Hybrid Methods for Fundus Image Analysis for Diagnosis of Diabetic Retinopathy Development Stages Based on Fusion Features
Diabetic retinopathy (DR) is a complication of diabetes that damages the delicate blood vessels of the retina and leads to blindness. Ophthalmologists rely on diagnosing the retina by imaging the fundus. The process takes a long time and needs skilled doctors to diagnose and determine the stage of D...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-08-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/13/17/2783 |
| _version_ | 1797582691613278208 |
|---|---|
| author | Mohammed Alshahrani Mohammed Al-Jabbar Ebrahim Mohammed Senan Ibrahim Abdulrab Ahmed Jamil Abdulhamid Mohammed Saif |
| author_facet | Mohammed Alshahrani Mohammed Al-Jabbar Ebrahim Mohammed Senan Ibrahim Abdulrab Ahmed Jamil Abdulhamid Mohammed Saif |
| author_sort | Mohammed Alshahrani |
| collection | DOAJ |
| description | Diabetic retinopathy (DR) is a complication of diabetes that damages the delicate blood vessels of the retina and leads to blindness. Ophthalmologists rely on diagnosing the retina by imaging the fundus. The process takes a long time and needs skilled doctors to diagnose and determine the stage of DR. Therefore, automatic techniques using artificial intelligence play an important role in analyzing fundus images for the detection of the stages of DR development. However, diagnosis using artificial intelligence techniques is a difficult task and passes through many stages, and the extraction of representative features is important in reaching satisfactory results. Convolutional Neural Network (CNN) models play an important and distinct role in extracting features with high accuracy. In this study, fundus images were used for the detection of the developmental stages of DR by two proposed methods, each with two systems. The first proposed method uses GoogLeNet with SVM and ResNet-18 with SVM. The second method uses Feed-Forward Neural Networks (FFNN) based on the hybrid features extracted by first using GoogLeNet, Fuzzy color histogram (FCH), Gray Level Co-occurrence Matrix (GLCM), and Local Binary Pattern (LBP); followed by ResNet-18, FCH, GLCM and LBP. All the proposed methods obtained superior results. The FFNN network with hybrid features of ResNet-18, FCH, GLCM, and LBP obtained 99.7% accuracy, 99.6% precision, 99.6% sensitivity, 100% specificity, and 99.86% AUC. |
| first_indexed | 2024-03-10T23:26:05Z |
| format | Article |
| id | doaj.art-b6fa455ab11540a892c7b7009332a69a |
| institution | Directory Open Access Journal |
| issn | 2075-4418 |
| language | English |
| last_indexed | 2024-03-10T23:26:05Z |
| publishDate | 2023-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj.art-b6fa455ab11540a892c7b7009332a69a2023-11-19T07:59:31ZengMDPI AGDiagnostics2075-44182023-08-011317278310.3390/diagnostics13172783Hybrid Methods for Fundus Image Analysis for Diagnosis of Diabetic Retinopathy Development Stages Based on Fusion FeaturesMohammed Alshahrani0Mohammed Al-Jabbar1Ebrahim Mohammed Senan2Ibrahim Abdulrab Ahmed3Jamil Abdulhamid Mohammed Saif4Computer Department, Applied College, Najran University, Najran 66462, Saudi ArabiaComputer Department, Applied College, Najran University, Najran 66462, Saudi ArabiaDepartment of Artificial Intelligence, Faculty of Computer Science and Information Technology, Alrazi University, Sana’a, YemenComputer Department, Applied College, Najran University, Najran 66462, Saudi ArabiaComputer and Information Systems Department, Applied College, University of Bisha, Bisha 67714, Saudi ArabiaDiabetic retinopathy (DR) is a complication of diabetes that damages the delicate blood vessels of the retina and leads to blindness. Ophthalmologists rely on diagnosing the retina by imaging the fundus. The process takes a long time and needs skilled doctors to diagnose and determine the stage of DR. Therefore, automatic techniques using artificial intelligence play an important role in analyzing fundus images for the detection of the stages of DR development. However, diagnosis using artificial intelligence techniques is a difficult task and passes through many stages, and the extraction of representative features is important in reaching satisfactory results. Convolutional Neural Network (CNN) models play an important and distinct role in extracting features with high accuracy. In this study, fundus images were used for the detection of the developmental stages of DR by two proposed methods, each with two systems. The first proposed method uses GoogLeNet with SVM and ResNet-18 with SVM. The second method uses Feed-Forward Neural Networks (FFNN) based on the hybrid features extracted by first using GoogLeNet, Fuzzy color histogram (FCH), Gray Level Co-occurrence Matrix (GLCM), and Local Binary Pattern (LBP); followed by ResNet-18, FCH, GLCM and LBP. All the proposed methods obtained superior results. The FFNN network with hybrid features of ResNet-18, FCH, GLCM, and LBP obtained 99.7% accuracy, 99.6% precision, 99.6% sensitivity, 100% specificity, and 99.86% AUC.https://www.mdpi.com/2075-4418/13/17/2783CNNFFNNhybrid modelshybrid featuresdiabetic retinopathyhandcrafted |
| spellingShingle | Mohammed Alshahrani Mohammed Al-Jabbar Ebrahim Mohammed Senan Ibrahim Abdulrab Ahmed Jamil Abdulhamid Mohammed Saif Hybrid Methods for Fundus Image Analysis for Diagnosis of Diabetic Retinopathy Development Stages Based on Fusion Features Diagnostics CNN FFNN hybrid models hybrid features diabetic retinopathy handcrafted |
| title | Hybrid Methods for Fundus Image Analysis for Diagnosis of Diabetic Retinopathy Development Stages Based on Fusion Features |
| title_full | Hybrid Methods for Fundus Image Analysis for Diagnosis of Diabetic Retinopathy Development Stages Based on Fusion Features |
| title_fullStr | Hybrid Methods for Fundus Image Analysis for Diagnosis of Diabetic Retinopathy Development Stages Based on Fusion Features |
| title_full_unstemmed | Hybrid Methods for Fundus Image Analysis for Diagnosis of Diabetic Retinopathy Development Stages Based on Fusion Features |
| title_short | Hybrid Methods for Fundus Image Analysis for Diagnosis of Diabetic Retinopathy Development Stages Based on Fusion Features |
| title_sort | hybrid methods for fundus image analysis for diagnosis of diabetic retinopathy development stages based on fusion features |
| topic | CNN FFNN hybrid models hybrid features diabetic retinopathy handcrafted |
| url | https://www.mdpi.com/2075-4418/13/17/2783 |
| work_keys_str_mv | AT mohammedalshahrani hybridmethodsforfundusimageanalysisfordiagnosisofdiabeticretinopathydevelopmentstagesbasedonfusionfeatures AT mohammedaljabbar hybridmethodsforfundusimageanalysisfordiagnosisofdiabeticretinopathydevelopmentstagesbasedonfusionfeatures AT ebrahimmohammedsenan hybridmethodsforfundusimageanalysisfordiagnosisofdiabeticretinopathydevelopmentstagesbasedonfusionfeatures AT ibrahimabdulrabahmed hybridmethodsforfundusimageanalysisfordiagnosisofdiabeticretinopathydevelopmentstagesbasedonfusionfeatures AT jamilabdulhamidmohammedsaif hybridmethodsforfundusimageanalysisfordiagnosisofdiabeticretinopathydevelopmentstagesbasedonfusionfeatures |