Abstract

Speckle noise in optical coherence tomography (OCT) impairs both the visual quality and the performance of automatic analysis. Edge preservation is an important issue for speckle reduction. In this paper, we propose an end-to-end framework for simultaneous speckle reduction and contrast enhancement for retinal OCT images based on the conditional generative adversarial network (cGAN). The edge loss function is added to the final objective so that the model is sensitive to the edge-related details. We also propose a novel method for obtaining clean images for training from outputs of commercial OCT scanners. The results show that the overall denoising performance of the proposed method is better than other traditional methods and deep learning methods. The proposed model also has good generalization ability and is capable of despeckling different types of retinal OCT images.

© 2018 Optical Society of America under the terms of the OSA Open Access Publishing Agreement

Full Article  |  PDF Article
OSA Recommended Articles
Speckle noise reduction algorithm with total variation regularization in optical coherence tomography

Guanghua Gong, Hongming Zhang, and Minyu Yao
Opt. Express 23(19) 24699-24712 (2015)

General Bayesian estimation for speckle noise reduction in optical coherence tomography retinal imagery

Alexander Wong, Akshaya Mishra, Kostadinka Bizheva, and David A. Clausi
Opt. Express 18(8) 8338-8352 (2010)

Gabor-based anisotropic diffusion for speckle noise reduction in medical ultrasonography

Qi Zhang, Hong Han, Chunhong Ji, Jinhua Yu, Yuanyuan Wang, and Wenping Wang
J. Opt. Soc. Am. A 31(6) 1273-1283 (2014)

References

  • View by:
  • |
  • |
  • |

  1. J. M. Schmitt, S. H. Xiang, and K. M. Yung, “Speckle in optical coherence tomography,” J. Biomed. Opt. 4(1), 95–105 (1999).
    [Crossref] [PubMed]
  2. H. M. Salinas and D. C. Fernández, “Comparison of PDE-based nonlinear diffusion approaches for image enhancement and denoising in optical coherence tomography,” IEEE Trans. Med. Imaging 26(6), 761–771 (2007).
    [Crossref] [PubMed]
  3. P. Puvanathasan and K. Bizheva, “Interval type-II fuzzy anisotropic diffusion algorithm for speckle noise reduction in optical coherence tomography images,” Opt. Express 17(2), 733–746 (2009).
    [Crossref] [PubMed]
  4. J. Aum, J. H. Kim, and J. Jeong, “Effective speckle noise suppression in optical coherence tomography images using nonlocal means denoising filter with double Gaussian anisotropic kernels,” Appl. Opt. 54(13), 13–14 (2015).
  5. X. Zhang, L. Li, F. Zhu, W. Hou, and X. Chen, “Spiking cortical model-based nonlocal means method for speckle reduction in optical coherence tomography images,” J. Biomed. Opt. 19(6), 066005 (2014).
    [Crossref] [PubMed]
  6. B. Chong and Y. K. Zhu, “Speckle reduction in optical coherence tomography images of human finger skin by wavelet modified BM3D filter,” Opt. Commun. 291(6), 461–469 (2013).
    [Crossref]
  7. F. Zaki, Y. Wang, H. Su, X. Yuan, and X. Liu, “Noise adaptive wavelet thresholding for speckle noise removal in optical coherence tomography,” Biomed. Opt. Express 8(5), 2720–2731 (2017).
    [Crossref] [PubMed]
  8. R. Kafieh, H. Rabbani, and I. Selesnick, “Three dimensional data-driven multi scale atomic representation of optical coherence tomography,” IEEE Trans. Med. Imaging 34(5), 1042–1062 (2015).
    [Crossref] [PubMed]
  9. Z. Jian, L. Yu, B. Rao, B. J. Tromberg, and Z. Chen, “Three-dimensional speckle suppression in Optical Coherence Tomography based on the curvelet transform,” Opt. Express 18(2), 1024–1032 (2010).
    [Crossref] [PubMed]
  10. L. Fang, S. Li, Q. Nie, J. A. Izatt, C. A. Toth, and S. Farsiu, “Sparsity based denoising of spectral domain optical coherence tomography images,” Biomed. Opt. Express 3(5), 927–942 (2012).
    [Crossref] [PubMed]
  11. L. Fang, S. Li, D. Cunefare, and S. Farsiu, “Segmentation based sparse reconstruction of optical coherence tomography images,” IEEE Trans. Med. Imaging 36(2), 407–421 (2017).
    [Crossref] [PubMed]
  12. A. Wong, A. Mishra, K. Bizheva, and D. A. Clausi, “General Bayesian estimation for speckle noise reduction in optical coherence tomography retinal imagery,” Opt. Express 18(8), 8338–8352 (2010).
    [Crossref] [PubMed]
  13. A. Cameron, D. Lui, A. Boroomand, J. Glaister, A. Wong, and K. Bizheva, “Stochastic speckle noise compensation in optical coherence tomography using non-stationary spline-based speckle noise modelling,” Biomed. Opt. Express 4(9), 1769–1785 (2013).
    [Crossref] [PubMed]
  14. M. Li, R. Idoughi, B. Choudhury, and W. Heidrich, “Statistical model for OCT image denoising,” Biomed. Opt. Express 8(9), 3903–3917 (2017).
    [Crossref] [PubMed]
  15. I. Kopriva, F. Shi, and X. Chen, “Enhanced low-rank + sparsity decomposition for speckle reduction in optical coherence tomography,” J. Biomed. Opt. 21(7), 076008 (2016).
    [Crossref] [PubMed]
  16. C. D. Tao, Y. Quan, D. W. K. Wong, G. C. M. Cheung, M. Akiba, and J. Liu, “Speckle reduction in 3d optical coherence tomography of retina by a-scan reconstruction,” IEEE Trans. Med. Imaging 35(10), 2270–2279 (2016).
    [Crossref] [PubMed]
  17. X. J. Mao, C. Shen, and Y. B. Yang, “Image restoration using very deep convolutional encoder-decoder networks with symmetric skip connections,” In Proceedings of International Conference on Neural Information Processing Systems (NIPS), (2016).
  18. Y. Tai, J. Yang, X. Liu, and C. Xu, “MemNet: a persistent memory network for image restoration,” In Proceedings of IEEE International Conference on Computer Vision (ICCV), 4549–4557(2017).
  19. K. Zhang, W. Zuo, Y. Chen, D. Meng, and L. Zhang, “Beyond a Gaussian denoiser: residual learning of deep CNN for image denoising,” IEEE Trans. Image Process. 26(7), 3142–3155 (2017).
    [Crossref] [PubMed]
  20. N. Cai, F. Shi, Y. Gu, D. Hu, Y. Chen, and X. Chen, “A ResNet-based universal method for speckle reduction in optical coherence tomography images,” In Proceedings of IEEE International Symposium on Biomedical Imaging (ISBI), (2018).
  21. P. Isola, J. Y. Zhu, T. Zhou, and A. A. Efros, “Image-to-image translation with conditional adversarial networks,” In Proceedings of Computer Vision and Pattern Recognition (CVPR), 5967–5976(2017).
    [Crossref]
  22. O. Ronneberger, P. Fischer, and T. Brox, “U-Net: convolutional networks for biomedical image segmentation,” In Proceedings of Medical Image Computing and Computer-Assisted Intervention (MICCAI), 234–241(2015).
  23. S. Ioffe and C. Szegedy, “Batch Normalization: accelerating deep network training by reducing internal covariate shift,” arXiv:1502.03167v3, (2015).
  24. I. J. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio, “Generative adversarial nets,” In proceedings of International Conference on Neural Information Processing Systems(NIPS), 2672–2680(2014).
  25. Z. Wang, A. C. Bovik, H. R. Sheikh, and E. P. Simoncelli, “Image quality assessment: from error visibility to structural similarity,” IEEE Trans. Image Process. 13(4), 600–612 (2004).
    [Crossref] [PubMed]
  26. A. Buades, B. Coll, and J. M. Morel, “A non-local algorithm for image denoising,” In Proceedings of Computer Vision and Pattern Recognition (CVPR), 60–65 (2005).
    [Crossref]
  27. K. Dabov, A. Foi, V. Katkovnik, and K. Egiazarian, “Image denoising by sparse 3-D transform-domain collaborative filtering,” IEEE Trans. Image Process. 16(8), 2080–2095 (2007).
    [Crossref] [PubMed]
  28. B. Wen, Y. Li, and Y. Bresler, “When sparsity meets low-rankness: transform learning with non-local low-rank constraint for image restoration,” In proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing(ICASSP), 2297–2301(2017).

2017 (4)

F. Zaki, Y. Wang, H. Su, X. Yuan, and X. Liu, “Noise adaptive wavelet thresholding for speckle noise removal in optical coherence tomography,” Biomed. Opt. Express 8(5), 2720–2731 (2017).
[Crossref] [PubMed]

L. Fang, S. Li, D. Cunefare, and S. Farsiu, “Segmentation based sparse reconstruction of optical coherence tomography images,” IEEE Trans. Med. Imaging 36(2), 407–421 (2017).
[Crossref] [PubMed]

M. Li, R. Idoughi, B. Choudhury, and W. Heidrich, “Statistical model for OCT image denoising,” Biomed. Opt. Express 8(9), 3903–3917 (2017).
[Crossref] [PubMed]

K. Zhang, W. Zuo, Y. Chen, D. Meng, and L. Zhang, “Beyond a Gaussian denoiser: residual learning of deep CNN for image denoising,” IEEE Trans. Image Process. 26(7), 3142–3155 (2017).
[Crossref] [PubMed]

2016 (2)

I. Kopriva, F. Shi, and X. Chen, “Enhanced low-rank + sparsity decomposition for speckle reduction in optical coherence tomography,” J. Biomed. Opt. 21(7), 076008 (2016).
[Crossref] [PubMed]

C. D. Tao, Y. Quan, D. W. K. Wong, G. C. M. Cheung, M. Akiba, and J. Liu, “Speckle reduction in 3d optical coherence tomography of retina by a-scan reconstruction,” IEEE Trans. Med. Imaging 35(10), 2270–2279 (2016).
[Crossref] [PubMed]

2015 (2)

R. Kafieh, H. Rabbani, and I. Selesnick, “Three dimensional data-driven multi scale atomic representation of optical coherence tomography,” IEEE Trans. Med. Imaging 34(5), 1042–1062 (2015).
[Crossref] [PubMed]

J. Aum, J. H. Kim, and J. Jeong, “Effective speckle noise suppression in optical coherence tomography images using nonlocal means denoising filter with double Gaussian anisotropic kernels,” Appl. Opt. 54(13), 13–14 (2015).

2014 (1)

X. Zhang, L. Li, F. Zhu, W. Hou, and X. Chen, “Spiking cortical model-based nonlocal means method for speckle reduction in optical coherence tomography images,” J. Biomed. Opt. 19(6), 066005 (2014).
[Crossref] [PubMed]

2013 (2)

2012 (1)

2010 (2)

2009 (1)

2007 (2)

H. M. Salinas and D. C. Fernández, “Comparison of PDE-based nonlinear diffusion approaches for image enhancement and denoising in optical coherence tomography,” IEEE Trans. Med. Imaging 26(6), 761–771 (2007).
[Crossref] [PubMed]

K. Dabov, A. Foi, V. Katkovnik, and K. Egiazarian, “Image denoising by sparse 3-D transform-domain collaborative filtering,” IEEE Trans. Image Process. 16(8), 2080–2095 (2007).
[Crossref] [PubMed]

2004 (1)

Z. Wang, A. C. Bovik, H. R. Sheikh, and E. P. Simoncelli, “Image quality assessment: from error visibility to structural similarity,” IEEE Trans. Image Process. 13(4), 600–612 (2004).
[Crossref] [PubMed]

1999 (1)

J. M. Schmitt, S. H. Xiang, and K. M. Yung, “Speckle in optical coherence tomography,” J. Biomed. Opt. 4(1), 95–105 (1999).
[Crossref] [PubMed]

Akiba, M.

C. D. Tao, Y. Quan, D. W. K. Wong, G. C. M. Cheung, M. Akiba, and J. Liu, “Speckle reduction in 3d optical coherence tomography of retina by a-scan reconstruction,” IEEE Trans. Med. Imaging 35(10), 2270–2279 (2016).
[Crossref] [PubMed]

Aum, J.

J. Aum, J. H. Kim, and J. Jeong, “Effective speckle noise suppression in optical coherence tomography images using nonlocal means denoising filter with double Gaussian anisotropic kernels,” Appl. Opt. 54(13), 13–14 (2015).

Bengio, Y.

I. J. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio, “Generative adversarial nets,” In proceedings of International Conference on Neural Information Processing Systems(NIPS), 2672–2680(2014).

Bizheva, K.

Boroomand, A.

Bovik, A. C.

Z. Wang, A. C. Bovik, H. R. Sheikh, and E. P. Simoncelli, “Image quality assessment: from error visibility to structural similarity,” IEEE Trans. Image Process. 13(4), 600–612 (2004).
[Crossref] [PubMed]

Bresler, Y.

B. Wen, Y. Li, and Y. Bresler, “When sparsity meets low-rankness: transform learning with non-local low-rank constraint for image restoration,” In proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing(ICASSP), 2297–2301(2017).

Cai, N.

N. Cai, F. Shi, Y. Gu, D. Hu, Y. Chen, and X. Chen, “A ResNet-based universal method for speckle reduction in optical coherence tomography images,” In Proceedings of IEEE International Symposium on Biomedical Imaging (ISBI), (2018).

Cameron, A.

Chen, X.

I. Kopriva, F. Shi, and X. Chen, “Enhanced low-rank + sparsity decomposition for speckle reduction in optical coherence tomography,” J. Biomed. Opt. 21(7), 076008 (2016).
[Crossref] [PubMed]

X. Zhang, L. Li, F. Zhu, W. Hou, and X. Chen, “Spiking cortical model-based nonlocal means method for speckle reduction in optical coherence tomography images,” J. Biomed. Opt. 19(6), 066005 (2014).
[Crossref] [PubMed]

N. Cai, F. Shi, Y. Gu, D. Hu, Y. Chen, and X. Chen, “A ResNet-based universal method for speckle reduction in optical coherence tomography images,” In Proceedings of IEEE International Symposium on Biomedical Imaging (ISBI), (2018).

Chen, Y.

K. Zhang, W. Zuo, Y. Chen, D. Meng, and L. Zhang, “Beyond a Gaussian denoiser: residual learning of deep CNN for image denoising,” IEEE Trans. Image Process. 26(7), 3142–3155 (2017).
[Crossref] [PubMed]

N. Cai, F. Shi, Y. Gu, D. Hu, Y. Chen, and X. Chen, “A ResNet-based universal method for speckle reduction in optical coherence tomography images,” In Proceedings of IEEE International Symposium on Biomedical Imaging (ISBI), (2018).

Chen, Z.

Cheung, G. C. M.

C. D. Tao, Y. Quan, D. W. K. Wong, G. C. M. Cheung, M. Akiba, and J. Liu, “Speckle reduction in 3d optical coherence tomography of retina by a-scan reconstruction,” IEEE Trans. Med. Imaging 35(10), 2270–2279 (2016).
[Crossref] [PubMed]

Chong, B.

B. Chong and Y. K. Zhu, “Speckle reduction in optical coherence tomography images of human finger skin by wavelet modified BM3D filter,” Opt. Commun. 291(6), 461–469 (2013).
[Crossref]

Choudhury, B.

Clausi, D. A.

Courville, A.

I. J. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio, “Generative adversarial nets,” In proceedings of International Conference on Neural Information Processing Systems(NIPS), 2672–2680(2014).

Cunefare, D.

L. Fang, S. Li, D. Cunefare, and S. Farsiu, “Segmentation based sparse reconstruction of optical coherence tomography images,” IEEE Trans. Med. Imaging 36(2), 407–421 (2017).
[Crossref] [PubMed]

Dabov, K.

K. Dabov, A. Foi, V. Katkovnik, and K. Egiazarian, “Image denoising by sparse 3-D transform-domain collaborative filtering,” IEEE Trans. Image Process. 16(8), 2080–2095 (2007).
[Crossref] [PubMed]

Egiazarian, K.

K. Dabov, A. Foi, V. Katkovnik, and K. Egiazarian, “Image denoising by sparse 3-D transform-domain collaborative filtering,” IEEE Trans. Image Process. 16(8), 2080–2095 (2007).
[Crossref] [PubMed]

Fang, L.

L. Fang, S. Li, D. Cunefare, and S. Farsiu, “Segmentation based sparse reconstruction of optical coherence tomography images,” IEEE Trans. Med. Imaging 36(2), 407–421 (2017).
[Crossref] [PubMed]

L. Fang, S. Li, Q. Nie, J. A. Izatt, C. A. Toth, and S. Farsiu, “Sparsity based denoising of spectral domain optical coherence tomography images,” Biomed. Opt. Express 3(5), 927–942 (2012).
[Crossref] [PubMed]

Farsiu, S.

L. Fang, S. Li, D. Cunefare, and S. Farsiu, “Segmentation based sparse reconstruction of optical coherence tomography images,” IEEE Trans. Med. Imaging 36(2), 407–421 (2017).
[Crossref] [PubMed]

L. Fang, S. Li, Q. Nie, J. A. Izatt, C. A. Toth, and S. Farsiu, “Sparsity based denoising of spectral domain optical coherence tomography images,” Biomed. Opt. Express 3(5), 927–942 (2012).
[Crossref] [PubMed]

Fernández, D. C.

H. M. Salinas and D. C. Fernández, “Comparison of PDE-based nonlinear diffusion approaches for image enhancement and denoising in optical coherence tomography,” IEEE Trans. Med. Imaging 26(6), 761–771 (2007).
[Crossref] [PubMed]

Foi, A.

K. Dabov, A. Foi, V. Katkovnik, and K. Egiazarian, “Image denoising by sparse 3-D transform-domain collaborative filtering,” IEEE Trans. Image Process. 16(8), 2080–2095 (2007).
[Crossref] [PubMed]

Glaister, J.

Goodfellow, I. J.

I. J. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio, “Generative adversarial nets,” In proceedings of International Conference on Neural Information Processing Systems(NIPS), 2672–2680(2014).

Gu, Y.

N. Cai, F. Shi, Y. Gu, D. Hu, Y. Chen, and X. Chen, “A ResNet-based universal method for speckle reduction in optical coherence tomography images,” In Proceedings of IEEE International Symposium on Biomedical Imaging (ISBI), (2018).

Heidrich, W.

Hou, W.

X. Zhang, L. Li, F. Zhu, W. Hou, and X. Chen, “Spiking cortical model-based nonlocal means method for speckle reduction in optical coherence tomography images,” J. Biomed. Opt. 19(6), 066005 (2014).
[Crossref] [PubMed]

Hu, D.

N. Cai, F. Shi, Y. Gu, D. Hu, Y. Chen, and X. Chen, “A ResNet-based universal method for speckle reduction in optical coherence tomography images,” In Proceedings of IEEE International Symposium on Biomedical Imaging (ISBI), (2018).

Idoughi, R.

Izatt, J. A.

Jeong, J.

J. Aum, J. H. Kim, and J. Jeong, “Effective speckle noise suppression in optical coherence tomography images using nonlocal means denoising filter with double Gaussian anisotropic kernels,” Appl. Opt. 54(13), 13–14 (2015).

Jian, Z.

Kafieh, R.

R. Kafieh, H. Rabbani, and I. Selesnick, “Three dimensional data-driven multi scale atomic representation of optical coherence tomography,” IEEE Trans. Med. Imaging 34(5), 1042–1062 (2015).
[Crossref] [PubMed]

Katkovnik, V.

K. Dabov, A. Foi, V. Katkovnik, and K. Egiazarian, “Image denoising by sparse 3-D transform-domain collaborative filtering,” IEEE Trans. Image Process. 16(8), 2080–2095 (2007).
[Crossref] [PubMed]

Kim, J. H.

J. Aum, J. H. Kim, and J. Jeong, “Effective speckle noise suppression in optical coherence tomography images using nonlocal means denoising filter with double Gaussian anisotropic kernels,” Appl. Opt. 54(13), 13–14 (2015).

Kopriva, I.

I. Kopriva, F. Shi, and X. Chen, “Enhanced low-rank + sparsity decomposition for speckle reduction in optical coherence tomography,” J. Biomed. Opt. 21(7), 076008 (2016).
[Crossref] [PubMed]

Li, L.

X. Zhang, L. Li, F. Zhu, W. Hou, and X. Chen, “Spiking cortical model-based nonlocal means method for speckle reduction in optical coherence tomography images,” J. Biomed. Opt. 19(6), 066005 (2014).
[Crossref] [PubMed]

Li, M.

Li, S.

L. Fang, S. Li, D. Cunefare, and S. Farsiu, “Segmentation based sparse reconstruction of optical coherence tomography images,” IEEE Trans. Med. Imaging 36(2), 407–421 (2017).
[Crossref] [PubMed]

L. Fang, S. Li, Q. Nie, J. A. Izatt, C. A. Toth, and S. Farsiu, “Sparsity based denoising of spectral domain optical coherence tomography images,” Biomed. Opt. Express 3(5), 927–942 (2012).
[Crossref] [PubMed]

Li, Y.

B. Wen, Y. Li, and Y. Bresler, “When sparsity meets low-rankness: transform learning with non-local low-rank constraint for image restoration,” In proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing(ICASSP), 2297–2301(2017).

Liu, J.

C. D. Tao, Y. Quan, D. W. K. Wong, G. C. M. Cheung, M. Akiba, and J. Liu, “Speckle reduction in 3d optical coherence tomography of retina by a-scan reconstruction,” IEEE Trans. Med. Imaging 35(10), 2270–2279 (2016).
[Crossref] [PubMed]

Liu, X.

F. Zaki, Y. Wang, H. Su, X. Yuan, and X. Liu, “Noise adaptive wavelet thresholding for speckle noise removal in optical coherence tomography,” Biomed. Opt. Express 8(5), 2720–2731 (2017).
[Crossref] [PubMed]

Y. Tai, J. Yang, X. Liu, and C. Xu, “MemNet: a persistent memory network for image restoration,” In Proceedings of IEEE International Conference on Computer Vision (ICCV), 4549–4557(2017).

Lui, D.

Mao, X. J.

X. J. Mao, C. Shen, and Y. B. Yang, “Image restoration using very deep convolutional encoder-decoder networks with symmetric skip connections,” In Proceedings of International Conference on Neural Information Processing Systems (NIPS), (2016).

Meng, D.

K. Zhang, W. Zuo, Y. Chen, D. Meng, and L. Zhang, “Beyond a Gaussian denoiser: residual learning of deep CNN for image denoising,” IEEE Trans. Image Process. 26(7), 3142–3155 (2017).
[Crossref] [PubMed]

Mirza, M.

I. J. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio, “Generative adversarial nets,” In proceedings of International Conference on Neural Information Processing Systems(NIPS), 2672–2680(2014).

Mishra, A.

Nie, Q.

Ozair, S.

I. J. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio, “Generative adversarial nets,” In proceedings of International Conference on Neural Information Processing Systems(NIPS), 2672–2680(2014).

Pouget-Abadie, J.

I. J. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio, “Generative adversarial nets,” In proceedings of International Conference on Neural Information Processing Systems(NIPS), 2672–2680(2014).

Puvanathasan, P.

Quan, Y.

C. D. Tao, Y. Quan, D. W. K. Wong, G. C. M. Cheung, M. Akiba, and J. Liu, “Speckle reduction in 3d optical coherence tomography of retina by a-scan reconstruction,” IEEE Trans. Med. Imaging 35(10), 2270–2279 (2016).
[Crossref] [PubMed]

Rabbani, H.

R. Kafieh, H. Rabbani, and I. Selesnick, “Three dimensional data-driven multi scale atomic representation of optical coherence tomography,” IEEE Trans. Med. Imaging 34(5), 1042–1062 (2015).
[Crossref] [PubMed]

Rao, B.

Salinas, H. M.

H. M. Salinas and D. C. Fernández, “Comparison of PDE-based nonlinear diffusion approaches for image enhancement and denoising in optical coherence tomography,” IEEE Trans. Med. Imaging 26(6), 761–771 (2007).
[Crossref] [PubMed]

Schmitt, J. M.

J. M. Schmitt, S. H. Xiang, and K. M. Yung, “Speckle in optical coherence tomography,” J. Biomed. Opt. 4(1), 95–105 (1999).
[Crossref] [PubMed]

Selesnick, I.

R. Kafieh, H. Rabbani, and I. Selesnick, “Three dimensional data-driven multi scale atomic representation of optical coherence tomography,” IEEE Trans. Med. Imaging 34(5), 1042–1062 (2015).
[Crossref] [PubMed]

Sheikh, H. R.

Z. Wang, A. C. Bovik, H. R. Sheikh, and E. P. Simoncelli, “Image quality assessment: from error visibility to structural similarity,” IEEE Trans. Image Process. 13(4), 600–612 (2004).
[Crossref] [PubMed]

Shen, C.

X. J. Mao, C. Shen, and Y. B. Yang, “Image restoration using very deep convolutional encoder-decoder networks with symmetric skip connections,” In Proceedings of International Conference on Neural Information Processing Systems (NIPS), (2016).

Shi, F.

I. Kopriva, F. Shi, and X. Chen, “Enhanced low-rank + sparsity decomposition for speckle reduction in optical coherence tomography,” J. Biomed. Opt. 21(7), 076008 (2016).
[Crossref] [PubMed]

N. Cai, F. Shi, Y. Gu, D. Hu, Y. Chen, and X. Chen, “A ResNet-based universal method for speckle reduction in optical coherence tomography images,” In Proceedings of IEEE International Symposium on Biomedical Imaging (ISBI), (2018).

Simoncelli, E. P.

Z. Wang, A. C. Bovik, H. R. Sheikh, and E. P. Simoncelli, “Image quality assessment: from error visibility to structural similarity,” IEEE Trans. Image Process. 13(4), 600–612 (2004).
[Crossref] [PubMed]

Su, H.

Tai, Y.

Y. Tai, J. Yang, X. Liu, and C. Xu, “MemNet: a persistent memory network for image restoration,” In Proceedings of IEEE International Conference on Computer Vision (ICCV), 4549–4557(2017).

Tao, C. D.

C. D. Tao, Y. Quan, D. W. K. Wong, G. C. M. Cheung, M. Akiba, and J. Liu, “Speckle reduction in 3d optical coherence tomography of retina by a-scan reconstruction,” IEEE Trans. Med. Imaging 35(10), 2270–2279 (2016).
[Crossref] [PubMed]

Toth, C. A.

Tromberg, B. J.

Wang, Y.

Wang, Z.

Z. Wang, A. C. Bovik, H. R. Sheikh, and E. P. Simoncelli, “Image quality assessment: from error visibility to structural similarity,” IEEE Trans. Image Process. 13(4), 600–612 (2004).
[Crossref] [PubMed]

Warde-Farley, D.

I. J. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio, “Generative adversarial nets,” In proceedings of International Conference on Neural Information Processing Systems(NIPS), 2672–2680(2014).

Wen, B.

B. Wen, Y. Li, and Y. Bresler, “When sparsity meets low-rankness: transform learning with non-local low-rank constraint for image restoration,” In proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing(ICASSP), 2297–2301(2017).

Wong, A.

Wong, D. W. K.

C. D. Tao, Y. Quan, D. W. K. Wong, G. C. M. Cheung, M. Akiba, and J. Liu, “Speckle reduction in 3d optical coherence tomography of retina by a-scan reconstruction,” IEEE Trans. Med. Imaging 35(10), 2270–2279 (2016).
[Crossref] [PubMed]

Xiang, S. H.

J. M. Schmitt, S. H. Xiang, and K. M. Yung, “Speckle in optical coherence tomography,” J. Biomed. Opt. 4(1), 95–105 (1999).
[Crossref] [PubMed]

Xu, B.

I. J. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio, “Generative adversarial nets,” In proceedings of International Conference on Neural Information Processing Systems(NIPS), 2672–2680(2014).

Xu, C.

Y. Tai, J. Yang, X. Liu, and C. Xu, “MemNet: a persistent memory network for image restoration,” In Proceedings of IEEE International Conference on Computer Vision (ICCV), 4549–4557(2017).

Yang, J.

Y. Tai, J. Yang, X. Liu, and C. Xu, “MemNet: a persistent memory network for image restoration,” In Proceedings of IEEE International Conference on Computer Vision (ICCV), 4549–4557(2017).

Yang, Y. B.

X. J. Mao, C. Shen, and Y. B. Yang, “Image restoration using very deep convolutional encoder-decoder networks with symmetric skip connections,” In Proceedings of International Conference on Neural Information Processing Systems (NIPS), (2016).

Yu, L.

Yuan, X.

Yung, K. M.

J. M. Schmitt, S. H. Xiang, and K. M. Yung, “Speckle in optical coherence tomography,” J. Biomed. Opt. 4(1), 95–105 (1999).
[Crossref] [PubMed]

Zaki, F.

Zhang, K.

K. Zhang, W. Zuo, Y. Chen, D. Meng, and L. Zhang, “Beyond a Gaussian denoiser: residual learning of deep CNN for image denoising,” IEEE Trans. Image Process. 26(7), 3142–3155 (2017).
[Crossref] [PubMed]

Zhang, L.

K. Zhang, W. Zuo, Y. Chen, D. Meng, and L. Zhang, “Beyond a Gaussian denoiser: residual learning of deep CNN for image denoising,” IEEE Trans. Image Process. 26(7), 3142–3155 (2017).
[Crossref] [PubMed]

Zhang, X.

X. Zhang, L. Li, F. Zhu, W. Hou, and X. Chen, “Spiking cortical model-based nonlocal means method for speckle reduction in optical coherence tomography images,” J. Biomed. Opt. 19(6), 066005 (2014).
[Crossref] [PubMed]

Zhu, F.

X. Zhang, L. Li, F. Zhu, W. Hou, and X. Chen, “Spiking cortical model-based nonlocal means method for speckle reduction in optical coherence tomography images,” J. Biomed. Opt. 19(6), 066005 (2014).
[Crossref] [PubMed]

Zhu, Y. K.

B. Chong and Y. K. Zhu, “Speckle reduction in optical coherence tomography images of human finger skin by wavelet modified BM3D filter,” Opt. Commun. 291(6), 461–469 (2013).
[Crossref]

Zuo, W.

K. Zhang, W. Zuo, Y. Chen, D. Meng, and L. Zhang, “Beyond a Gaussian denoiser: residual learning of deep CNN for image denoising,” IEEE Trans. Image Process. 26(7), 3142–3155 (2017).
[Crossref] [PubMed]

Appl. Opt. (1)

J. Aum, J. H. Kim, and J. Jeong, “Effective speckle noise suppression in optical coherence tomography images using nonlocal means denoising filter with double Gaussian anisotropic kernels,” Appl. Opt. 54(13), 13–14 (2015).

Biomed. Opt. Express (4)

IEEE Trans. Image Process. (3)

K. Zhang, W. Zuo, Y. Chen, D. Meng, and L. Zhang, “Beyond a Gaussian denoiser: residual learning of deep CNN for image denoising,” IEEE Trans. Image Process. 26(7), 3142–3155 (2017).
[Crossref] [PubMed]

Z. Wang, A. C. Bovik, H. R. Sheikh, and E. P. Simoncelli, “Image quality assessment: from error visibility to structural similarity,” IEEE Trans. Image Process. 13(4), 600–612 (2004).
[Crossref] [PubMed]

K. Dabov, A. Foi, V. Katkovnik, and K. Egiazarian, “Image denoising by sparse 3-D transform-domain collaborative filtering,” IEEE Trans. Image Process. 16(8), 2080–2095 (2007).
[Crossref] [PubMed]

IEEE Trans. Med. Imaging (4)

C. D. Tao, Y. Quan, D. W. K. Wong, G. C. M. Cheung, M. Akiba, and J. Liu, “Speckle reduction in 3d optical coherence tomography of retina by a-scan reconstruction,” IEEE Trans. Med. Imaging 35(10), 2270–2279 (2016).
[Crossref] [PubMed]

L. Fang, S. Li, D. Cunefare, and S. Farsiu, “Segmentation based sparse reconstruction of optical coherence tomography images,” IEEE Trans. Med. Imaging 36(2), 407–421 (2017).
[Crossref] [PubMed]

R. Kafieh, H. Rabbani, and I. Selesnick, “Three dimensional data-driven multi scale atomic representation of optical coherence tomography,” IEEE Trans. Med. Imaging 34(5), 1042–1062 (2015).
[Crossref] [PubMed]

H. M. Salinas and D. C. Fernández, “Comparison of PDE-based nonlinear diffusion approaches for image enhancement and denoising in optical coherence tomography,” IEEE Trans. Med. Imaging 26(6), 761–771 (2007).
[Crossref] [PubMed]

J. Biomed. Opt. (3)

X. Zhang, L. Li, F. Zhu, W. Hou, and X. Chen, “Spiking cortical model-based nonlocal means method for speckle reduction in optical coherence tomography images,” J. Biomed. Opt. 19(6), 066005 (2014).
[Crossref] [PubMed]

I. Kopriva, F. Shi, and X. Chen, “Enhanced low-rank + sparsity decomposition for speckle reduction in optical coherence tomography,” J. Biomed. Opt. 21(7), 076008 (2016).
[Crossref] [PubMed]

J. M. Schmitt, S. H. Xiang, and K. M. Yung, “Speckle in optical coherence tomography,” J. Biomed. Opt. 4(1), 95–105 (1999).
[Crossref] [PubMed]

Opt. Commun. (1)

B. Chong and Y. K. Zhu, “Speckle reduction in optical coherence tomography images of human finger skin by wavelet modified BM3D filter,” Opt. Commun. 291(6), 461–469 (2013).
[Crossref]

Opt. Express (3)

Other (9)

X. J. Mao, C. Shen, and Y. B. Yang, “Image restoration using very deep convolutional encoder-decoder networks with symmetric skip connections,” In Proceedings of International Conference on Neural Information Processing Systems (NIPS), (2016).

Y. Tai, J. Yang, X. Liu, and C. Xu, “MemNet: a persistent memory network for image restoration,” In Proceedings of IEEE International Conference on Computer Vision (ICCV), 4549–4557(2017).

N. Cai, F. Shi, Y. Gu, D. Hu, Y. Chen, and X. Chen, “A ResNet-based universal method for speckle reduction in optical coherence tomography images,” In Proceedings of IEEE International Symposium on Biomedical Imaging (ISBI), (2018).

P. Isola, J. Y. Zhu, T. Zhou, and A. A. Efros, “Image-to-image translation with conditional adversarial networks,” In Proceedings of Computer Vision and Pattern Recognition (CVPR), 5967–5976(2017).
[Crossref]

O. Ronneberger, P. Fischer, and T. Brox, “U-Net: convolutional networks for biomedical image segmentation,” In Proceedings of Medical Image Computing and Computer-Assisted Intervention (MICCAI), 234–241(2015).

S. Ioffe and C. Szegedy, “Batch Normalization: accelerating deep network training by reducing internal covariate shift,” arXiv:1502.03167v3, (2015).

I. J. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y. Bengio, “Generative adversarial nets,” In proceedings of International Conference on Neural Information Processing Systems(NIPS), 2672–2680(2014).

B. Wen, Y. Li, and Y. Bresler, “When sparsity meets low-rankness: transform learning with non-local low-rank constraint for image restoration,” In proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing(ICASSP), 2297–2301(2017).

A. Buades, B. Coll, and J. M. Morel, “A non-local algorithm for image denoising,” In Proceedings of Computer Vision and Pattern Recognition (CVPR), 60–65 (2005).
[Crossref]

Cited By

OSA participates in Crossref's Cited-By Linking service. Citing articles from OSA journals and other participating publishers are listed here.

Alert me when this article is cited.


Figures (11)

Fig. 1
Fig. 1 Flowchart of the proposed speckle noise reduction method.
Fig. 2
Fig. 2 Model structure of cGAN. G tries to generate fake images that fool D, while D tries to identify the fake pairs.
Fig. 3
Fig. 3 Ground truth for training. Row 1: training data 1; Row 2: training data 2. (a)(d) Bscans from the original target volume. (b)(e) Corresponding Bscans after registration and averaging. (c)(f) Corresponding Bscans after contrast enhancement.
Fig. 4
Fig. 4 Original noisy OCT images with selected ROIs and boundaries marked. Three signal regions (red) and one background region (green) are manually selected for calculating SNR, CNR and ENL. Three boundaries (blue) are manually delineated for calculating EPI. Panel (a) to (i) correspond to testing data 1 to 9 listed in Table 1.
Fig. 5
Fig. 5 Denoised Bscans by the proposed method, corresponding to the Bscans in Fig. 4.
Fig. 6
Fig. 6 Results for two Bscans obtained by different objective functions. (a) Original images (b) Results using cGAN term only (c) Results using cGAN + L1 term (d) Results using the edge-sensitive objective function.
Fig. 7
Fig. 7 Evaluation metrics obtained by different training data and for test data from different scanners. (a)SNR (b)CNR (c)ENL (d)EPI
Fig. 8
Fig. 8 Results for one Bscan of test data 1. (a) Original image (b) NLM(c) BM3D (d) STROLLR (e) K-SVD (f) MAP (g) DnCNN (h) ResNet (i) Proposed(training 1) (j) Proposed(training 2).
Fig. 9
Fig. 9 Results for one Bscan of test data 8. (a) Original image (b) NLM(c) BM3D (d) STROLLR (e) K-SVD (f) MAP (g) DnCNN (h) ResNet (i) Proposed(training 1) (j) Proposed(training 2).
Fig. 10
Fig. 10 U-shape architecture of the generator.
Fig. 11
Fig. 11 Architecture of the discriminator: PatchGAN.

Tables (3)

Tables Icon

Table 1 Specifications of training and testing OCT data

Tables Icon

Table 2 Evaluation metrics in average for different objective functions.

Tables Icon

Table 3 Evaluation metrics in average for different denoising methods.

Equations (10)

Equations on this page are rendered with MathJax. Learn more.

L cGAN ( G,D )= E x,y~ p data ( x,y ) [ logD( x,y ) ]+ E x~ p data ( x ),z~ p z ( z ) [ log( 1D( x,G( x,z ) ) ) ]
G * =arg min G max D L cGAN ( G,D )
L L1 ( G )= E x,y~ p data ( x,y ),z~ p z ( z ) [ yG( x,z ) 1 ]
G * =arg min G max D L cGAN ( G,D )+α L L1 ( G )
L Edge ( G )= E x,y~ p data ( x,y ),z~ p z ( z ) [ log i,j | G ( x,z ) i+1,j G ( x,z ) i,j | i,j | y i+1,j y i,j | ]
G * =arg min G max D L cGAN ( G,D )+α L L1 ( G )+β L Edge ( G )
SNR=10 log 10 ( max ( I ) 2 σ b 2 )
CN R i =10 log 10 ( | μ i μ b | σ i 2 + σ b 2 )
EN L i = μ i 2 σ i 2
EPI= i j | I d ( i+1,j ) I d ( i,j ) | i j | I o ( i+1,j ) I o ( i,j ) |