Aiming at the problem that optical coherence tomography (OCT) images with low contrast and layer structure blur are difficult to be automatically layered, a new OCT detection method based on complex shearlet transform is proposed. The method utilises nearly optimal sparse approximation singular curves of multi-scale shearlet transform, and the contrast invariance of the phase congruence method. Compared with the Canny edge detector and wavelet methods, the complex shearlet-based method achieved the highest Pratt figure of merit (PFOM) value. The PFOM value of a step type edge is 0.92, and that of a pulse type edge is 0.98. Three types of OCT images were tested, including normal retinal macula area, dry age-related macular degeneration, and Stargardt disease. The experimental results show that the complex shearlet-based method can detect more layered structures of OCT images, especially the boundary between the ganglion cell layer and the inner plexiform layer that is difficult to detect, and it can detect various types of OCT images. The complex shearlet-based transform method provides an effective and general way to measure retinal OCT images.

References

1. 1)
  - 20. Yi-Han, X., Zhi-Hong, X.I., Tao, H., et al: ‘Image edge detection based on nonsubsampled contourlet transform’, Syst. Eng. Electron., 2011, 33, (7), pp. 1668–1672.
2. 2)
  - 31. Kovesi, P.: ‘Image features from phase congruency’, J. Comput. Vis. Pattern Recogn., 1999, 1, (3), pp. 1–26.
3. 3)
  - 17. Chi, J.: ‘Visual measurement technology’ (Mechanical Industry Press, Beijing, 2011).
4. 4)
  - 18. Mallat, S., Zhong, S.: ‘Characterization of signals from multiscale edges’, IEEE Trans. Pattern Anal. Mach. Intell., 1992, 14, (7), pp. 710–732.
5. 5)
  - 19. Mallat, S., Huang, W.L.: ‘Singularity detection and processing with wavelet’, IEEE Trans. Inf. Theory, 1992, 38, (2), pp. 617–643.
6. 6)
  - 9. Garvin M, K., AbrÃ moff, M.D., Wu, X., et al: ‘Automated 3-D intraretinal layer segmentation of macular spectral-domain optical coherence tomography images’, IEEE Trans. Med. Imaging, 2009, 28, (9), pp. 1436–1447.
7. 7)
  - 26. Rafael, R.: ‘The Complex shearlet transform and applications to image quality assessment’. Master thesis, Technische Universitat Berlin, 2014.
8. 8)
  - 3. Baroni, M., Fortunato, P., Torre, A.L.: ‘Towards quantitative analysis of retinal features in optical coherence tomography’, Med. Eng. Phys., 2007, 29, (4), pp. 432–441.
9. 9)
  - 8. Mishra, A., Wong, A., Bizheva, K., et al: ‘Intra-retinal layer segmentation in optical coherence tomography images’, Opt. Express, 2009, 17, (26), pp. 23719–23728.
10. 10)
  - 7. Xu, Q., Chang, Y., Li, W.B., et al: ‘A segmentation algorithm of OCT image based on region growth’, Inf. Technol., 2013, 4, pp. 136–140.
11. 11)
  - 23. Yi, S., Labate, D., Easley, G.R., et al: ‘A shearlet approach to edge analysis and detection’, IEEE Trans. Image Process., 2009, 18, (5), p. 929.
12. 12)
  - 11. Chen, Q., Xu, J., Niu, S.: ‘Retinal nerve fiber layer segmentation of spectral domain optical’, J. Electron. Inf. Technol., 2017, 39, (5), pp. 1101–1108.
13. 13)
  - 25. Reisenhofer, R., Kiefer, J., King, E.J.: ‘Shearlet-Based detection of flame fronts’, Exp. Fluids, 2016, 57, (3), pp. 1–14.
14. 14)
  - 2. Jiang, Y., Zhou, C., Ren, Q.: ‘Retinal image segmentation with optical coherence tomography’, Beijing Biomed. Eng., 2011, 30, (5), pp. 452–456.
15. 15)
  - 4. Cabrera, D.F., Salinas, H.M., Puliafito, C.A.: ‘Automated detection of retinal layer structures on optical coherence tomography images’, Opt. Express, 2005, 13, (25), pp. 10200–10216.
16. 16)
  - 29. Kutyniok, G., Lim, W.Q., Reisenhofer, R.: ‘Shearlab 3D: faithful digital shearlet transforms based on compactly supported shearlets’, ACM Trans. Math. Softw., 2016, 42, (1), pp. 1–42.
17. 17)
  - 32. Xu, C., Shi, Q., Cheng, M.: ‘Zero-symmetrical and zero-antisymmetrical dyadic wavelet and its application to edge detection’, China J. Image Graph., 1996, 1, (1), pp. 4–11.
18. 18)
  - 5. Fabritius, T., Makita, S., Miura, M., et al: ‘Automated segmentation of the macula by optical coherence tomography’, Opt. Express, 2009, 17, (18), pp. 15659–15669.
19. 19)
  - 28. Easley, G., Labate, D., Lim, W.Q.: ‘Sparse directional image representations using the discrete shearlet transform’, Appl. Comput. Harmonic Analysis, 2008, 25, (1), pp. 25–46.
20. 20)
  - 14. Fang, L., Cunefare, D., Wang, C., et al: ‘Automatic segmentation of nine retinal layer boundaries in OCT images of non-exudative AMD patients using deep learning and graph search’, Biomed. Opt. Express, 2017, 8, (5), p. 2732.
21. 21)
  - 24. Emily, J.K., Rafael, R., Johannes, K., et al: ‘Shearlet-based edge detection: flame fronts and tidal flats’. Appl. Digit. Image Process. XXXVIII, SPIE, San Diego, CA, USA, 2015, 9699.
22. 22)
  - 12. He, Q., Li, Z., Wang, X.: ‘Automated retinal layer segmentation based on optical coherence tomographic images’, Acta Opt. Sin., 2016, 36, (10), pp. 71–80.
23. 23)
  - 10. Slonczewski, J.C.: ‘Automatic segmentation of seven retinal layers in SDOCT images congruent with expert manual segmentation’, Opt. Express, 2010, 18, (18), pp. 19413–19428.
24. 24)
  - 22. Ma, S.F., Zheng, G.F., Jin, L.X., et al: ‘Directional multiscale edge detection using the contourlet transform’. 2010 2nd Int. Conf. on Advanced Computer Control IEEE, New York, NY, USA, 2010.
25. 25)
  - 30. Morrone, M.C., Owens, R.A.: ‘Feature detection from local energy’, Pattern Recognit. Lett., 1987, 6, (5), pp. 303–313.
26. 26)
  - 16. Kai, Y., Fei, S., Enting, G., et al: ‘Shared-hole graph search with adaptive constraints for 3D optic nerve head optical coherence tomography image segmentation’, Biomed. Opt. Express, 2018, 9, (3), p. 962.
27. 27)
  - 6. Vedran, K., Považay, B., Herman, B., et al: ‘Robust segmentation of intraretinal layers in the normal human fovea using a novel statistical model based on texture and shape analysis’, Opt. Express, 2010, 18, (14), p. 14730.
28. 28)
  - 27. Easley, G.R., Labate, D., Lim, W.Q.: ‘Optimally sparse image representations using shearlets’, Wavelets XI, 2005, 5914, (1), pp. 974–978.
29. 29)
  - 13. Antony, B.J., Prince, J.L.: ‘Simultaneous segmentation of retinal surfaces and microcystic macular edema in SDOCT volumes’. Proc. of SPIE--the Int. Society for Optical Engineering, 2016, vol. 9784, p. 97841.
30. 30)
  - 33. Dabov, K., Foi, A., Katkovnik, V., et al: ‘Image denoising by sparse 3-D transform-domain collaborative filtering’, IEEE Trans. Image Process., 2007, 16, (8), p. 2080.
31. 31)
  - 15. Jared, H., Alonso-Caneiro, D., Scott, A., et al: ‘Effect of patch size and network architecture on a convolutional neural network approach for automatic segmentation of OCT retinal layers’, Biomed. Opt. Express, 2018, 9, (7), p. 3049.
32. 32)
  - 1. Liu, Y., Liu, H.: ‘Clinical application progress of OCT scan in ophthalmology’, Med. Recapitulate, 2007, 13, (24), pp. 2014–2016.
33. 33)
  - 21. Zhang, Y.-T., Yin, Z.-K., Wang, J.-Y.: ‘A new image edge detection scheme’, J. Electron. Inf. Technol., 2008, 30, (6), pp. 1295–1299.

Edge detection of retinal OCT image based on complex shearlet transform

References

Related content