Retinal fundus images are used for the diagnosis and treatment of various eye diseases such as diabetic retinopathy, glaucoma, exudates and so on. The retinal vasculature is difficult to investigate retinal conditions due to the presence of various noises in the retinal image during the capture of the image. Removal of noise is an important aspect for better visibility and diagnosis of the noisy fundus in ophthalmology. This study represents a deep learning based approach to denoising images and restoring features using stack denoising convolutional autoencoder. The proposed scheme is implemented to restore the structural details of fundus as well as to decrease the noise level. Furthermore, the proposed model utilises shared layers with the optimal manner to reduce the noise level of the target image with minimal computational cost. To restore an image, the proposed model brings a patched base training on samples to suppress with one to one manner without any loss of information. To access the denoising effect of the proposed scheme, several standard fundus databases such as DRIVE, STARE and DIARETDB1 have been tested in this study. Comparing the efficiency of the suggested model with state-of-art methods, the proposed scheme gives better result in terms of qualitative and quantitative analysis.

References

1. 1)
  - 21. Garcia, A.G., Escolano, S.O., Oprea, S., et al: ‘A survey on deep learning techniques for image and video semantic segmentation’, Appl. Soft Comput., 2018, 70, pp. 41–65.
2. 2)
  - 10. Zhang, Y., Tian, X., Ren, P.: ‘An adaptive bilateral filter based framework for image denoising’, Neurocomputing, 2014, 140, pp. 299–316.
3. 3)
  - 13. Goodfellow, I., Bengio, Y., Courville, A.: ‘Deep learning’ (MIT Press, Cambridge, 2016).
4. 4)
  - 1. Saleh, M.D., Eswaran, C., Mueen, A.: ‘An automated blood vessel segmentation algorithm using histogram equalization and automatic threshold selection’, J. Digital Imag., 2014, 24, (4), pp. 564–572.
5. 5)
  - 12. Yang, Y., Sun, J., Li, H., et al: ‘ADMM-Net: a deep learning approach for compressive sensing MRI’, ArXiv: abs/1705.06869, 2017.
6. 6)
  - 8. Huang, Z.K., Li, Z.H.: ‘Comparison of different image denoising algorithms for Chinese calligraphy images’, Neurocomputing, 2016, 188, pp. 102–112.
7. 7)
  - 22. Wang, Q., Gao, J., Yuan, Y.: ‘Embedding structured contour and location prior in siamesed fully convolutional networks for road detection’, IEEE Trans. Intell. Transp. Syst., 2018, 19, (1), pp. 230–241.
8. 8)
  - 29. Liu, Y., Zhang, Y.: ‘Low-dose CT restoration via stacked sparse denoising autoencoders’, Neurocomputing, 2018, 284, pp. 80–89.
9. 9)
  - 28. Xu, J., Xiang, L., Liu, Q., et al: ‘Stacked sparse autoencoder (SSAE) for nuclei detection on breast cancer histopathology images’, IEEE Trans. Med. Imag., 2016, 35, (1), pp. 119–130.
10. 10)
  - 32. Hoover, A., Kouznetsova, V., Goldbaum, M.: ‘Locating blood vessels in retinal images by piecewise threshold probing of a matched filter response’, IEEE Trans. Med. Imaging, 2000, 19, (3), pp. 203–210.
11. 11)
  - 6. Guo, Y., Liu, Y., Oerlemans, A., et al: ‘Deep learning for visual understanding: A review’, Neurocomputing, 2016, 187, pp. 27–48.
12. 12)
  - 16. Vincent, P.: ‘A connection between score matching and denoising autoencoders’, Neural Comput.., 2011, 23, (7), pp. 1661–1674.
13. 13)
  - 20. Kamilaris, A., Prenafeta-Boldú, F.X.: ‘Deep learning in agriculture: a survey’, Comput. Electr. Agriculture, 2018, 147, pp. 70–90.
14. 14)
  - 36. Mittal, A., Bovik, A.C.: ‘No-reference image quality assessment in the spatial domain’, IEEE Trans. Image Process., 2012, 21, (12), pp. 4695–4708.
15. 15)
  - 35. Available at http://www.it.lut.fi/project/imageret/diaretdb1/.
16. 16)
  - 33. Available at http://cecas.clemson.edu/ahoover/stare/.
17. 17)
  - 34. Kalesnykiene, V., Kamarainen, J.K., Voutilainen, R., et al: ‘DIARETDB1 diabetic retinopathy database and evaluation protocol’.
18. 18)
  - 31. Available at https://www.isi.uu.nl/Research/Databases/DRIVE/.
19. 19)
  - 23. Wang, Q., Yuan, Z., Du, Q., et al: ‘GETNET: a general end-to-end two-dimensional CNN framework for hyperspectral image change detection’, IEEE Trans. Geosci. Remote Sens., 2011, 57, (1), pp. 3–13.
20. 20)
  - 19. Wolterink, J.M., Leiner, T., Viergever, M.A., et al: ‘Generative adversarial networks for noise reduction in low-dose CT’, IEEE Trans. Med. Imaging, 2017, 36, (12), pp. 2536–2545.
21. 21)
  - 25. Zhang, Y., Zhang, W.H., Chen, H., et al: ‘Few-view image reconstruction combining total variation and a high-order norm’, Int. J. Imag. Syst. Technol., 2013, 23, (3), pp. 249–255.
22. 22)
  - 4. Gu, J., Wang, Z., Kuen, J., et al: ‘Recent advances in convolutional neural networks’, Pattern Recognit., 2018, 77, pp. 354–377.
23. 23)
  - 15. Dong, C., Loy, C.C., He, K., et al: ‘Image super-resolution using deep convolutional networks’, IEEE Trans. Pattern Anal. Mach. Intellg., 2015, 38, (2), pp. 295–307.
24. 24)
  - 14. Kang, E., Min, J., Ye, J.C., et al: ‘A deep convolutional neural network using directional wavelets for low-dose X-ray CT reconstruction’, Med. Phys., 2016, 44, (10), pp. e360–e375.
25. 25)
  - 37. Yang, C., Zhang, J.-Q., Wang, X.-R., et al: ‘A novel similarity based quality metric for image fusion’, Inf. Fusion, 2008, 9, (2), pp. 156–160.
26. 26)
  - 18. Jin, K.H., McCann, M.T., Froustey, E., et al: ‘Deep convolutional neural network for inverse problems in imaging’, IEEE Trans. Image Pro., 2017, 26, (9), pp. 4509–4522.
27. 27)
  - 2. Ghosh, S.K., Ghosh, A., Chakrabarti, A.: ‘VEA: vessels extraction algorithm and a novel wavelet analyser for diabetic retinopathy detection’, Int. J. Image Graphics – Worldscientific, 2018, 18, (2), pp. 1850008-1–1850008-20.
28. 28)
  - 5. LeCun, Y., Bengio, Y., Hinton, G., et al: ‘Deep learning’, Nature, 2015, 521, pp. 436–444.
29. 29)
  - 11. Gondara, L.: ‘Medical image denoising using convolutional denoising autoencoders’. Proc. of the IEEE Int. Con. Data Mining Workshops (ICDMW 2016), Barcelona, Spain, 2016, pp. 241–246.
30. 30)
  - 3. Kanski, J.J., Bowling, B.: ‘Synopsis of clinical ophthalmology’ (Elsevier Health Sciences, New York, 2012).
31. 31)
  - 17. Litjens, G., Kooi, T., Bejnordi, B.E., et al: ‘A survey on deep learning in medical image analysis’, Med. Image Anal., 2017, 42, pp. 60–88.
32. 32)
  - 26. Shan, H., Zhang, Y., Yang, Q., et al: ‘3-D convolutional encoder–decoder network for low-dose CT via transfer learning from a 2-D trained network’, IEEE Trans. Med. Imaging., 2018, 37, (6), pp. 1522–1534.
33. 33)
  - 7. Chen, H., Zhang, Y., Kalra, M.K., et al: ‘Low-dose CT with a residual encoder–decoder convolutional neural network’, IEEE Trans. Med. Imaging., 2017, 36, (12), pp. 2524–2535.
34. 34)
  - 30. Niemeijer, M., Staal, J.J., Ginneken, B., et al: ‘Comparative study of retinal vessel segmentation methods on a new publicly available database’. SPIE Medical Imaging, 2004, vol. 5370, pp. 648–656.
35. 35)
  - 24. Im, D.J., Ahn, S., Memisevic, R., et al: ‘Denoising criterion for variational auto-encoding framework’. Proc. of the Thirty-First AAAI Conf. on Artificial Intelligence (AAAI-17), 2017. Available at https://arXiv:1511.06406.
36. 36)
  - 9. Zhang, Y., Wang, Y., Zhang, W., et al: ‘Statistical iterative reconstruction using adaptive fractional order regularization’, Biomed. Opt. Exp., 2016, 7, (3), pp. 1015–1029.
37. 37)
  - 27. Lee, D., Choi, S., Kim, H.J.: ‘Performance evaluation of image denoising developed using convolutional denoising autoencoders in chest radiography’, Nuclear Inst. Methods in Phys., 2018, 88, (4), pp. 97–104.

SDCA: a novel stack deep convolutional autoencoder – an application on retinal image denoising

References

Related content