Advertisement

Detection of Wet Age-related Macular Degeneration in OCT Images: A Case Study

  • Anam HaqEmail author
  • Szymon Wilk
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 623)

Abstract

Progress in medical imaging and computer vision has enabled us to rely on machines for the detection or diagnosis of many diseases, including eye-related problems. One of them is wet age-related macular degeneration (wet AMD) which is a type of age-related macular degeneration. Wet AMD causes the detachment of retinal pigment epithelium layer (RPE) – a condition referred to as pigment epithelium detachment (PED) – and also creates fluid fill region called choroidal neovascularization (CNV). In this paper we present a case study of detecting wet ADM in OCT images. We used a set of 51 images – 21 of sick eyes and 30 of healthy eyes. We employed feature extraction techniques to identify abnormalities in RPE layer (PED and CNV) along with the structural and textural properties of the RPE layer (gray level co-occurrence matrix, GLCM). Specifically, we considered four possible set of features and for each set we constructed k-NN, naive Bayes, support vector machine (SVM) and rule-based classifiers. The best classification performance was obtained for the features capturing the structural and textural properties of the RPE layer and for naive Bayes classifier (accuracy = 96.1%, sensitivity = 91.3%, specificity = 100.0%) and SVM classifier (accuracy = 94.1%, sensitivity = 100.0%, specificity = 93.7%). Our results confirm the usefulness of the features characterizing the RPE layer in the diagnosis of wet AMD.

Keywords

wet aged-related macular degeneration OCT images gray level cooccurrence matrix feature extraction classification 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    National Eye Institute: Facts about age-related macular degeneration (2015)Google Scholar
  2. 2.
    Kanski, J.J., Bowling, B.: Clinical Ophthalmology: A Systematic Approach. Elsevier Health Sciences (2011)Google Scholar
  3. 3.
    Denniston, A.K.O., Murray, P.I.: Oxford Handbook of Ophthalmology. Oxford University Press (2014)Google Scholar
  4. 4.
    Keane, P.A., Patel, P.J., Liakopoulos, S., Heussen, F.M., Sadda, S.R., Tufail, A.: Evaluation of age-related macular degeneration with optical coherence tomography. Surv. Ophthalmol. 57(5) (2012) 389–414Google Scholar
  5. 5.
    Walecki, W.J., Szondy, F.: Fiber optics low-coherence IR interferometry for defense sensors manufacturing. In: Procedings of SPIE. Volume 7322., SPIE (2009)Google Scholar
  6. 6.
    Walecki,W.J., Pravdivtsev, A., Santos, M., Koo, A.: High-speed high-accuracy fiber optic lowcoherence interferometry for in situ grinding and etching process monitoring. In: Procedings of SPIE. Volume 6293., SPIE (2006)Google Scholar
  7. 7.
    Gupta, V., Chan, C.C., Poh, C.L., Chow, T.H., Meng, T.C., Koon, N.B.: Computerized automation of wavelet based denoising method to reduce speckle noise in OCT images. In: International Conference on Information Technology and Applications in Biomedicine, Procedings of IEEE (2008)Google Scholar
  8. 8.
    Fabritius, T., Makita, S., Miura, M., Myllylä, R., Yasuno, Y.: Automated segmentation of the macula by optical coherence tomography. Opt. Express 17(18) (2009) 15659–15669Google Scholar
  9. 9.
    Lee, S.Y., Stetson, P.F., Ruiz-Garcia, H., Heussen, F.M., Sadda, S.R.: Automated characterization of pigment epithelial detachment by optical coherence tomography. Invest Ophthalmol Vis Sci 53(1) (2012) 164–170Google Scholar
  10. 10.
    Haq, A., Mir, F.J., Yasin, U.U., Khan, S.A.: Classification of Wet Aged Related Macular Degeneration using Optical Coherence Tomographic Images. In: Proceeding of 6th International Conference on Machine Vision. Volume 9067. (2013)Google Scholar
  11. 11.
    Prashanth, R., Paranjape, S.V., Ghosh, S., Dutta, P.K., Chatterjee, J.: Characterization of changes in retinal pigment epithelium layer in choroidal neovascularization through analysis of optical coherence tomographs. In: 2010 IEEE Students Technology Symposium (Tech-Sym), IEEE (2010) 39–43Google Scholar
  12. 12.
    Ayaz, S., Sahar, S., Zafar, M., Akram, M.U., Nadeem, Y.: Analysis of OCT images for detection of choroidal neovascularization in retinal pigment epithelial layer. In: Neural Information Processing: 21st International Conference, ICONIP 2014. Springer (2014) 226–233Google Scholar
  13. 13.
    Otsu, N.: A threshold selection method from gray-level histograms. IEEE Trans. Syst., Man, Cybern., Syst 9(1) (1979) 62–66Google Scholar
  14. 14.
    Zhao, F., Zhang, J., Ma, Y.: Medical image processing based on mathematical morphology. In: International Conference on Computer Application and System Modeling, Procedings of ICCASM (2012)Google Scholar
  15. 15.
    Saroja, G.A.S., Sulochana, C.H.: Texture analysis of non-uniform images using glcm. In: 2013 IEEE Conference on Information Communication Technologies. (2013) 1319–1322Google Scholar
  16. 16.
    Kubat, M., Matwin, S.: Addressing the curse of imbalanced training sets: One-sided selection. In: Proceedings of the Fourteenth International Conference on Machine Learning, Morgan Kaufmann (1997) 179–186Google Scholar

Copyright information

© Springer International Publishing AG 2018

Authors and Affiliations

  1. 1.Poznan University of TechnologyPoznanPoland

Personalised recommendations