期刊名称：International Journal of Computer Science and Network Security
印刷版ISSN：1738-7906
出版年度：2010
卷号：10
期号：6
页码：134-140
出版社：International Journal of Computer Science and Network Security
摘要：Early detection of structural damage to the optic nerve head is critical in diagnosis of glaucoma, because such glaucomatous damage precedes clinically identifiable visual loss. Glaucoma is the second leading ocular disease and early detection of glaucoma can prevent progression of the disease and consequent loss of vision. Segmentation of optic disc cup and neuroretinal rim can provide important parameters for detecting and tracking this disease. This paper proposes an approach for the automatic localization and exact boundary detection of optic disc using the component analysis method and region of interest (ROI) based segmentation. Connected component analysis method is used to detect optic cup. The method is compared with manual thresholding approach and later the active contour is used to plot the boundary accurately. The proposed method can be used to automatically segment the neuroretinal rim area using mask to filter ISNT quadrants. Neuroretinal rim area is calculated in each of the quadrants separately to suspect glaucoma. This method is tested on image data sets from Aravind Eye Hospital, Madurai and compared with the Ophthalmologists data. Features of glaucomatous disc damage like CDR, asymmetry between left and right eye, neuro retinal rim area, ISNT, was evaluated to suspect glaucoma.
关键词：Glaucoma; fundus; Region of Interest (ROI); Cup to Disc Ratio (CDR); ISNT(inferior;superior;nasal;temporal quadrants)
Loading...
