An Adoptive Threshold-Based Multi-Level Deep Convolutional Neural Network for Glaucoma Eye Disease Detection and Classification
Glaucoma, an eye disease, occurs due to Retinal damages and it is an ordinary cause of blindness. Most of the available examining procedures are too long and require manual instructions to use them. In this work, we proposed a multi-level deep convolutional neural network (ML-DCNN) architecture on r...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-08-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/10/8/602 |
| _version_ | 1797557403666874368 |
|---|---|
| author | Muhammad Aamir Muhammad Irfan Tariq Ali Ghulam Ali Ahmad Shaf Alqahtani Saeed S Ali Al-Beshri Tariq Alasbali Mater H. Mahnashi |
| author_facet | Muhammad Aamir Muhammad Irfan Tariq Ali Ghulam Ali Ahmad Shaf Alqahtani Saeed S Ali Al-Beshri Tariq Alasbali Mater H. Mahnashi |
| author_sort | Muhammad Aamir |
| collection | DOAJ |
| description | Glaucoma, an eye disease, occurs due to Retinal damages and it is an ordinary cause of blindness. Most of the available examining procedures are too long and require manual instructions to use them. In this work, we proposed a multi-level deep convolutional neural network (ML-DCNN) architecture on retinal fundus images to diagnose glaucoma. We collected a retinal fundus images database from the local hospital. The fundus images are pre-processed by an adaptive histogram equalizer to reduce the noise of images. The ML-DCNN architecture is used for features extraction and classification into two phases, one for glaucoma detection known as detection-net and the second one is classification-net used for classification of affected retinal glaucoma images into three different categories: Advanced, Moderate and Early. The proposed model is tested on 1338 retinal glaucoma images and performance is measured in the form of different statistical terms known as sensitivity (SE), specificity (SP), accuracy (ACC), and precision (PRE). On average, SE of 97.04%, SP of 98.99%, ACC of 99.39%, and PRC of 98.2% are achieved. The obtained outcomes are comparable to the state-of-the-art systems and achieved competitive results to solve the glaucoma eye disease problems for complex glaucoma eye disease cases. |
| first_indexed | 2024-03-10T17:16:35Z |
| format | Article |
| id | doaj.art-c24ed26ba8684ae9b88e2ff408e166b5 |
| institution | Directory Open Access Journal |
| issn | 2075-4418 |
| language | English |
| last_indexed | 2024-03-10T17:16:35Z |
| publishDate | 2020-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj.art-c24ed26ba8684ae9b88e2ff408e166b52023-11-20T10:28:48ZengMDPI AGDiagnostics2075-44182020-08-0110860210.3390/diagnostics10080602An Adoptive Threshold-Based Multi-Level Deep Convolutional Neural Network for Glaucoma Eye Disease Detection and ClassificationMuhammad Aamir0Muhammad Irfan1Tariq Ali2Ghulam Ali3Ahmad Shaf4Alqahtani Saeed S5Ali Al-Beshri6Tariq Alasbali7Mater H. Mahnashi8Department of Computer Science, COMSATS University Islamabad Sahiwal Campus, Sahiwal 57000, PakistanCollege of Engineering, Electrical Engineering Department, Najran University, Najran 61441, Saudi ArabiaCollege of Engineering, Electrical Engineering Department, Najran University, Najran 61441, Saudi ArabiaDepartment of Computer Science, University of Okara, Okara 56300, PakistanDepartment of Computer Science, COMSATS University Islamabad Sahiwal Campus, Sahiwal 57000, PakistanDepartment of Surgery, Faculty of Medicine, Najran University, Najran 61441, Saudi ArabiaKing Khalid Eye Specialist Hospital, Riyadh 12329, Saudi ArabiaDepartment of Ophthalmology, College of Medicine, Al Imam Mohammad Ibn Saud Islamic University (IMSIU), Riyadh 4233-13317, Saudi ArabiaDepartment of Pharmaceutical Chemistry, College of Pharmacy, Najran University, Najran 61441, Saudi ArabiaGlaucoma, an eye disease, occurs due to Retinal damages and it is an ordinary cause of blindness. Most of the available examining procedures are too long and require manual instructions to use them. In this work, we proposed a multi-level deep convolutional neural network (ML-DCNN) architecture on retinal fundus images to diagnose glaucoma. We collected a retinal fundus images database from the local hospital. The fundus images are pre-processed by an adaptive histogram equalizer to reduce the noise of images. The ML-DCNN architecture is used for features extraction and classification into two phases, one for glaucoma detection known as detection-net and the second one is classification-net used for classification of affected retinal glaucoma images into three different categories: Advanced, Moderate and Early. The proposed model is tested on 1338 retinal glaucoma images and performance is measured in the form of different statistical terms known as sensitivity (SE), specificity (SP), accuracy (ACC), and precision (PRE). On average, SE of 97.04%, SP of 98.99%, ACC of 99.39%, and PRC of 98.2% are achieved. The obtained outcomes are comparable to the state-of-the-art systems and achieved competitive results to solve the glaucoma eye disease problems for complex glaucoma eye disease cases.https://www.mdpi.com/2075-4418/10/8/602ML-DCNNglaucoma deep-learningcomputer visionconvolutional neural networkglaucoma eye disease |
| spellingShingle | Muhammad Aamir Muhammad Irfan Tariq Ali Ghulam Ali Ahmad Shaf Alqahtani Saeed S Ali Al-Beshri Tariq Alasbali Mater H. Mahnashi An Adoptive Threshold-Based Multi-Level Deep Convolutional Neural Network for Glaucoma Eye Disease Detection and Classification Diagnostics ML-DCNN glaucoma deep-learning computer vision convolutional neural network glaucoma eye disease |
| title | An Adoptive Threshold-Based Multi-Level Deep Convolutional Neural Network for Glaucoma Eye Disease Detection and Classification |
| title_full | An Adoptive Threshold-Based Multi-Level Deep Convolutional Neural Network for Glaucoma Eye Disease Detection and Classification |
| title_fullStr | An Adoptive Threshold-Based Multi-Level Deep Convolutional Neural Network for Glaucoma Eye Disease Detection and Classification |
| title_full_unstemmed | An Adoptive Threshold-Based Multi-Level Deep Convolutional Neural Network for Glaucoma Eye Disease Detection and Classification |
| title_short | An Adoptive Threshold-Based Multi-Level Deep Convolutional Neural Network for Glaucoma Eye Disease Detection and Classification |
| title_sort | adoptive threshold based multi level deep convolutional neural network for glaucoma eye disease detection and classification |
| topic | ML-DCNN glaucoma deep-learning computer vision convolutional neural network glaucoma eye disease |
| url | https://www.mdpi.com/2075-4418/10/8/602 |
| work_keys_str_mv | AT muhammadaamir anadoptivethresholdbasedmultileveldeepconvolutionalneuralnetworkforglaucomaeyediseasedetectionandclassification AT muhammadirfan anadoptivethresholdbasedmultileveldeepconvolutionalneuralnetworkforglaucomaeyediseasedetectionandclassification AT tariqali anadoptivethresholdbasedmultileveldeepconvolutionalneuralnetworkforglaucomaeyediseasedetectionandclassification AT ghulamali anadoptivethresholdbasedmultileveldeepconvolutionalneuralnetworkforglaucomaeyediseasedetectionandclassification AT ahmadshaf anadoptivethresholdbasedmultileveldeepconvolutionalneuralnetworkforglaucomaeyediseasedetectionandclassification AT alqahtanisaeeds anadoptivethresholdbasedmultileveldeepconvolutionalneuralnetworkforglaucomaeyediseasedetectionandclassification AT alialbeshri anadoptivethresholdbasedmultileveldeepconvolutionalneuralnetworkforglaucomaeyediseasedetectionandclassification AT tariqalasbali anadoptivethresholdbasedmultileveldeepconvolutionalneuralnetworkforglaucomaeyediseasedetectionandclassification AT materhmahnashi anadoptivethresholdbasedmultileveldeepconvolutionalneuralnetworkforglaucomaeyediseasedetectionandclassification AT muhammadaamir adoptivethresholdbasedmultileveldeepconvolutionalneuralnetworkforglaucomaeyediseasedetectionandclassification AT muhammadirfan adoptivethresholdbasedmultileveldeepconvolutionalneuralnetworkforglaucomaeyediseasedetectionandclassification AT tariqali adoptivethresholdbasedmultileveldeepconvolutionalneuralnetworkforglaucomaeyediseasedetectionandclassification AT ghulamali adoptivethresholdbasedmultileveldeepconvolutionalneuralnetworkforglaucomaeyediseasedetectionandclassification AT ahmadshaf adoptivethresholdbasedmultileveldeepconvolutionalneuralnetworkforglaucomaeyediseasedetectionandclassification AT alqahtanisaeeds adoptivethresholdbasedmultileveldeepconvolutionalneuralnetworkforglaucomaeyediseasedetectionandclassification AT alialbeshri adoptivethresholdbasedmultileveldeepconvolutionalneuralnetworkforglaucomaeyediseasedetectionandclassification AT tariqalasbali adoptivethresholdbasedmultileveldeepconvolutionalneuralnetworkforglaucomaeyediseasedetectionandclassification AT materhmahnashi adoptivethresholdbasedmultileveldeepconvolutionalneuralnetworkforglaucomaeyediseasedetectionandclassification |