Top

Published in:

Open Access 01-12-2019 | Image & Signal Processing

Automatic Annotation of Retinal Layers in Optical Coherence Tomography Images

Authors: Bashir Isa Dodo, Yongmin Li, Khalid Eltayef, Xiaohui Liu

Published in: Journal of Medical Systems | Issue 12/2019

Abstract

Early diagnosis of retinal OCT images has been shown to curtail blindness and visual impairments. However, the advancement of ophthalmic imaging technologies produces an ever-growing scale of retina images, both in volume and variety, which overwhelms the ophthalmologist ability to segment these images. While many automated methods exist, speckle noise and intensity inhomogeneity negatively impacts the performance of these methods. We present a comprehensive and fully automatic method for annotation of retinal layers in OCT images comprising of fuzzy histogram hyperbolisation (FHH) and graph cut methods to segment 7 retinal layers across 8 boundaries. The FHH handles speckle noise and inhomogeneity in the preprocessing step. Then the normalised vertical image gradient, and it’s inverse to represent image intensity in calculating two adjacency matrices and then the FHH reassigns the edge-weights to make edges along retinal boundaries have a low cost, and graph cut method identifies the shortest-paths (layer boundaries). The method is evaluated on 150 B-Scan images, 50 each from the temporal, foveal and nasal regions were used in our study. Promising experimental results have been achieved with high tolerance and adaptability to contour variance and pathological inconsistency of the retinal layers in all (temporal, foveal and nasal) regions. The method also achieves high accuracy, sensitivity, and Dice score of 0.98360, 0.9692 and 0.9712, respectively in segmenting the retinal nerve fibre layer. The annotation can facilitate eye examination by providing accurate results. The integration of the vertical gradients into the graph cut framework, which captures the unique characteristics of retinal structures, is particularly useful in finding the actual minimum paths across multiple retinal layer boundaries. Prior knowledge plays an integral role in image segmentation.

Curvature correction of retinal OCTs using graph-based geometry detection. Phys. Med. Biol. 58(9):2925–2938. https://doi.org/10.1088/0031-9155/58/9/2925, 2013CrossRef

Baroni, M., Fortunato, P., and La Torre, A., Towards quantitative analysis of retinal features in optical coherence tomography. Med. Eng. Phys. 29(4):432–441, 2007. https://doi.org/10.1016/j.medengphy.2006.06.003.CrossRefPubMed

Boyer, K.L., Herzog, A., and Roberts, C., Automatic recovery of the optic nervehead geometry in optical coherence tomography. IEEE Trans. Med. Imaging 25(5):553–570, 2006. https://doi.org/10.1109/TMI.2006.871417.CrossRefPubMed

Cabrera Fernández, D., Salinas, H.M., and Puliafito, C.A., Automated detection of retinal layer structures on optical coherence tomography images. Opt. Express 13(25):10200, 2005. https://doi.org/10.1364/OPEX.13.010200.CrossRefPubMed

Chiu, S.J., Li, X.T., Nicholas, P., Toth, C.A., Izatt, J.A., and Farsiu, S., Automatic segmentation of seven retinal layers in SDOCT images congruent with expert manual segmentation. Opt. express 18(18):19413–19428, 2010. https://doi.org/10.1364/OE.18.019413.CrossRefPubMedPubMedCentral

Dijkstra, E.W., A note on two problems in connexion with graphs. Numerische Mathematik 1(1):269–271, 1959.CrossRef

Dodo, B.I., Li, Y., Eltayef, K., and Liu, X.: Graph-cut segmentation of retinal layers from oct images. In: Proceedings of the 11th International Joint Conference on Biomedical Engineering Systems and Technologies - volume 2: BIOIMAGING pp. 35–42. INSTICC, SciTePress. https://doi.org/10.5220/0006580600350042, 2018

Dodo, B.I., Li, Y., Kaba, D., and Liu, X.: Retinal oct segmentation using fuzzy region competition and level set methods. In: 2019 IEEE 32th International Symposium on Computer-Based Medical Systems (CBMS), p. In press. IEEE, 2017.

Dodo, B.I., Li, Y., and Liu, X.: Retinal oct image segmentation using fuzzy histogram hyperbolization and continuous max-flow. In: 2017 IEEE 30th International Symposium on Computer-Based Medical Systems (CBMS), pp. 745–750. IEEE, 2017.

10.

Dodo, B.I., Li., Y., Liu, X., and Dodo, M.I.: Level set segmentation of retinal oct images. In: Proceedings of the 12th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 2: BIOIMAGING, pp. 49–56. INSTICC, SciTePress. https://doi.org/10.5220/0007577600490056, 2019

11.

Fercher, A.F., Hitzenberger, C.K., Kamp, G., and El-Zaiat, S.Y., Measurement of intraocular distances by backscattering spectral interferometry. Opt. Commun. 117(1-2):43–48, 1995.CrossRef

12.

Fernandez, D.C., Delineating fluid-filled region boundaries in optical coherence tomography images of the retina. IEEE Trans. Med. Imaging 24(8):939–945, 2005. https://doi.org/10.1109/TMI.2005.848655.CrossRef

13.

Krell, G., Tizhoosh, H.R., Lilienblum, T., Moore, C.J., and Michaelis, B.: Fuzzy image enhancement and associative feature matching in radiotherapy. In: IEEE International Conference on Neural Networks, p. 1490, 1997.

14.

Garvin, M.K., Abrámoff, M.D., Wu, X., Russell, S.R., Burns, T.L., and Sonka, M., Automated 3-D intraretinal layer segmentation of macular spectral-domain optical coherence tomography images. IEEE Trans. Med. Imaging 28(9):1436–1447, 2009. https://doi.org/10.1109/TMI.2009.2016958.CrossRefPubMedPubMedCentral

15.

Gregori, G., and Knighton, R., A robust algorithm for retinal thickness measurements using optical coherence tomography (Stratus OCT). Invest. Ophthalmol. Vis. Sci. 45(13):3007 , 2004.

16.

Haeker, M., Wu, X., Abrèmoff, M., Kardon, R., and Sonka, M., Incorporation of regional information in optimal 3-D graph search with application for intraretinal layer segmentation of optical coherence tomography images. Information processing in medical imaging: Proceedings of the... conference 20:607–618, 2007.CrossRef

17.

Huang, D., Swanson, E.A., Lin, C.P., Schuman, J.S., Stinson, W.G., Chang, W., Hee, M.R., Flotte, T., Gregory, K., and Puliafito, C.A., Optical coherence tomography. Science (New York, N.Y.) 254 (5035):1178–81, 1991. https://doi.org/10.1002/jcp.24872.The.CrossRef

18.

Iftimia, N., Bouma, B.E., and Tearney, G.J., Speckle reduction in optical coherence tomography by “path length encoded” angular compounding. J. Biomed. Opt. 8(2):260–263, 2003. https://doi.org/10.1117/1.1559060.CrossRefPubMed

19.

Kaba, D., Salazar-Gonzalez, A.G., Li, Y., Liu, X., and Serag, A.: Segmentation of retinal blood vessels using gaussian mixture models and expectation maximisation. In: International Conference on Health Information Science, pp. 105–112, 2013.

20.

Kaba, D., Wang, C., Li, Y., Salazar-Gonzalez, A., Liu, X., and Serag, A., Retinal blood vessels extraction using probabilistic modelling. Health Information Science and Systems 2(1):2 , 2014.CrossRef

21.

Kaba, D., Wang, Y., Wang, C., Liu, X., Zhu, H., Salazar-Gonzalez, A.G., and Li, Y., Retina layer segmentation using kernel graph cuts and continuous max-flow. Opt. Express 23(6):7366–7384, 2015.CrossRef

22.

Klein, R., and Klein, B.E.K., The prevalence of age-related eye diseases and visual impairment in aging: current estimatesprevalences of age-related eye diseases. Invest. Ophthalmol. Vis. Sci. 54(14):ORSF5–ORSF13, 2013.CrossRef

23.

Koozekanani, D., Boyer, K., and Roberts, C., Retinal thickness measurements from optical coherence tomography using a Markov boundary model. IEEE Trans. Med. Imaging 20 (9): 900–916, 2001. https://doi.org/10.1109/42.952728.CrossRefPubMed

24.

Lang, A., Carass, A., Hauser, M., Sotirchos, E.S., Calabresi, P.A., Ying, H.S., and Prince, J.L., Retinal layer segmentation of macular OCT images using boundary classification. Biomed. Opt. Express 4(7):1133–52, 2013. https://doi.org/10.1364/BOE.4.001133.CrossRefPubMedPubMedCentral

25.

Lu, S., Yim-Liu, C., Lim, J.H., Leung, C.K.S., and Wong, T.Y., Automated layer segmentation of optical coherence tomography images. Proceedings - 2011 4th International Conference on Biomedical Engineering and Informatics, BMEI 2011 1(10):142–146, 2011. https://doi.org/10.1109/BMEI.2011.6098329.CrossRef

26.

Magudeeswaran, V., and Ravichandran, C.G.: Fuzzy Logic-Based histogram equalization for image contrast enhancement. Mathematical problems in engineering, 2013

27.

Mayer, M.A., Hornegger, J., Mardin, C.Y., and Tornow, R.P., Retinal nerve fiber layer segmentation on FD-OCT scans of normal subjects and glaucoma patients. Biomed. Opt. Express 1(5):1358–1383, 2010. https://doi.org/10.1364/BOE.1.001358.CrossRefPubMedPubMedCentral

28.

Mishra, A., Wong, A., Bizheva, K., and Clausi, D.A., Intra-retinal layer segmentation in optical coherence tomography images. Opt. Express 17(26):23719–28, 2009. https://doi.org/10.1364/OE.17.023719.CrossRefPubMed

29.

Novosel, J., Vermeer, K.A., Thepass, G., Lemij, H.G., and Vliet, L.J.V.: Loosely coupled level sets for retinal layer segmentation in optical coherence tomography. In: IEEE 10th International Symposium on Biomedical Imaging, pp. 998–1001, 2013.

30.

Pircher, M., Gotzinger, E., Leitgeb, R., Fercher, A.F., and Hitzenberger, C.K., Speckle reduction in optical coherence tomography by frequency compounding. J. Biomed. Opt. 8(3):565–569, 2003. https://doi.org/10.1117/1.1578087.CrossRefPubMed

31.

Salazar-Gonzalez, A., Kaba, D., Li, Y., and Liu, X., Segmentation of the blood vessels and optic disk in retinal images. IEEE J. Biomed. Health Inform. 18(6):1874–1886, 2014.CrossRef

32.

Salazar-Gonzalez, A., Li, Y., and Kaba, D.: MRF reconstruction of retinal images for the optic disc segmentation. In: International Conference on Health Information Science, pp. 88–99, 2012.

33.

Salazar-Gonzalez, A., Li, Y., and Liu, X., Automatic graph cut based segmentation of retinal optic disc by incorporating blood vessel compensation. Journal of Artificial Intelligence and Soft Computing Research 2(3): 235–245, 2012.

34.

Salazar-Gonzalez, A.G., Li, Y., and Liu, X.: Retinal blood vessel segmentation via graph cut. In: International Conference on Control Automation Robotics & Vision, pp. 225–230, 2010.

35.

Salazar-Gonzalez, A.G., Li, Y., and Liu, X.: Optic disc segmentation by incorporating blood vessel compensation. In: IEEE Third International Workshop on Computational Intelligence in Medical Imaging, pp. 1–8, 2011.

36.

Salinas, H.M., and Fernandez, D.C., 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. https://doi.org/10.1109/TMI.2006.887375.CrossRefPubMed

37.

Suganya, R., Rajaram, S., and Abdullah, A.S., Big Data in Medical Image Processing. Boca Raton: CRC Press, 2018.CrossRef

38.

Tian, J., Varga, B., Somfai, G.M., Lee, W.H., Smiddy, W.E., and DeBuc, D.C., Real-time automatic segmentation of optical coherence tomography volume data of the macular region. PLoS ONE 10(8):1–20, 2015. https://doi.org/10.1371/journal.pone.0133908.CrossRef

39.

Tizhoosh, H.R., Fuzzy image processing: Potentials and state of the art. International Conference on Soft Computing 1(February):321–324, 1998.

40.

Tizhoosh, H.R., and Fochem, M.: Fuzzy histogram hyperbolization for image enhancement. Proceedings EUFIT 95(January 1995), 1995

41.

Tizhoosh, H.R., Krell, G., and Michaelis, B.: Locally adaptive fuzzy image enhancement. Image (Rochester, N.Y.) 1(1):1–5

42.

Wang, C., Kaba, D., and Li, Y., Level set segmentation of optic discs from retinal images. J. Med. Syst. 4(3):213–220, 2015.

43.

Wang, C., Wang, Y., Kaba, D., Wang, Z., Liu, X., and Li, Y.: Automated layer segmentation of 3d macular images using hybrid methods. In: Proc. International Conference on Image and Graphics. Tianjing, China, Vol. 9217, pp. 614–628, 2015.

44.

Wang, C., Wang, Y., Kaba, D., Wang, Z., Liu, X., and Li, Y., Automated layer segmentation of 3D macular images using hybrid methods. Image and Graphics 9217:614–628, 2015. https://doi.org/10.1007/978-3-319-21978-3.CrossRef

45.

Wang, C., Wang, Y., Kaba, D., Zhu, H., Wang, Z., Liu, X., and Li, Y.: Segmentation of intra-retinal layers in 3d optic nerve head images. In: Proc. International Conference on Image and Graphics. Tianjing, Vol. 9219, pp. 321–332, 2015.

46.

Wang, C., Wang, Y., and Li, Y.: Automatic choroidal layer segmentation using Markov random field and level set method. IEEE journal of biomedical and health informatics, 2017

47.

Wang, Z., Jenkins, M., Linderman, G., Bezerra, H., Fujino, Y., Costa, M., Wilson, D., and Rollins, A., 3-D stent detection in intravascular OCT using a Bayesian network and graph search. IEEE Trans. Med. Imaging 0062(c):1–14, 2015. https://doi.org/10.1109/TMI.2015.2405341.CrossRef

48.

Weese, J., and Lorenz, C., Four challenges in medical image analysis from an industrial perspective. Med. Image Anal. 33:1339–1351, 2016. https://doi.org/10.1016/j.media.2016.06.023.CrossRef

49.

Wojtkowski, M., Leitgeb, R., Kowalczyk, A., Bajraszewski, T., and Fercher, A.F., In vivo human retinal imaging by fourier domain optical coherence tomography. J. Biomed. Opt. 7(3):457–464, 2002.CrossRef

Title: Automatic Annotation of Retinal Layers in Optical Coherence Tomography Images
Authors: Bashir Isa Dodo
Yongmin Li
Khalid Eltayef
Xiaohui Liu
Publication date: 01-12-2019
Publisher: Springer US
Published in: Journal of Medical Systems / Issue 12/2019
Print ISSN: 0148-5598
Electronic ISSN: 1573-689X
DOI: https://doi.org/10.1007/s10916-019-1452-9

Keynote webinar | Spotlight on medication adherence

Springer Medicine

Automatic Annotation of Retinal Layers in Optical Coherence Tomography Images

Abstract

Keynote webinar | Spotlight on medication adherence

Springer Medicine

Abstract

Please log in to get access to this content

Other articles of this Issue 12/2019

Lung Nodule Detection based on Ensemble of Hand Crafted and Deep Features

Intra-Individual Variation of HRV during Orthostatic Challenge in Elite Male Field Hockey Players

Correction to: Implementation and Evaluation of a RFID Smart Cabinet to Improve Traceability and the Efficient Consumption of High Cost Medical Supplies in a Large Hospital

Prediction of Clinical Pathologic Prognostic Factors for Rectal Adenocarcinoma: Volumetric Texture Analysis Based on Apparent Diffusion Coefficient Maps

Stomach Deformities Recognition Using Rank-Based Deep Features Selection

A Framework for Automatic Morphological Feature Extraction and Analysis of Abdominal Organs in MRI Volumes