Automatic analysis of fundus eye images using mathematical morphology and neural networks for supporting glaucoma diagnosis

• Autorzy: Stąpor K. , Świtoński A.
• Języki publikacji: EN

Abstrakty

EN

In this paper a new method for automatic segmentation and classification of fundus eye images (fei) into normal and glaucomatous ones is proposed. The segmentation of the cup region from the fei makes use of a morphological watershed transformation with markers imposed. New features for quantitative cup evaluation are found based on genetic algorithms with the proposed new fitness function. The computed features are then used in a classification procedure which is based on a multilayer perceptron. The mean sensitivity is 90%, while the mean specificity reaches 85%. The results obtained are encouraging.

Słowa kluczowe

EN

gray-level morphological operators; watershed transformation; genetic algorithms; multilayer perceptron; glaucoma

• Wydawca: Institute of Information Technology of the Warsaw University of Life Sciences – SGGW
• Czasopismo: Machine Graphics and Vision
• Rocznik: 2004
• Tom: Vol. 13, No. 1/2
• Strony: 65--78
• Opis fizyczny: Bibliogr. 16 poz., il., wykr.

Twórcy

autor

Stąpor K.

• Institute of Computer Science Silesian Technical University, Gliwice, Poland

autor

Świtoński A.

• Institute of Computer Science Silesian Technical University, Gliwice, Poland

Bibliografia

• [1] Tamura S., Okamoto Y.: Zero-crossing interval correction in tracing eye-fundus blood vessels. PR, 21(3), 227-233, 1988.
• [2] Chaudhuri S., et al.: Detection of blood vessels in retinal images using two-dimensional matched filter. IEEE Trans. on Medical Imaging, 8(3), 263-269, 1989.
• [3] Beucher S., Meyer F.: The morphological approach to image segmentation: the watershed transformation. E. R. Dougherty (Eds.): Mathematical morphology in image processing, 433-481, 1993.
• [4] Bishop C.M.: Neural Networks for Pattern Recognition. Clarendon Press, Oxford, 1995.
• [5] Kanski J. et al. Glaucoma: a Color Manual of Diagnosis and Treatment. Butterworth-Heinemann, 1996.
• [6] Trier O., Jain A., Taxt T.: Feature extraction methods for character recognition - a survey. PR, 641-662, 1996.
• [7] Pinz A., et al.: Mapping the human retina. IEEE Trans. Medical Imaging, 1, 210-215, 1998.
• [8] Jonas J. et al.: Ophthalmoscopic evalutation of the optic nerve head. Survey of Ophthalmology, 43(4), 1999.
• [9] Morris D.T., Donnison C.: Identifying the neuroretinal rim boundary using dynamic contours. Image and Vision Computing, 17, 169-174, 1999.
• [10] Soille P.: Morphological Image Analysis: Principles and Applications. S-V, Berlin, 1999.
• [11] Walter T., Klein J.: Segmentation of color fundus images of the human retina: detection of the optic disc and the vascular tree using morphological techniques. Proc. 2nd Int. Symp. Medical Data Analysis, 282-287, 1999.
• [12] Goh K. G, et al: ADRIS An Automatic Diabetic Retinal Image Screening system. K. J. Cios (Eds.): Medical Data Mining and Knowledge Discovery. S-V, NY, 181-201, 1999.
• [13] Arabas J.: Lectures on Genetic Algorithms. WNT, Warsaw, 2001. [14] Gonzalez R. C., Woods R. E.: Digital Image Processing. Prentice-Hall, 2002.
• [15] Osareh A. et al.: Classification and localisation of diabetic-related eye disease. 7th European Conf. on Computer Vision (ECCV), Springer LNCS 2353, May, 502-516, 2002.
• [16] Lowell J.: Optic nerve head segmentation. IEEE Trans. Medical Imaging, 23, 256-264, 2004.