Automated Detection of Glaucoma Stages using Retinal Images |
Author(s): |
| Lija George , Sri Jayachamarajendra College Of Engineering; Sheela N Rao, SRI JAYACHAMARAJENDRA COLLEGE OF ENGINEERING |
Keywords: |
| Glaucoma, Optic cup, Disc, Cup to Disc Ratio (CDR), Retinal Nerve Fiber Layer (RNFL), Optical Coherence Tomography (OCT) and Support Vector Machine (SVM) |
Abstract |
|
Glaucoma is a group of disease often causing visual impairment without any prior symptoms. It is usually caused due to high intra ocular pressure (IOP) which can result in blindness by damaging the optic nerve. Hence, diagnosing the glaucoma in the early stage can prevent the vision loss. This paper presents an automatic method to find the CDR value and thickness of RNFL using fundus and OCT images respectively. The proposed algorithm first extracts optic cup, optic disc and RNFL layer. Then based on the pixel calculation we have calculated CDR and thickness of RNFL. The result shows that the proposed algorithm is efficient in segmenting the region of interest without manual intervention. Then the CDR and RNFL thickness values are applied to the SVM classifier. It gives an accuracy of 92.14%, sensitivity 90.66% and specificity 100%. |
Other Details |
|
Paper ID: IJSRDV3I41266 Published in: Volume : 3, Issue : 4 Publication Date: 01/07/2015 Page(s): 3407-3411 |
Article Preview |
|
|
|
|
