Multilevel Deep Feature Generation Framework for Automated Detection of Retinal Abnormalities Using OCT Images
Optical coherence tomography (OCT) images coupled with many learning techniques have been developed to diagnose retinal disorders. This work aims to develop a novel framework for extracting deep features from 18 pre-trained convolutional neural networks (CNN) and to attain high performance using OCT...
Main Authors: | , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-12-01
|
Series: | Entropy |
Subjects: | |
Online Access: | https://www.mdpi.com/1099-4300/23/12/1651 |
_version_ | 1797504936750088192 |
---|---|
author | Prabal Datta Barua Wai Yee Chan Sengul Dogan Mehmet Baygin Turker Tuncer Edward J. Ciaccio Nazrul Islam Kang Hao Cheong Zakia Sultana Shahid U. Rajendra Acharya |
author_facet | Prabal Datta Barua Wai Yee Chan Sengul Dogan Mehmet Baygin Turker Tuncer Edward J. Ciaccio Nazrul Islam Kang Hao Cheong Zakia Sultana Shahid U. Rajendra Acharya |
author_sort | Prabal Datta Barua |
collection | DOAJ |
description | Optical coherence tomography (OCT) images coupled with many learning techniques have been developed to diagnose retinal disorders. This work aims to develop a novel framework for extracting deep features from 18 pre-trained convolutional neural networks (CNN) and to attain high performance using OCT images. In this work, we have developed a new framework for automated detection of retinal disorders using transfer learning. This model consists of three phases: deep fused and multilevel feature extraction, using 18 pre-trained networks and tent maximal pooling, feature selection with ReliefF, and classification using the optimized classifier. The novelty of this proposed framework is the feature generation using widely used CNNs and to select the most suitable features for classification. The extracted features using our proposed intelligent feature extractor are fed to iterative ReliefF (IRF) to automatically select the best feature vector. The quadratic support vector machine (QSVM) is utilized as a classifier in this work. We have developed our model using two public OCT image datasets, and they are named database 1 (DB1) and database 2 (DB2). The proposed framework can attain 97.40% and 100% classification accuracies using the two OCT datasets, DB1 and DB2, respectively. These results illustrate the success of our model. |
first_indexed | 2024-03-10T04:11:30Z |
format | Article |
id | doaj.art-c577473323ae4fa5af86fc6fcb126b0c |
institution | Directory Open Access Journal |
issn | 1099-4300 |
language | English |
last_indexed | 2024-03-10T04:11:30Z |
publishDate | 2021-12-01 |
publisher | MDPI AG |
record_format | Article |
series | Entropy |
spelling | doaj.art-c577473323ae4fa5af86fc6fcb126b0c2023-11-23T08:11:09ZengMDPI AGEntropy1099-43002021-12-012312165110.3390/e23121651Multilevel Deep Feature Generation Framework for Automated Detection of Retinal Abnormalities Using OCT ImagesPrabal Datta Barua0Wai Yee Chan1Sengul Dogan2Mehmet Baygin3Turker Tuncer4Edward J. Ciaccio5Nazrul Islam6Kang Hao Cheong7Zakia Sultana Shahid8U. Rajendra Acharya9School of Management & Enterprise, University of Southern Queensland, Toowoomba, QLD 4350, AustraliaUniversity Malaya Research Imaging Centre, Department of Biomedical Imaging, Faculty of Medicine, University of Malaya, Kuala Lumpur 59100, MalaysiaDepartment of Digital Forensics Engineering, College of Technology, Firat University, Elazig 23002, TurkeyDepartment of Computer Engineering, College of Engineering, Ardahan University, Ardahan 75000, TurkeyDepartment of Digital Forensics Engineering, College of Technology, Firat University, Elazig 23002, TurkeyDepartment of Medicine, Columbia University Irving Medical Center, New York, NY 10032-3784, USAGlaucoma Faculty, Bangladesh Eye Hospital & Institute, Dhaka 1206, BangladeshScience, Mathematics and Technology Cluster, Singapore University of Technology and Design, Singapore 487372, SingaporeDepartment of Ophthalmology, Anwer Khan Modern Medical College, Dhaka 1205, BangladeshDepartment of Electronics and Computer Engineering, Ngee Ann Polytechnic, Singapore 599489, SingaporeOptical coherence tomography (OCT) images coupled with many learning techniques have been developed to diagnose retinal disorders. This work aims to develop a novel framework for extracting deep features from 18 pre-trained convolutional neural networks (CNN) and to attain high performance using OCT images. In this work, we have developed a new framework for automated detection of retinal disorders using transfer learning. This model consists of three phases: deep fused and multilevel feature extraction, using 18 pre-trained networks and tent maximal pooling, feature selection with ReliefF, and classification using the optimized classifier. The novelty of this proposed framework is the feature generation using widely used CNNs and to select the most suitable features for classification. The extracted features using our proposed intelligent feature extractor are fed to iterative ReliefF (IRF) to automatically select the best feature vector. The quadratic support vector machine (QSVM) is utilized as a classifier in this work. We have developed our model using two public OCT image datasets, and they are named database 1 (DB1) and database 2 (DB2). The proposed framework can attain 97.40% and 100% classification accuracies using the two OCT datasets, DB1 and DB2, respectively. These results illustrate the success of our model.https://www.mdpi.com/1099-4300/23/12/1651OCT image classificationdiabetic macular edema (DME)hybrid deep feature generationiterative feature selectiondigital image processing |
spellingShingle | Prabal Datta Barua Wai Yee Chan Sengul Dogan Mehmet Baygin Turker Tuncer Edward J. Ciaccio Nazrul Islam Kang Hao Cheong Zakia Sultana Shahid U. Rajendra Acharya Multilevel Deep Feature Generation Framework for Automated Detection of Retinal Abnormalities Using OCT Images Entropy OCT image classification diabetic macular edema (DME) hybrid deep feature generation iterative feature selection digital image processing |
title | Multilevel Deep Feature Generation Framework for Automated Detection of Retinal Abnormalities Using OCT Images |
title_full | Multilevel Deep Feature Generation Framework for Automated Detection of Retinal Abnormalities Using OCT Images |
title_fullStr | Multilevel Deep Feature Generation Framework for Automated Detection of Retinal Abnormalities Using OCT Images |
title_full_unstemmed | Multilevel Deep Feature Generation Framework for Automated Detection of Retinal Abnormalities Using OCT Images |
title_short | Multilevel Deep Feature Generation Framework for Automated Detection of Retinal Abnormalities Using OCT Images |
title_sort | multilevel deep feature generation framework for automated detection of retinal abnormalities using oct images |
topic | OCT image classification diabetic macular edema (DME) hybrid deep feature generation iterative feature selection digital image processing |
url | https://www.mdpi.com/1099-4300/23/12/1651 |
work_keys_str_mv | AT prabaldattabarua multileveldeepfeaturegenerationframeworkforautomateddetectionofretinalabnormalitiesusingoctimages AT waiyeechan multileveldeepfeaturegenerationframeworkforautomateddetectionofretinalabnormalitiesusingoctimages AT senguldogan multileveldeepfeaturegenerationframeworkforautomateddetectionofretinalabnormalitiesusingoctimages AT mehmetbaygin multileveldeepfeaturegenerationframeworkforautomateddetectionofretinalabnormalitiesusingoctimages AT turkertuncer multileveldeepfeaturegenerationframeworkforautomateddetectionofretinalabnormalitiesusingoctimages AT edwardjciaccio multileveldeepfeaturegenerationframeworkforautomateddetectionofretinalabnormalitiesusingoctimages AT nazrulislam multileveldeepfeaturegenerationframeworkforautomateddetectionofretinalabnormalitiesusingoctimages AT kanghaocheong multileveldeepfeaturegenerationframeworkforautomateddetectionofretinalabnormalitiesusingoctimages AT zakiasultanashahid multileveldeepfeaturegenerationframeworkforautomateddetectionofretinalabnormalitiesusingoctimages AT urajendraacharya multileveldeepfeaturegenerationframeworkforautomateddetectionofretinalabnormalitiesusingoctimages |