Your browser doesn't support javascript.
loading
Show: 20 | 50 | 100
Results 1 - 1 de 1
Filter
Add more filters










Database
Language
Publication year range
1.
J Med Syst ; 43(3): 53, 2019 Jan 28.
Article in English | MEDLINE | ID: mdl-30693385

ABSTRACT

The eye disease is prominent in many nations including India and is said to affect up to 80% patients having diabetes. Diabetic Retinopathy is the medical term for denoting the damages to retina caused due to diabetes mellitus. Implying K means Clustering algorithm for coarse segmentation, hard distils are identified with better accuracy than the classical approaches. The variance based methods for segmenting hard distils are reviewed in the surveys and had to be improved. To remove the background features from the picture and conserve computational costs, a mathematical morphological method is used to reconstruct the image features for better segmentation. The results obtained for 96.4% sensitivity and 97.2% specificity. Along with this advantage, a graphical user interface is developed which will simplify the usage of this system. This model will divide the fragments into regions of interests having lesions and normal regions carrying normal features. After this segmentation, ophthalmologists will utilize the results to grade diabetic retinopathy and devise a treatment plan.


Subject(s)
Algorithms , Diabetic Retinopathy/diagnosis , Diabetic Retinopathy/pathology , Image Processing, Computer-Assisted/methods , Pattern Recognition, Automated/methods , Cluster Analysis , Diabetic Retinopathy/diagnostic imaging , Humans , India , Retina/diagnostic imaging , Sensitivity and Specificity , Severity of Illness Index , User-Computer Interface
SELECTION OF CITATIONS
SEARCH DETAIL
...