Multitasking Deep Learning Model for Detection of Five Stages of Diabetic Retinopathy
Early diagnosis and treatment of diabetic retinopathy (DR) can reduce the risk of vision loss. There are five stages of DR consisting of no DR, mild DR, moderate DR, severe DR, and proliferate DR. This paper presents a multitask deep learning model to detect all the five stages of DR more accurately...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9526554/ |
| _version_ | 1819082812257468416 |
|---|---|
| author | Sharmin Majumder Nasser Kehtarnavaz |
| author_facet | Sharmin Majumder Nasser Kehtarnavaz |
| author_sort | Sharmin Majumder |
| collection | DOAJ |
| description | Early diagnosis and treatment of diabetic retinopathy (DR) can reduce the risk of vision loss. There are five stages of DR consisting of no DR, mild DR, moderate DR, severe DR, and proliferate DR. This paper presents a multitask deep learning model to detect all the five stages of DR more accurately than existing methods. The developed multitask model consists of one classification model and one regression model, each with its own loss function. After training the regression model and the classification model separately, the features extracted by these two models are concatenated and inputted to a multilayer perceptron network to classify the five stages of DR. A modified Squeeze Excitation Densely Connected deep neural network is also developed as part of this multitasking approach. The developed multitask model is applied to the two large Kaggle datasets of APTOS and EyePACS. The results obtained indicate that the developed multitask model achieved a weighted Kappa score of 0.90 and 0.88 for the APTOS and EyePACS datasets, respectively. In addition, the micro and macro average area under the receiver operating characteristic (ROC) curve was found to be 0.96, and 0.93, respectively, which are higher than existing methods for detecting the five stages of DR. |
| first_indexed | 2024-12-21T20:22:37Z |
| format | Article |
| id | doaj.art-10f80f68f18a435ca94cf3d43dc197a4 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-21T20:22:37Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-10f80f68f18a435ca94cf3d43dc197a42022-12-21T18:51:27ZengIEEEIEEE Access2169-35362021-01-01912322012323010.1109/ACCESS.2021.31092409526554Multitasking Deep Learning Model for Detection of Five Stages of Diabetic RetinopathySharmin Majumder0https://orcid.org/0000-0002-7534-8293Nasser Kehtarnavaz1https://orcid.org/0000-0001-5183-6359Department of Electrical and Computer Engineering, The University of Texas at Dallas, Richardson, TX, USADepartment of Electrical and Computer Engineering, The University of Texas at Dallas, Richardson, TX, USAEarly diagnosis and treatment of diabetic retinopathy (DR) can reduce the risk of vision loss. There are five stages of DR consisting of no DR, mild DR, moderate DR, severe DR, and proliferate DR. This paper presents a multitask deep learning model to detect all the five stages of DR more accurately than existing methods. The developed multitask model consists of one classification model and one regression model, each with its own loss function. After training the regression model and the classification model separately, the features extracted by these two models are concatenated and inputted to a multilayer perceptron network to classify the five stages of DR. A modified Squeeze Excitation Densely Connected deep neural network is also developed as part of this multitasking approach. The developed multitask model is applied to the two large Kaggle datasets of APTOS and EyePACS. The results obtained indicate that the developed multitask model achieved a weighted Kappa score of 0.90 and 0.88 for the APTOS and EyePACS datasets, respectively. In addition, the micro and macro average area under the receiver operating characteristic (ROC) curve was found to be 0.96, and 0.93, respectively, which are higher than existing methods for detecting the five stages of DR.https://ieeexplore.ieee.org/document/9526554/Diabetic retinopathy (DR)eye fundus imagesfive stages of diabetic retinopathymultitasking deep neural networksqueeze excitation densely connected network |
| spellingShingle | Sharmin Majumder Nasser Kehtarnavaz Multitasking Deep Learning Model for Detection of Five Stages of Diabetic Retinopathy IEEE Access Diabetic retinopathy (DR) eye fundus images five stages of diabetic retinopathy multitasking deep neural network squeeze excitation densely connected network |
| title | Multitasking Deep Learning Model for Detection of Five Stages of Diabetic Retinopathy |
| title_full | Multitasking Deep Learning Model for Detection of Five Stages of Diabetic Retinopathy |
| title_fullStr | Multitasking Deep Learning Model for Detection of Five Stages of Diabetic Retinopathy |
| title_full_unstemmed | Multitasking Deep Learning Model for Detection of Five Stages of Diabetic Retinopathy |
| title_short | Multitasking Deep Learning Model for Detection of Five Stages of Diabetic Retinopathy |
| title_sort | multitasking deep learning model for detection of five stages of diabetic retinopathy |
| topic | Diabetic retinopathy (DR) eye fundus images five stages of diabetic retinopathy multitasking deep neural network squeeze excitation densely connected network |
| url | https://ieeexplore.ieee.org/document/9526554/ |
| work_keys_str_mv | AT sharminmajumder multitaskingdeeplearningmodelfordetectionoffivestagesofdiabeticretinopathy AT nasserkehtarnavaz multitaskingdeeplearningmodelfordetectionoffivestagesofdiabeticretinopathy |