Diabetic retinopathy pathological signs detection using image enhancement technique and deep learning / Abdul Hafiz Abu Samah …[et al.]

Abu Samah, Abdul Hafiz and Ahmad, Fadzil and Osman, Muhammad Khusairi and Md Tahir, Noritawati and Idris, Mohaiyedin and Abd. Aziz, Nor Azimah (2021) Diabetic retinopathy pathological signs detection using image enhancement technique and deep learning / Abdul Hafiz Abu Samah …[et al.]. Journal of Electrical and Electronic Systems Research (JEESR), 18. pp. 44-52. ISSN 1985-5389

Download

[thumbnail of 47329.pdf] Text
47329.pdf

Download (1MB)

Abstract

The screening of diabetic retinopathy (DR) affects the visual inspection of retina images taken by ophthalmologists to detect the specific signs of pathology such as exudate, hemorrhage (HEM) and microaneurysm (MA). However, this process is currently conducted manually in many hospitals. Therefore, it is time-wasting and risky for humans to make mistake. In general, this paper introduces an automated machine learning algorithm for detecting diabetic retinopathy (DR) in fundus images. It also involves an image pre-processing enhancement technique to support accuracy on deep learning for DR classification. For the image enhancement process, high-pass filter, histogram equalization and de-haze algorithm are applied to improve the visual quality of fundus images. By using four convolution layers, a CNN architecture is set up to classify the three pathological signs; HEM, MA and exudate. Two public online datasets, eOphtha and DIARETDB1 are used to evaluate the performance of this system. From training and testing results using enhanced DR images, a slight improvement in classification accuracy is revealed, compared to those original images with no enhancement for both datasets.

Metadata

Item Type: Article
Creators:
Creators
Email
Abu Samah, Abdul Hafiz
UNSPECIFIED
Ahmad, Fadzil
UNSPECIFIED
Osman, Muhammad Khusairi
UNSPECIFIED
Md Tahir, Noritawati
UNSPECIFIED
Idris, Mohaiyedin
UNSPECIFIED
Abd. Aziz, Nor Azimah
UNSPECIFIED
Subjects: R Medicine > R Medicine (General) > Computer applications to medicine. Medical informatics
R Medicine > R Medicine (General) > Neural Networks (Computer). Artificial intelligence
R Medicine > RC Internal Medicine > Diabetes Mellitus
Divisions: Universiti Teknologi MARA, Shah Alam > Faculty of Electrical Engineering
Journal or Publication Title: Journal of Electrical and Electronic Systems Research (JEESR)
UiTM Journal Collections: UiTM Journal > Journal of Electrical and Electronic Systems Research (JEESR)
ISSN: 1985-5389
Volume: 18
Page Range: pp. 44-52
Official URL: https://jeesr.uitm.edu.my
Item ID: 47329
Uncontrolled Keywords: Diabetic retinopathy, microaneurysm, hemorrhage,
URI: https://ir.uitm.edu.my/id/eprint/47329

ID Number

47329

Indexing


View in Google Scholar

Edit Item
Edit Item