Please use this identifier to cite or link to this item:
Title: Diabetic Retinopathy Detection Tool (DRDT)
Authors: Gasmen, Perlita
Ocaña, Christine Eve
Keywords: diabetic retinopathy
decision support tool
support vector machine
image processing
Issue Date: Jun-2016
Abstract: Diabetic retinopathy is one common cause of vision impairment. If not detected and treated, this can also cause blindness. Diabetic Retinopathy Detection Tool (DRDT) is a non-proprietary decision support tool. It classifies fundus/eye images as normal or diabetic retinopathy positive through the use of image processing and support vector machines. The classification is based on the areas of retinal structures and GLCM texture features. DRDT could be used as a starting point for other developers who want to create a decision support tool for DR. Since DRDT’s trained classifier gives an average accuracy of 66.6667%, the methods used in the creation of the tool needs to be enhanced to achieve higher accuracy. If the tool is improved, it could be used to provide second opinion to ophthalmologists on detecting DR in patients.
Appears in Collections:Computer Science SP

Files in This Item:
File Description SizeFormat 
SP Final Document (Ocana).pdf2.6 MBAdobe PDFThumbnail

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.