Automatic detection and classification of diabetic retinopathy from retinal fundus images

Abdullah Biran

doi:10.32920/ryerson.14648760

Abstract

Automatic Detection and Classification of Diabetic Retinopathy from Retinal Fundus Images by Abdullah Biran, Master of Applied Science, lectrical and computer engineering Department, Ryerson University, 2017. Diabetic Retinopathy (DR) is an eye disease that leads to blindness when it progresses to proliferative level. The earliest signs of DR are the appearance of red and yellow lesions on the retina called hemorrhages and exudates. Early diagnosis of DR prevents from blindness. In this thesis, an automatic algorithm for detecting diabetic retinopathy is presented. The algorithm is based on combination of several image processing techniques including Circular Hough Transform (CHT), Contrast Limited Adaptive Histogram Equalization (CLAHE), Gabor filter and thresholding. In addition, Support Vector Machine (SVM) classifier is used to classify retinal images into normal or abnormal cases of DR including non-proliferative (NPDR) or proliferative diabetic retinopathy (PDR). The proposed method has been tested on fundus images from Standard Diabetic Retinopathy Database (DIARETDB). The implementation of the presented methodology was done in MATLAB. The methodology is tested for sensitivity and accuracy.

Highlights

1.1 BackgroundThe application of image processing and computer vision techniques in different fields of science and engineering is rapidly growing
This study aims to develop an approach for automatic detection and classification of Diabetic Retinopathy (DR) through developing the main three stages of detection, i.e., processing, segmentation and classification
The upside, downside, left and right sides of the frequency domain are the maximum frequencies. As illustrated in these images, the optic disc (OD) removal adds some high frequency noises to the image. This is because we introduce a mask into the image that generates a sudden change in the fundus image in the OD region

Summary

Introduction

1.1 BackgroundThe application of image processing and computer vision techniques in different fields of science and engineering is rapidly growing. Successful developments have been made in image processing, such as the automated diagnostic systems. These systems are based on a verity of algorithms that diagnose diseases invasively in a short period of time. Different automatic systems have been proposed to detect Diabetic Retinopathy (DR) from retinal fundus images. Background removing is an essential step in image preprocessing because the proposed algorithms should be applied only on the eye pixels. The inputs of this stage are public RGB colored images from the DIARETDB database. Image normalization is a process of changing the range of pixel intensities to simplify the analysis. The selected range is 0 to 1; while 0 refers to minimum and 1 refers to maximum intensity value in the image [34]

Objectives

Results

Conclusion