Cargando…

Deep Learning for Ocular Disease Recognition: An Inner-Class Balance

It can be challenging for doctors to identify eye disorders early enough using fundus pictures. Diagnosing ocular illnesses by hand is time-consuming, error-prone, and complicated. Therefore, an automated ocular disease detection system with computer-aided tools is necessary to detect various eye di...

Descripción completa

Detalles Bibliográficos
Autores principales: Khan, Md Shakib, Tafshir, Nafisa, Alam, Kazi Nabiul, Dhruba, Abdur Rab, Khan, Mohammad Monirujjaman, Albraikan, Amani Abdulrahman, Almalki, Faris A.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Hindawi 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9071974/
https://www.ncbi.nlm.nih.gov/pubmed/35528343
http://dx.doi.org/10.1155/2022/5007111
_version_ 1784700949913141248
author Khan, Md Shakib
Tafshir, Nafisa
Alam, Kazi Nabiul
Dhruba, Abdur Rab
Khan, Mohammad Monirujjaman
Albraikan, Amani Abdulrahman
Almalki, Faris A.
author_facet Khan, Md Shakib
Tafshir, Nafisa
Alam, Kazi Nabiul
Dhruba, Abdur Rab
Khan, Mohammad Monirujjaman
Albraikan, Amani Abdulrahman
Almalki, Faris A.
author_sort Khan, Md Shakib
collection PubMed
description It can be challenging for doctors to identify eye disorders early enough using fundus pictures. Diagnosing ocular illnesses by hand is time-consuming, error-prone, and complicated. Therefore, an automated ocular disease detection system with computer-aided tools is necessary to detect various eye disorders using fundus pictures. Such a system is now possible as a consequence of deep learning algorithms that have improved image classification capabilities. A deep-learning-based approach to targeted ocular detection is presented in this study. For this study, we used state-of-the-art image classification algorithms, such as VGG-19, to classify the ODIR dataset, which contains 5000 images of eight different classes of the fundus. These classes represent different ocular diseases. However, the dataset within these classes is highly unbalanced. To resolve this issue, the work suggested converting this multiclass classification problem into a binary classification problem and taking the same number of images for both classifications. Then, the binary classifications were trained with VGG-19. The accuracy of the VGG-19 model was 98.13% for the normal (N) versus pathological myopia (M) class; the model reached an accuracy of 94.03% for normal (N) versus cataract (C), and the model provided an accuracy of 90.94% for normal (N) versus glaucoma (G). All of the other models also improve the accuracy when the data is balanced.
format Online
Article
Text
id pubmed-9071974
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Hindawi
record_format MEDLINE/PubMed
spelling pubmed-90719742022-05-06 Deep Learning for Ocular Disease Recognition: An Inner-Class Balance Khan, Md Shakib Tafshir, Nafisa Alam, Kazi Nabiul Dhruba, Abdur Rab Khan, Mohammad Monirujjaman Albraikan, Amani Abdulrahman Almalki, Faris A. Comput Intell Neurosci Research Article It can be challenging for doctors to identify eye disorders early enough using fundus pictures. Diagnosing ocular illnesses by hand is time-consuming, error-prone, and complicated. Therefore, an automated ocular disease detection system with computer-aided tools is necessary to detect various eye disorders using fundus pictures. Such a system is now possible as a consequence of deep learning algorithms that have improved image classification capabilities. A deep-learning-based approach to targeted ocular detection is presented in this study. For this study, we used state-of-the-art image classification algorithms, such as VGG-19, to classify the ODIR dataset, which contains 5000 images of eight different classes of the fundus. These classes represent different ocular diseases. However, the dataset within these classes is highly unbalanced. To resolve this issue, the work suggested converting this multiclass classification problem into a binary classification problem and taking the same number of images for both classifications. Then, the binary classifications were trained with VGG-19. The accuracy of the VGG-19 model was 98.13% for the normal (N) versus pathological myopia (M) class; the model reached an accuracy of 94.03% for normal (N) versus cataract (C), and the model provided an accuracy of 90.94% for normal (N) versus glaucoma (G). All of the other models also improve the accuracy when the data is balanced. Hindawi 2022-04-28 /pmc/articles/PMC9071974/ /pubmed/35528343 http://dx.doi.org/10.1155/2022/5007111 Text en Copyright © 2022 Md Shakib Khan et al. https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
spellingShingle Research Article
Khan, Md Shakib
Tafshir, Nafisa
Alam, Kazi Nabiul
Dhruba, Abdur Rab
Khan, Mohammad Monirujjaman
Albraikan, Amani Abdulrahman
Almalki, Faris A.
Deep Learning for Ocular Disease Recognition: An Inner-Class Balance
title Deep Learning for Ocular Disease Recognition: An Inner-Class Balance
title_full Deep Learning for Ocular Disease Recognition: An Inner-Class Balance
title_fullStr Deep Learning for Ocular Disease Recognition: An Inner-Class Balance
title_full_unstemmed Deep Learning for Ocular Disease Recognition: An Inner-Class Balance
title_short Deep Learning for Ocular Disease Recognition: An Inner-Class Balance
title_sort deep learning for ocular disease recognition: an inner-class balance
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9071974/
https://www.ncbi.nlm.nih.gov/pubmed/35528343
http://dx.doi.org/10.1155/2022/5007111
work_keys_str_mv AT khanmdshakib deeplearningforoculardiseaserecognitionaninnerclassbalance
AT tafshirnafisa deeplearningforoculardiseaserecognitionaninnerclassbalance
AT alamkazinabiul deeplearningforoculardiseaserecognitionaninnerclassbalance
AT dhrubaabdurrab deeplearningforoculardiseaserecognitionaninnerclassbalance
AT khanmohammadmonirujjaman deeplearningforoculardiseaserecognitionaninnerclassbalance
AT albraikanamaniabdulrahman deeplearningforoculardiseaserecognitionaninnerclassbalance
AT almalkifarisa deeplearningforoculardiseaserecognitionaninnerclassbalance