Abstract
Conventional 3-channel color images have limited information and quality dependency on parametric conditions. Hence, spectral imaging and reproduction is desired in many color applications to record and reproduce the reflectance of objects. Likewise RGB images lack sufficient information to successfully analyze diabetic retinopathy. In this case, spectral imaging may be the alternative solution. In this article, we propose a new supervised technique to detect and classify the abnormal lesions in retinal spectral reflectance images affected by diabetes. The technique employs both stochastic and deterministic spectral similarity measures to match the desired reflectance pattern. At first, it classifies a pixel as normal or abnormal depending on the probabilistic behavior of training spectra. The final decision is made evaluating the geometric similarity. We assessed several multispectral object detection methods developed for other applications. They could not proof to be the solution. The results were interpreted using receiver operating characteristics (ROC) curves analysis.
Chapter PDF
Similar content being viewed by others
Keywords
References
Kuivalainen, M.: Retinal Image Analysis using Machine Vision, Masters Thesis. Lappeenranta University of Technology (June 6, 2005)
von Wendt, G.: Screening for diabetic retinopathy: Aspects of photographic methods. PhD thesis, Karolinska Institutet (2005)
World Health Organization, Diabetes action now: An initiative of the world health organization and the international diabetes federation, nr ISBN 92 4 159151 (2004)
Kauppi, T.: Eye Fundus Image Analysis for Automatic Detection of Diabetic Retinopathy. PhD Thesis, Lappeenranta Technical University (2010)
Carinci, F., Stracci, F., Storms, F.: Diabetes. In: Major and Chronic Diseases, Report 2007 (2007)
Gardner, T.W., Antonetti, D.A., Barber, A.J., LaNoue, K.F., Levison, S.W.: Diabetic Retinopathy: More Than Meets the Eye. Survey of Opthalmology 47(2), 253–262 (2002)
Diabetes mellitus, http://en.wikipedia.org/wiki/Diabetes (accessed May 7, 2011)
Abramoff, M.D., Niemeijer, M., Suttorp-Schulten, M.S., Viergever, M.A.: Evaluation of a system for automatic detection of diabetic retinopathy from color fundus photographs in a large population of patients with diabetes. Diabetes Care 31(2), 193–197 (2008)
Rahaman, G.M.A., Ahsan Rajon, A.H.M., Rahman, A.: Effective Approach for Automatic Detection of Vessels, Optic Disk and Macula: Retinal Spectral Image Analysis Perspective. International Journal of Applied Research in Computer Science and Information Technology (IJAR-CSIT), 25–37 (2012)
Soliz, P., Truitt, P., Nemeth, S.: Spectrally-Based Fundus Imaging: Implications for Image Enhancement And Diagnosis of Retinal Diseases. In: Thirty-Fifth Asilomar Conference on Signals, Systems and Computers, Novemer 4-7, vol. 2, pp. 1268–1272. IEEE Explore (2001)
Delori, F., Pflibsen, K.: Spectral reflectance of the human ocular fundus. Applied Optics 28(6), 1061–1077 (1989)
Styles, I., Calcagni, A., Claridge, E., Orihuela-Espina, F., Gibson, J.: Quantitative analysis of multi-spectral fundus images. Medical Image Analysis 10(4), 578–597 (2006)
Kilbride, P.E., Keehan, K.M.: Visual pigments in the human macula assessed by imaging fundus reflectometry. Applied Optics 29(10), 1427–1435 (1990)
Falt, P., Hiltunen, J., Hauta-Kasari, M., Sorri, I., Kalesnykiene, V., Uusitalo, H.: Extending Diabetic Retinopathy Imaging from Color to Spectra. In: Proceedings of the Scandinavian Conference on Image Analysis (SCIA 2009), Oslo, Norway (2009)
Chang, C.-I.: Hyperspectral Imaging: Techniques for Spectral Detection and Classification, 1st edn. Springer (2003)
Eye Anatomy and Function, http://faculty.washington.edu/chudler/eyetr.html (accessed May 11, 2011)
Diabetic Eye Disease, http://www.emedicinehealth.com/diabetic_eye_disease/article_em.htm#DiabeticEyeDiseaseOverview (accessed May 12, 2011)
Diabetic Retinopathy http://en.wikipedia.org/wiki/Diabetic_retinopathy (accessed May 7, 2011)
Wang, C.-M., Chen, C.-C., Chung, N., Yang, C., Chung, P.-C., Yang, C.-W., Chang, C.-I.: Detection of Spectral Signatures in Multispectral MR Images for Classification. IEEE Transactions on Medical Imaging 22(1), 50–61 (2003)
Lin, G.-C., Wang, W.-J., Wang, C.-M.: Feature Selection Algorithm for Classification of Multispectral MR Images Using Constrained Energy Minimization. In: 10th International Conference on Hybrid Intelligent Systems, Atlanta, GA, August 23-25, pp. 43–46. IEEE Xplore (2010)
Harsanyi, J., Chang, C.-I.: Hyperspectral image classification and dimensionality reduction: an orthogonal subspace projection approach. IEEE Transactions on Geoscience and Remote Sensing 32(4), 779–785 (1994)
Wang, C., Yang, S., Chung, P., Chang, C., Lo, C., Chen, C., Yang, C., Wen, C.: Orthogonal Subspace Projection-based Approaches to Classification of MR image Sequence. Computerized Medical Imaging and Graphics 25(6), 465–476 (2001)
Fawcett, T.: An introduction to ROC analysis. Pattern Recognition Letters 27, 861–874 (2009)
IMAGERET, http://www2.it.lut.fi/project/imageret/ (accessed June 08, 2011)
Chang, C.-C., Lin, C.-J.: LIBSVM : a library for support vector machines (2001), http://www.csie.ntu.edu.tw/~cjlin/libsvm/
Cardillo, G.: Clinical test performance: the performance of a clinical test based on the Bayes theorem, http://www.mathworks.com/matlabcentral/fileexchange/2705-clinical-test-performance (accessed May 11, 2011)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Rahaman, G.M.A., Parkkinen, J., Hauta-Kasari, M., Norberg, O. (2013). Retinal Spectral Image Analysis Methods Using Spectral Reflectance Pattern Recognition. In: Tominaga, S., Schettini, R., Trémeau, A. (eds) Computational Color Imaging. CCIW 2013. Lecture Notes in Computer Science, vol 7786. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-36700-7_18
Download citation
DOI: https://doi.org/10.1007/978-3-642-36700-7_18
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-36699-4
Online ISBN: 978-3-642-36700-7
eBook Packages: Computer ScienceComputer Science (R0)