Performance Analysis of Deep-Neural-Network-Based Automatic Diagnosis of Diabetic Retinopathy
Diabetic retinopathy (DR) is a human eye disease that affects people who are suffering from diabetes. It causes damage to their eyes, including vision loss. It is treatable; however, it takes a long time to diagnose and may require many eye exams. Early detection of DR may prevent or delay the visio...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-12-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/1/205 |
| _version_ | 1797497546735616000 |
|---|---|
| author | Hassan Tariq Muhammad Rashid Asfa Javed Eeman Zafar Saud S. Alotaibi Muhammad Yousuf Irfan Zia |
| author_facet | Hassan Tariq Muhammad Rashid Asfa Javed Eeman Zafar Saud S. Alotaibi Muhammad Yousuf Irfan Zia |
| author_sort | Hassan Tariq |
| collection | DOAJ |
| description | Diabetic retinopathy (DR) is a human eye disease that affects people who are suffering from diabetes. It causes damage to their eyes, including vision loss. It is treatable; however, it takes a long time to diagnose and may require many eye exams. Early detection of DR may prevent or delay the vision loss. Therefore, a robust, automatic and computer-based diagnosis of DR is essential. Currently, deep neural networks are being utilized in numerous medical areas to diagnose various diseases. Consequently, deep transfer learning is utilized in this article. We employ five convolutional-neural-network-based designs (AlexNet, GoogleNet, Inception V4, Inception ResNet V2 and ResNeXt-50). A collection of DR pictures is created. Subsequently, the created collections are labeled with an appropriate treatment approach. This automates the diagnosis and assists patients through subsequent therapies. Furthermore, in order to identify the severity of DR retina pictures, we use our own dataset to train deep convolutional neural networks (CNNs). Experimental results reveal that the pre-trained model Se-ResNeXt-50 obtains the best classification accuracy of 97.53% for our dataset out of all pre-trained models. Moreover, we perform five different experiments on each CNN architecture. As a result, a minimum accuracy of 84.01% is achieved for a five-degree classification. |
| first_indexed | 2024-03-10T03:20:46Z |
| format | Article |
| id | doaj.art-117a6ff2dbbd425c9f8b43608ca71e97 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T03:20:46Z |
| publishDate | 2021-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-117a6ff2dbbd425c9f8b43608ca71e972023-11-23T12:18:35ZengMDPI AGSensors1424-82202021-12-0122120510.3390/s22010205Performance Analysis of Deep-Neural-Network-Based Automatic Diagnosis of Diabetic RetinopathyHassan Tariq0Muhammad Rashid1Asfa Javed2Eeman Zafar3Saud S. Alotaibi4Muhammad Yousuf Irfan Zia5Department of Electrical Engineering, School of Engineering, University of Management and Technology (UMT), Lahore 54770, PakistanDepartment of Computer Engineering, Umm Al-Qura University, Makkah 21955, Saudi ArabiaDepartment of Electrical Engineering, School of Engineering, University of Management and Technology (UMT), Lahore 54770, PakistanDepartment of Electrical Engineering, School of Engineering, University of Management and Technology (UMT), Lahore 54770, PakistanDepartment of Information Systems, Umm Al-Qura University, Makkah 21955, Saudi ArabiaTelecommunications Engineering School, University of Malaga, 29010 Malaga, SpainDiabetic retinopathy (DR) is a human eye disease that affects people who are suffering from diabetes. It causes damage to their eyes, including vision loss. It is treatable; however, it takes a long time to diagnose and may require many eye exams. Early detection of DR may prevent or delay the vision loss. Therefore, a robust, automatic and computer-based diagnosis of DR is essential. Currently, deep neural networks are being utilized in numerous medical areas to diagnose various diseases. Consequently, deep transfer learning is utilized in this article. We employ five convolutional-neural-network-based designs (AlexNet, GoogleNet, Inception V4, Inception ResNet V2 and ResNeXt-50). A collection of DR pictures is created. Subsequently, the created collections are labeled with an appropriate treatment approach. This automates the diagnosis and assists patients through subsequent therapies. Furthermore, in order to identify the severity of DR retina pictures, we use our own dataset to train deep convolutional neural networks (CNNs). Experimental results reveal that the pre-trained model Se-ResNeXt-50 obtains the best classification accuracy of 97.53% for our dataset out of all pre-trained models. Moreover, we perform five different experiments on each CNN architecture. As a result, a minimum accuracy of 84.01% is achieved for a five-degree classification.https://www.mdpi.com/1424-8220/22/1/205deep learningdiabetic retinopathydeep transfer learningconvolutional neural networkautomatic detection |
| spellingShingle | Hassan Tariq Muhammad Rashid Asfa Javed Eeman Zafar Saud S. Alotaibi Muhammad Yousuf Irfan Zia Performance Analysis of Deep-Neural-Network-Based Automatic Diagnosis of Diabetic Retinopathy Sensors deep learning diabetic retinopathy deep transfer learning convolutional neural network automatic detection |
| title | Performance Analysis of Deep-Neural-Network-Based Automatic Diagnosis of Diabetic Retinopathy |
| title_full | Performance Analysis of Deep-Neural-Network-Based Automatic Diagnosis of Diabetic Retinopathy |
| title_fullStr | Performance Analysis of Deep-Neural-Network-Based Automatic Diagnosis of Diabetic Retinopathy |
| title_full_unstemmed | Performance Analysis of Deep-Neural-Network-Based Automatic Diagnosis of Diabetic Retinopathy |
| title_short | Performance Analysis of Deep-Neural-Network-Based Automatic Diagnosis of Diabetic Retinopathy |
| title_sort | performance analysis of deep neural network based automatic diagnosis of diabetic retinopathy |
| topic | deep learning diabetic retinopathy deep transfer learning convolutional neural network automatic detection |
| url | https://www.mdpi.com/1424-8220/22/1/205 |
| work_keys_str_mv | AT hassantariq performanceanalysisofdeepneuralnetworkbasedautomaticdiagnosisofdiabeticretinopathy AT muhammadrashid performanceanalysisofdeepneuralnetworkbasedautomaticdiagnosisofdiabeticretinopathy AT asfajaved performanceanalysisofdeepneuralnetworkbasedautomaticdiagnosisofdiabeticretinopathy AT eemanzafar performanceanalysisofdeepneuralnetworkbasedautomaticdiagnosisofdiabeticretinopathy AT saudsalotaibi performanceanalysisofdeepneuralnetworkbasedautomaticdiagnosisofdiabeticretinopathy AT muhammadyousufirfanzia performanceanalysisofdeepneuralnetworkbasedautomaticdiagnosisofdiabeticretinopathy |