vioft2nntf2t|tblJournal|Abstract_paper|0xf4ff23c20c0000009afa010001000300 An improved Computer Aided Clinical Decision Support System has been developed for grading the retinal images using neural network and presented in this paper. Hard exudates, Cotton wool spots, large plaque hard exudates, Microaneurysms and Hemorrhages have been extracted. SVM classifiers have been used for classification. Further rule based classifiers have been used to grade the retinal images. The percentages of sensitivity, specificity have been found for both bright lesions and dark lesions. The accuracy of the proposed method is capable of detecting the bright and dark lesions sharply with an average accuracy of 98.19% and 97.51% respectively.
M. Madheswaran1 and S. Jerald Jeba Kumar2
1Muthayammal Engineering College, India,2The Rajaas Engineering College, India
Bright Lesion, Dark Lesion, Hard Exudates, Cotton Wool Spots, LPHE, Microaneurysms, Hemorrhages, SVM, Diabetic Retinopathy(DR), Non Proliferative Diabetic Retinopathy (NPDR)
| January | February | March | April | May | June | July | August | September | October | November | December |
| 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 | 0 |
| Published By :
ICTACT
Published In :
ICTACT Journal on Image and Video Processing
( Volume: 3 , Issue: 2 , Pages: 502-510 )
Date of Publication :
November 2012
Page Views :
102
Full Text Views :
|