse axial scanning (tomography): part 1. Description of system. Br. J. Radiol. 46(552), 1016–1022 (1973)

[2] Wang, J. et al.: Sinogram noise reduction for low-dose CT by statistics-based nonlinear filters. In: Medical Imaging 2005: Image Processing, vol. 5747, pp. 2058–2066 (2005)

[3] Hara, A.K., et al.: Iterative reconstruction technique for reducing body radiation dose at CT: feasibility study. Am. J. Roentgenol. 193(3), 764–771 (2009)

[4] Beister, M., et al.: Iterative reconstruction methods in X-ray CT. Physica Med. 28(2), 94–108 (2012)

[5] Stiller, W.: Basics of iterative reconstruction methods in computed tomography: a vendor-independent overview. Eur. J. Radiol. 109, 147–154 (2018)

[6] Buades, A., et al.: A review of image denoising algorithms, with a new one. Multiscale Model. Simul. 4(2), 490–530 (2005)

[7] Li, Z., et al.: Adaptive nonlocal means filtering based on local noise level for CT denoising. Med. Phys. 41(1), 011908 (2014)

[8] Green, M. et al.: Efficient low-dose CT denoising by locally-consistent non-local means (LC-NLM). In: Proceedings MICCAI 2016, Part III, pp. 423–431 (2016)

[9] Elad, M., Aharon, M.: Image denoising via sparse and redundant representations over learned dictionaries. IEEE Trans. Image Process. 15(2), 3736–3745 (2006)

[10] Chen, Y., et al.: Improving abdomen tumor low-dose CT images using a fast dictionary learning based processing. Phys. Med. Biol. 58(16), 5803 (2013)

[11] Chen, Y., et al.: Artifact suppressed dictionary learning for low-dose CT image processing. IEEE Trans. Med. Imag. 33(12), 2271–2292 (2014)

[12] Pizurica, A., et al.: A versatile wavelet domain noise filtration technique for medical imaging. IEEE Trans. Med. Imag. 22, 323–331 (2003)

[13] Portilla, J., et al.: Image denoising using scale mixtures of Gaussians in the wavelet domain. IEEE Trans. Image Process. 12(11), 1338–1351 (2003)

[14] Dabov, K., et al.: Image denoising by sparse 3-D transform-domain collaborative filtering. IEEE Trans. Image Process. 16(8), 2080–2095 (2007)

[15] Lu, H., et al.: Noise properties of low-dose CT projections and noise treatment by scale transformations. Nuclear Sci. Symp. 3, 1662–1666 (2001)

[16] Trinh, D.-H., et al.: Novel example-based method for super-resolution and denoising of medical images. IEEE Trans. Image Process. 23(4), 1882–1895 (2014)

[17] Chen, H., et al.: Low-dose CT with a residual encoder–decoder convolutional neural network. IEEE Trans. Med. Imag. 36(12), 2524–2535 (2017)

[18] Yang, Q., et al.: Low dose CT image denoising using a generative adversarial network with Wasserstein distance and perceptual loss. IEEE Trans. Med. Imag. 37(6), 1348–1357 (2018)

[19] Yi, X., Babyn, P.: Sharpness-aware low-dose CT denoising using conditional generative adversarial network. J. Dig. Imag. 31(5), 655–669 (2018)

[20] You, C., et al.: Structurally-sensitive multi-scale deep neural network for low-dose CT denoising. IEEE Access 6, 41839–41855 (2018)

[21] Trung, N.T. et al.: Robust denoising of low-dose CT images using convolutional neural networks. In: Proceedings of NICS, pp. 506–511 (2019)

[22] Trinh, D.H., et al.: Medical image denoising using kernel ridge regression. In: Proceedings of ICIP, pp. 1597–1600 (2011)

[23] Ma, J., et al.: Low-dose computed tomography image restoration using previous normal-dose scan. Med. Phys. 38(10), 5713–5731 (2011)

[24] Trinh, D.H., et al.: An optimal weight method for CT image denoising. J. Electron. Sci. Technol. 10(2) (2012)

[25] Araujo, A., et al.: Computing receptive fields of convolutional neural networks. Distill 4(11), e21 (2019)

[26] Zhang, K., et al.: FFDnet: toward a fast and flexible solution for CNN-based image denoising. IEEE Trans. Image Process. 27(9), 4608–4622 (2018)

[27] Zhang, Q., et al.: Learning a dilated residual network for SAR image despeckling. Rem. Sens. 10(2), 196 (2018)

[28] Kervrann, C., Boulanger, J.: Optimal spatial adaptation for patchbased image denoising. IEEE Trans. Image Process. 15, 2866–2878 (2006)

[29] Nguyen, T.-T., et al., An efficient example-based method for CT image denoising based on frequency decomposition and sparse representation. In: Proceedings of ATC, pp 293–296 (2016)

[30] Trung, N.T., et al.: Low-dose CT image denoising using image decomposition and sparse representation. REV J. Electron. Commun. 9(3–4), 78–88 (2020)

[31] Zoran,D., Weiss,Y.: From learning models of natural image patches to whole image restoration. In: Proceedings of ICCV, pp. 479–486 (2011)

[32] Burger, H.C., et al.: Learning how to combine internal and external denoising methods. Proc. GCPR 8142, 121–130 (2013)

[33] Luo, E.: et al., Adaptive image denoising by targeted databases. IEEE Trans. Image Process. 24(7), 2167–2181 (2015)

[34] Jain, V., Seung, H.S.: Natural image denoising with convolutional networks. In: NIPS, pp. 769–776 (2008)

[35] Li, D.: Support vector regression based image denoising. Image Vis. Comput. 27(6), 623–627 (2009)

[36] Burger, H.C., et al. Image denoising: can plain neural networks compete with BM3D? In: Proceedings of CVPR, pp. 2392–2399 (2012)

[37] Trinh, D.H., et al.: An effective example-based denoising method for CT images using Markov random field. In: Proceedings of ATC, pp. 355–359 (2014)

[38] Zhang, K., et al.: Beyond a gaussian denoiser: residual learning of deep CNN for image denoising. IEEE Trans. Image Process. 26(7), 3142–3155 (2017)

[39] Yue, Z. et al. (2019) Variational denoising network: toward blind noise modeling and removal. In: Proceedings of NeurIPS, pp. 1688–1699 (2019)

[40] Anwar, S., Barnes, N.: Real image denoising with feature attention. In: Proceedings of ICCV, pp. 3155–3164 (2019)

[41] NIH, AAPM, and Mayo Clinic, Low dose CT grand challenge (2016)

[42] Leuschner, J., et al.: LoDoPaB-CT, a benchmark dataset for low-dose computed tomography reconstruction. Sci. Data 8(109), 1–12 (2021)

[43] Mao, X.-J. et al.: Image restoration using very deep convolutional encoder-decoder networks with symmetric skip connections. arXiv:1603.09056 (2016)

[44] Ronneberger, O., et al.: U-net: Convolutional networks for biomedical image segmentation. In: Proceedings of MICCAI, vol. 9351, pp. 234–241 (2015)

[45] Li, M., et al.: SACNN: self-attention convolutional neural network for low-dose CT denoising with self-supervised perceptual loss network. IEEE Trans. Med. Imag. 39(7), 2289–2301 (2020)

[46] Shan, H., et al.: Correction for 3D convolutional encoder-decoder network for low-dose CT via transfer learning from a 2D trained network. IEEE Trans. Med. Imag. 37(12), 2750 (2018)

[47] Goodfellow, I.J. et al.: Generative adversarial networks. arXiv preprint arXiv:1406.2661 (2014)

[48] Arjovsky, M. et al.: Wasserstein GAN. arXiv:1701.07875 (2017)

[49] Du, W., et al.: Visual attention network for low-dose CT. IEEE Sig. Process. Let. 26(8), 1152–1156 (2019)

[50] Dalmaz, O. et al.: ResViT: Residual vision transformers for multi-modal medical image synthesis. arXiv preprint arXiv:2106.16031 (2021)

[51] Korkmaz Y. et al.: Unsupervised MRI reconstruction via zero-shot learned adversarial transformers. arXiv preprint arXiv:2105.08059 (2021)

[52] Chen, J. et al.: Transunet: transformers make strong encoders for medical image segmentation. arXiv preprint arXiv:2102.04306 (2021)

[53] Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolutions. In: Proceedings of ICLR (2016)

[54] Simonyan, K. , Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: Proceedings of ICLR (2015)

[55] Kang, D. et al.: Image denoising of low-radiation dose coronary CT angiography by an adaptive block-matching 3D algorithm. In: Medical Imaging 2013: Image Process, 86692G (2013)

[56] Wang, Z., et al.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600–612 (2004)

[57] Zhang, L., et al.: FSIM: a feature similarity index for image quality assessment. IEEE Trans. Image Process. 20(8), 2378–2386 (2011)

[58] Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv:1412.6980 (2014)

[59] Wang, J., et al.: Penalized weighted least-squares approach to Sinogram noise reduction and image reconstruction for low-dose X-ray computed tomography. IEEE Trans. Med. Imag. 25(10), 1272–1283 (2006)

← Quay lại danh sách bài báo