AI-Based Automatic Detection and Classification of Diabetic Retinopathy Using U-Net and Deep Learning
Artificial intelligence is widely applied to automate Diabetic retinopathy diagnosis. Diabetes-related retinal vascular disease is one of the world’s most common leading causes of blindness and vision impairment. Therefore, automated DR detection systems would greatly benefit the early screening and...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-07-01
|
| Series: | Symmetry |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-8994/14/7/1427 |
| _version_ | 1797433016604164096 |
|---|---|
| author | Anas Bilal Liucun Zhu Anan Deng Huihui Lu Ning Wu |
| author_facet | Anas Bilal Liucun Zhu Anan Deng Huihui Lu Ning Wu |
| author_sort | Anas Bilal |
| collection | DOAJ |
| description | Artificial intelligence is widely applied to automate Diabetic retinopathy diagnosis. Diabetes-related retinal vascular disease is one of the world’s most common leading causes of blindness and vision impairment. Therefore, automated DR detection systems would greatly benefit the early screening and treatment of DR and prevent vision loss caused by it. Researchers have proposed several systems to detect abnormalities in retinal images in the past few years. However, Diabetic Retinopathy automatic detection methods have traditionally been based on hand-crafted feature extraction from the retinal images and using a classifier to obtain the final classification. DNN (Deep neural networks) have made several changes in the previous few years to assist overcome the problem mentioned above. We suggested a two-stage novel approach for automated DR classification in this research. Due to the low fraction of positive instances in the asymmetric Optic Disk (OD) and blood vessels (BV) detection system, preprocessing and data augmentation techniques are used to enhance the image quality and quantity. The first step uses two independent U-Net models for OD (optic disc) and BV (blood vessel) segmentation. In the second stage, the symmetric hybrid CNN-SVD model was created after preprocessing to extract and choose the most discriminant features following OD and BV extraction using Inception-V3 based on transfer learning, and detects DR by recognizing retinal biomarkers such as MA (microaneurysms), HM (hemorrhages), and exudates (EX). On EyePACS-1, Messidor-2, and DIARETDB0, the proposed methodology demonstrated state-of-the-art performance, with an average accuracy of 97.92%, 94.59%, and 93.52%, respectively. Extensive testing and comparisons with baseline approaches indicate the efficacy of the suggested methodology. |
| first_indexed | 2024-03-09T10:11:06Z |
| format | Article |
| id | doaj.art-024d6b16418e46209ce3cbf0864be3ae |
| institution | Directory Open Access Journal |
| issn | 2073-8994 |
| language | English |
| last_indexed | 2024-03-09T10:11:06Z |
| publishDate | 2022-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Symmetry |
| spelling | doaj.art-024d6b16418e46209ce3cbf0864be3ae2023-12-01T22:44:52ZengMDPI AGSymmetry2073-89942022-07-01147142710.3390/sym14071427AI-Based Automatic Detection and Classification of Diabetic Retinopathy Using U-Net and Deep LearningAnas Bilal0Liucun Zhu1Anan Deng2Huihui Lu3Ning Wu4College of Electronics and Information Engineering, Beibu Gulf University, Qinzhou 535011, ChinaAdvanced Science and Technology Research Institue, Beibu Gulf University, Qinzhou 535011, ChinaCollege of Electronics and Information Engineering, Beibu Gulf University, Qinzhou 535011, ChinaCollege of Electronics and Information Engineering, Beibu Gulf University, Qinzhou 535011, ChinaCollege of Electronics and Information Engineering, Beibu Gulf University, Qinzhou 535011, ChinaArtificial intelligence is widely applied to automate Diabetic retinopathy diagnosis. Diabetes-related retinal vascular disease is one of the world’s most common leading causes of blindness and vision impairment. Therefore, automated DR detection systems would greatly benefit the early screening and treatment of DR and prevent vision loss caused by it. Researchers have proposed several systems to detect abnormalities in retinal images in the past few years. However, Diabetic Retinopathy automatic detection methods have traditionally been based on hand-crafted feature extraction from the retinal images and using a classifier to obtain the final classification. DNN (Deep neural networks) have made several changes in the previous few years to assist overcome the problem mentioned above. We suggested a two-stage novel approach for automated DR classification in this research. Due to the low fraction of positive instances in the asymmetric Optic Disk (OD) and blood vessels (BV) detection system, preprocessing and data augmentation techniques are used to enhance the image quality and quantity. The first step uses two independent U-Net models for OD (optic disc) and BV (blood vessel) segmentation. In the second stage, the symmetric hybrid CNN-SVD model was created after preprocessing to extract and choose the most discriminant features following OD and BV extraction using Inception-V3 based on transfer learning, and detects DR by recognizing retinal biomarkers such as MA (microaneurysms), HM (hemorrhages), and exudates (EX). On EyePACS-1, Messidor-2, and DIARETDB0, the proposed methodology demonstrated state-of-the-art performance, with an average accuracy of 97.92%, 94.59%, and 93.52%, respectively. Extensive testing and comparisons with baseline approaches indicate the efficacy of the suggested methodology.https://www.mdpi.com/2073-8994/14/7/1427diabetic retinopathy (DR)DR detection and classificationautomatic diagnosisfeature extractionmulti-class segmentation and classificationfundus images (FIs) |
| spellingShingle | Anas Bilal Liucun Zhu Anan Deng Huihui Lu Ning Wu AI-Based Automatic Detection and Classification of Diabetic Retinopathy Using U-Net and Deep Learning Symmetry diabetic retinopathy (DR) DR detection and classification automatic diagnosis feature extraction multi-class segmentation and classification fundus images (FIs) |
| title | AI-Based Automatic Detection and Classification of Diabetic Retinopathy Using U-Net and Deep Learning |
| title_full | AI-Based Automatic Detection and Classification of Diabetic Retinopathy Using U-Net and Deep Learning |
| title_fullStr | AI-Based Automatic Detection and Classification of Diabetic Retinopathy Using U-Net and Deep Learning |
| title_full_unstemmed | AI-Based Automatic Detection and Classification of Diabetic Retinopathy Using U-Net and Deep Learning |
| title_short | AI-Based Automatic Detection and Classification of Diabetic Retinopathy Using U-Net and Deep Learning |
| title_sort | ai based automatic detection and classification of diabetic retinopathy using u net and deep learning |
| topic | diabetic retinopathy (DR) DR detection and classification automatic diagnosis feature extraction multi-class segmentation and classification fundus images (FIs) |
| url | https://www.mdpi.com/2073-8994/14/7/1427 |
| work_keys_str_mv | AT anasbilal aibasedautomaticdetectionandclassificationofdiabeticretinopathyusingunetanddeeplearning AT liucunzhu aibasedautomaticdetectionandclassificationofdiabeticretinopathyusingunetanddeeplearning AT anandeng aibasedautomaticdetectionandclassificationofdiabeticretinopathyusingunetanddeeplearning AT huihuilu aibasedautomaticdetectionandclassificationofdiabeticretinopathyusingunetanddeeplearning AT ningwu aibasedautomaticdetectionandclassificationofdiabeticretinopathyusingunetanddeeplearning |