|
مقاله
|
Abstract
|
|
|
|
Title:
|
Automatic detection of hard exudates regions in retinal images of diabetic patients
|
|
Author(s):
|
Mahsa I. Partovi1, Seyed Hosein Rasta1 , Alireza Javadzadeh, Hadi Seyedarabi
|
|
Presentation Type:
|
Poster
|
|
Subject:
|
Retina and Retinal Cell Biology
|
|
Others:
|
|
|
Presenting Author:
|
|
|
Name:
|
Seyed Hossein Rasta
|
|
Affiliation :(optional)
|
Medical Physics Dept., Faculty of Medicine, and Medical Bioengineering, Faculty of Advanced, Medical Sciences, Tabriz University of Medical Sciences, Tabriz, Iran
|
|
E mail:
|
s.h.rasta@abdn.ac.uk
|
|
Phone:
|
|
|
Mobile:
|
09370630833
|
|
|
|
|
Purpose:
|
The purpose of the current study was to detect the exudates regions of retinal images of retinopathy patients using different image processing techniques.
|
|
Methods:
|
30 color images from retinopathy patients were selected for the current study. The images were taken by Topcon TRC-50 IX mydriatic camera and saves with TIFF format with a resolution of 500X752 pixel. The morphological functions were applied on red component of RGB and intensity components of HSI space. To detect the exudates regions, thresholding was performed on all images and the exudates region was segmented. To optimize the detection efficiency the binary morphological functions were applied. Finally the exudates regions were quantified and evaluated for further statistical purposes.
|
|
Results:
|
using the intensity component in HIS, the average sensitivity of 76%, specificity of 98%, accuracy of 97% was obtained, while for red component in RGB average sensitivity of 53%, specificity of 99%, accuracy of 98% were obtain.
|
|
Conclusion:
|
The results showed that our approach can identify the exudate regions in retinopathy images. Furthermore, the processing of intensity components revealed better performance compared to red component.
|
|
Attachment:
|
|
|