A Deep Learning Based Approach for Grading of Diabetic Retinopathy Using Large Fundus Image Dataset
Diabetic Retinopathy affects one-third of all diabetic patients and may cause vision impairment. It has four stages of progression, i.e., mild non-proliferative, moderate non-proliferative, severe non-proliferative and proliferative Diabetic Retinopathy. The disease has no noticeable symptoms at ear...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-12-01
|
Series: | Diagnostics |
Subjects: | |
Online Access: | https://www.mdpi.com/2075-4418/12/12/3084 |
_version_ | 1797460681611542528 |
---|---|
author | Ayesha Mehboob Muhammad Usman Akram Norah Saleh Alghamdi Anum Abdul Salam |
author_facet | Ayesha Mehboob Muhammad Usman Akram Norah Saleh Alghamdi Anum Abdul Salam |
author_sort | Ayesha Mehboob |
collection | DOAJ |
description | Diabetic Retinopathy affects one-third of all diabetic patients and may cause vision impairment. It has four stages of progression, i.e., mild non-proliferative, moderate non-proliferative, severe non-proliferative and proliferative Diabetic Retinopathy. The disease has no noticeable symptoms at early stages and may lead to chronic destruction, thus causing permanent blindness if not detected at an early stage. The proposed research provides deep learning frameworks for autonomous detection of Diabetic Retinopathy at an early stage using fundus images. The first framework consists of cascaded neural networks, spanned in three layers where each layer classifies data into two classes, one is the desired stage and the other output is passed to another classifier until the input image is classified as one of the stages. The second framework takes normalized, HSV and RGB fundus images as input to three Convolutional Neural Networks, and the resultant probabilistic vectors are averaged together to obtain the final output of the input image. Third framework used the Long Short Term Memory Module in CNN to emphasize the network in remembering information over a long time span. Proposed frameworks were tested and compared on the large-scale Kaggle fundus image dataset EYEPAC. The evaluations have shown that the second framework outperformed others and achieved an accuracy of 78.06% and 83.78% without and with augmentation, respectively. |
first_indexed | 2024-03-09T17:08:29Z |
format | Article |
id | doaj.art-93a1de7aeb1344cbbd2ebef8220ff480 |
institution | Directory Open Access Journal |
issn | 2075-4418 |
language | English |
last_indexed | 2024-03-09T17:08:29Z |
publishDate | 2022-12-01 |
publisher | MDPI AG |
record_format | Article |
series | Diagnostics |
spelling | doaj.art-93a1de7aeb1344cbbd2ebef8220ff4802023-11-24T14:18:23ZengMDPI AGDiagnostics2075-44182022-12-011212308410.3390/diagnostics12123084A Deep Learning Based Approach for Grading of Diabetic Retinopathy Using Large Fundus Image DatasetAyesha Mehboob0Muhammad Usman Akram1Norah Saleh Alghamdi2Anum Abdul Salam3Computer and Software Engineering Department, College of E&ME, National University of Sciences and Technology, Islamabad 44000, PakistanComputer and Software Engineering Department, College of E&ME, National University of Sciences and Technology, Islamabad 44000, PakistanDepartment of Computer Sciences, College of Computer and Information Sciences, Princess Nourah Bint Abdulrahman University, P.O. Box 84428, Riyadh 11671, Saudi ArabiaComputer and Software Engineering Department, College of E&ME, National University of Sciences and Technology, Islamabad 44000, PakistanDiabetic Retinopathy affects one-third of all diabetic patients and may cause vision impairment. It has four stages of progression, i.e., mild non-proliferative, moderate non-proliferative, severe non-proliferative and proliferative Diabetic Retinopathy. The disease has no noticeable symptoms at early stages and may lead to chronic destruction, thus causing permanent blindness if not detected at an early stage. The proposed research provides deep learning frameworks for autonomous detection of Diabetic Retinopathy at an early stage using fundus images. The first framework consists of cascaded neural networks, spanned in three layers where each layer classifies data into two classes, one is the desired stage and the other output is passed to another classifier until the input image is classified as one of the stages. The second framework takes normalized, HSV and RGB fundus images as input to three Convolutional Neural Networks, and the resultant probabilistic vectors are averaged together to obtain the final output of the input image. Third framework used the Long Short Term Memory Module in CNN to emphasize the network in remembering information over a long time span. Proposed frameworks were tested and compared on the large-scale Kaggle fundus image dataset EYEPAC. The evaluations have shown that the second framework outperformed others and achieved an accuracy of 78.06% and 83.78% without and with augmentation, respectively.https://www.mdpi.com/2075-4418/12/12/3084diabetic retinopathyconvolution neural network (CNN)random forest tree (RFT)long short term memory (LSTM) |
spellingShingle | Ayesha Mehboob Muhammad Usman Akram Norah Saleh Alghamdi Anum Abdul Salam A Deep Learning Based Approach for Grading of Diabetic Retinopathy Using Large Fundus Image Dataset Diagnostics diabetic retinopathy convolution neural network (CNN) random forest tree (RFT) long short term memory (LSTM) |
title | A Deep Learning Based Approach for Grading of Diabetic Retinopathy Using Large Fundus Image Dataset |
title_full | A Deep Learning Based Approach for Grading of Diabetic Retinopathy Using Large Fundus Image Dataset |
title_fullStr | A Deep Learning Based Approach for Grading of Diabetic Retinopathy Using Large Fundus Image Dataset |
title_full_unstemmed | A Deep Learning Based Approach for Grading of Diabetic Retinopathy Using Large Fundus Image Dataset |
title_short | A Deep Learning Based Approach for Grading of Diabetic Retinopathy Using Large Fundus Image Dataset |
title_sort | deep learning based approach for grading of diabetic retinopathy using large fundus image dataset |
topic | diabetic retinopathy convolution neural network (CNN) random forest tree (RFT) long short term memory (LSTM) |
url | https://www.mdpi.com/2075-4418/12/12/3084 |
work_keys_str_mv | AT ayeshamehboob adeeplearningbasedapproachforgradingofdiabeticretinopathyusinglargefundusimagedataset AT muhammadusmanakram adeeplearningbasedapproachforgradingofdiabeticretinopathyusinglargefundusimagedataset AT norahsalehalghamdi adeeplearningbasedapproachforgradingofdiabeticretinopathyusinglargefundusimagedataset AT anumabdulsalam adeeplearningbasedapproachforgradingofdiabeticretinopathyusinglargefundusimagedataset AT ayeshamehboob deeplearningbasedapproachforgradingofdiabeticretinopathyusinglargefundusimagedataset AT muhammadusmanakram deeplearningbasedapproachforgradingofdiabeticretinopathyusinglargefundusimagedataset AT norahsalehalghamdi deeplearningbasedapproachforgradingofdiabeticretinopathyusinglargefundusimagedataset AT anumabdulsalam deeplearningbasedapproachforgradingofdiabeticretinopathyusinglargefundusimagedataset |