Identification of Diabetic Retinopathy Using Weighted Fusion Deep Learning Based on Dual-Channel Fundus Scans
It is a well-known fact that diabetic retinopathy (DR) is one of the most common causes of visual impairment between the ages of 25 and 74 around the globe. Diabetes is caused by persistently high blood glucose levels, which leads to blood vessel aggravations and vision loss. Early diagnosis can min...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-02-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/12/2/540 |
| _version_ | 1797481082785890304 |
|---|---|
| author | Grace Ugochi Nneji Jingye Cai Jianhua Deng Happy Nkanta Monday Md Altab Hossin Saifun Nahar |
| author_facet | Grace Ugochi Nneji Jingye Cai Jianhua Deng Happy Nkanta Monday Md Altab Hossin Saifun Nahar |
| author_sort | Grace Ugochi Nneji |
| collection | DOAJ |
| description | It is a well-known fact that diabetic retinopathy (DR) is one of the most common causes of visual impairment between the ages of 25 and 74 around the globe. Diabetes is caused by persistently high blood glucose levels, which leads to blood vessel aggravations and vision loss. Early diagnosis can minimise the risk of proliferated diabetic retinopathy, which is the advanced level of this disease, and having higher risk of severe impairment. Therefore, it becomes important to classify DR stages. To this effect, this paper presents a weighted fusion deep learning network (WFDLN) to automatically extract features and classify DR stages from fundus scans. The proposed framework aims to treat the issue of low quality and identify retinopathy symptoms in fundus images. Two channels of fundus images, namely, the contrast-limited adaptive histogram equalization (CLAHE) fundus images and the contrast-enhanced canny edge detection (CECED) fundus images are processed by WFDLN. Fundus-related features of CLAHE images are extracted by fine-tuned Inception V3, whereas the features of CECED fundus images are extracted using fine-tuned VGG-16. Both channels’ outputs are merged in a weighted approach, and softmax classification is used to determine the final recognition result. Experimental results show that the proposed network can identify the DR stages with high accuracy. The proposed method tested on the Messidor dataset reports an accuracy level of 98.5%, sensitivity of 98.9%, and specificity of 98.0%, whereas on the Kaggle dataset, the proposed model reports an accuracy level of 98.0%, sensitivity of 98.7%, and specificity of 97.8%. Compared with other models, our proposed network achieves comparable performance. |
| first_indexed | 2024-03-09T22:10:23Z |
| format | Article |
| id | doaj.art-6f4a347fdb6744559028ccf445591cde |
| institution | Directory Open Access Journal |
| issn | 2075-4418 |
| language | English |
| last_indexed | 2024-03-09T22:10:23Z |
| publishDate | 2022-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj.art-6f4a347fdb6744559028ccf445591cde2023-11-23T19:33:50ZengMDPI AGDiagnostics2075-44182022-02-0112254010.3390/diagnostics12020540Identification of Diabetic Retinopathy Using Weighted Fusion Deep Learning Based on Dual-Channel Fundus ScansGrace Ugochi Nneji0Jingye Cai1Jianhua Deng2Happy Nkanta Monday3Md Altab Hossin4Saifun Nahar5School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 611731, ChinaSchool of Management and Economics, University of Electronic Science and Technology of China, Chengdu 611731, ChinaDepartment of Information System and Technology, University of Missouri St. Louis, St. Louis, MO 63121, USAIt is a well-known fact that diabetic retinopathy (DR) is one of the most common causes of visual impairment between the ages of 25 and 74 around the globe. Diabetes is caused by persistently high blood glucose levels, which leads to blood vessel aggravations and vision loss. Early diagnosis can minimise the risk of proliferated diabetic retinopathy, which is the advanced level of this disease, and having higher risk of severe impairment. Therefore, it becomes important to classify DR stages. To this effect, this paper presents a weighted fusion deep learning network (WFDLN) to automatically extract features and classify DR stages from fundus scans. The proposed framework aims to treat the issue of low quality and identify retinopathy symptoms in fundus images. Two channels of fundus images, namely, the contrast-limited adaptive histogram equalization (CLAHE) fundus images and the contrast-enhanced canny edge detection (CECED) fundus images are processed by WFDLN. Fundus-related features of CLAHE images are extracted by fine-tuned Inception V3, whereas the features of CECED fundus images are extracted using fine-tuned VGG-16. Both channels’ outputs are merged in a weighted approach, and softmax classification is used to determine the final recognition result. Experimental results show that the proposed network can identify the DR stages with high accuracy. The proposed method tested on the Messidor dataset reports an accuracy level of 98.5%, sensitivity of 98.9%, and specificity of 98.0%, whereas on the Kaggle dataset, the proposed model reports an accuracy level of 98.0%, sensitivity of 98.7%, and specificity of 97.8%. Compared with other models, our proposed network achieves comparable performance.https://www.mdpi.com/2075-4418/12/2/540CLAHECECEDdeep learningfundus scandiabetic retinopathyimage identification |
| spellingShingle | Grace Ugochi Nneji Jingye Cai Jianhua Deng Happy Nkanta Monday Md Altab Hossin Saifun Nahar Identification of Diabetic Retinopathy Using Weighted Fusion Deep Learning Based on Dual-Channel Fundus Scans Diagnostics CLAHE CECED deep learning fundus scan diabetic retinopathy image identification |
| title | Identification of Diabetic Retinopathy Using Weighted Fusion Deep Learning Based on Dual-Channel Fundus Scans |
| title_full | Identification of Diabetic Retinopathy Using Weighted Fusion Deep Learning Based on Dual-Channel Fundus Scans |
| title_fullStr | Identification of Diabetic Retinopathy Using Weighted Fusion Deep Learning Based on Dual-Channel Fundus Scans |
| title_full_unstemmed | Identification of Diabetic Retinopathy Using Weighted Fusion Deep Learning Based on Dual-Channel Fundus Scans |
| title_short | Identification of Diabetic Retinopathy Using Weighted Fusion Deep Learning Based on Dual-Channel Fundus Scans |
| title_sort | identification of diabetic retinopathy using weighted fusion deep learning based on dual channel fundus scans |
| topic | CLAHE CECED deep learning fundus scan diabetic retinopathy image identification |
| url | https://www.mdpi.com/2075-4418/12/2/540 |
| work_keys_str_mv | AT graceugochinneji identificationofdiabeticretinopathyusingweightedfusiondeeplearningbasedondualchannelfundusscans AT jingyecai identificationofdiabeticretinopathyusingweightedfusiondeeplearningbasedondualchannelfundusscans AT jianhuadeng identificationofdiabeticretinopathyusingweightedfusiondeeplearningbasedondualchannelfundusscans AT happynkantamonday identificationofdiabeticretinopathyusingweightedfusiondeeplearningbasedondualchannelfundusscans AT mdaltabhossin identificationofdiabeticretinopathyusingweightedfusiondeeplearningbasedondualchannelfundusscans AT saifunnahar identificationofdiabeticretinopathyusingweightedfusiondeeplearningbasedondualchannelfundusscans |