Neuroretinal rim Quantification in Fundus Images to Detect Glaucoma

Summary 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.

[1]  Bunyarit Uyyanonvara,et al.  AUTOMATIC OPTIC DISK DETECTION FROM LOW CONTRAST RETINAL IMAGES OF ROP INFANT USING GVF SNAKE , 2007 .

[2]  U. Rajendra Acharya,et al.  Automated Diagnosis of Glaucoma Using Digital Fundus Images , 2009, Journal of Medical Systems.

[3]  Demetri Terzopoulos,et al.  Snakes: Active contour models , 2004, International Journal of Computer Vision.

[4]  U. Rajendra Acharya,et al.  Automated Identification of Diabetic Retinopathy Stages Using Digital Fundus Images , 2008, Journal of Medical Systems.

[5]  K. Yanashima,et al.  Development of a simple diagnostic method for the glaucoma using ocular Fundus pictures. , 2005, 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference.

[6]  J. Liu,et al.  Optic cup and disk extraction from retinal fundus images for determination of cup-to-disc ratio , 2008, 2008 3rd IEEE Conference on Industrial Electronics and Applications.

[7]  U. Rajendra Acharya,et al.  Application of Higher Order Spectra for the Identification of Diabetes Retinopathy Stages , 2008, Journal of Medical Systems.

[8]  Huiqi Li,et al.  A model-based approach for automated feature extraction in fundus images , 2003, Proceedings Ninth IEEE International Conference on Computer Vision.

[9]  B. Schwartz,et al.  Neuroretinal rim area measurements by configuration and by pallor in ocular hypertension and glaucoma. , 1992, Ophthalmology.

[10]  U. Rajendra Acharya,et al.  Identification of different stages of diabetic retinopathy using retinal optical images , 2008, Inf. Sci..

[11]  Kande.  Automatic detection and boundary estimation of optic disk in fundus images using geometric active contours , 2009 .

[12]  G. Gamble,et al.  Comparison of disc damage likelihood scale, cup to disc ratio, and Heidelberg retina tomograph in the diagnosis of glaucoma , 2006, British Journal of Ophthalmology.

[13]  Jasjit S. Suri,et al.  Image modeling of the human eye , 2008 .