Deep Feature Vectors Concatenation for Eye Disease Detection Using Fundus Image
Fundus image is an image that captures the back of the eye (retina), which plays an important role in the detection of a disease, including diabetic retinopathy (DR). It is the most common complication in diabetics that remains an important cause of visual impairment, especially in the young and eco...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-12-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/11/1/23 |
| _version_ | 1797499275818565632 |
|---|---|
| author | Radifa Hilya Paradisa Alhadi Bustamam Wibowo Mangunwardoyo Andi Arus Victor Anggun Rama Yudantha Prasnurzaki Anki |
| author_facet | Radifa Hilya Paradisa Alhadi Bustamam Wibowo Mangunwardoyo Andi Arus Victor Anggun Rama Yudantha Prasnurzaki Anki |
| author_sort | Radifa Hilya Paradisa |
| collection | DOAJ |
| description | Fundus image is an image that captures the back of the eye (retina), which plays an important role in the detection of a disease, including diabetic retinopathy (DR). It is the most common complication in diabetics that remains an important cause of visual impairment, especially in the young and economically active age group. In patients with DR, early diagnosis can effectively help prevent the risk of vision loss. DR screening was performed by an ophthalmologist by analysing the lesions on the fundus image. However, the increasing prevalence of DR is not proportional to the availability of ophthalmologists who can read fundus images. It can lead to delayed prevention and management of DR. Therefore, there is a need for an automated diagnostic system as it can help ophthalmologists increase the efficiency of the diagnostic process. This paper provides a deep learning approach with the concatenate model for fundus image classification with three classes: no DR, non-proliferative diabetic retinopathy (NPDR), and proliferative diabetic retinopathy (PDR). The model architecture used is DenseNet121 and Inception-ResNetV2. The feature extraction results from the two models are combined and classified using the multilayer perceptron (MLP) method. The method that we propose gives an improvement compared to a single model with the results of accuracy, and average precision and recall of 91% and 90% for the F1-score, respectively. This experiment demonstrates that our proposed deep-learning approach is effective for the automatic DR classification using fundus photo data. |
| first_indexed | 2024-03-10T03:45:08Z |
| format | Article |
| id | doaj.art-1eeb28d235784b6991fb796193d2ca69 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-10T03:45:08Z |
| publishDate | 2021-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-1eeb28d235784b6991fb796193d2ca692023-11-23T11:21:42ZengMDPI AGElectronics2079-92922021-12-011112310.3390/electronics11010023Deep Feature Vectors Concatenation for Eye Disease Detection Using Fundus ImageRadifa Hilya Paradisa0Alhadi Bustamam1Wibowo Mangunwardoyo2Andi Arus Victor3Anggun Rama Yudantha4Prasnurzaki Anki5Department of Mathematics, Faculty of Mathematics and Natural Science, Universitas Indonesia, Depok 16424, IndonesiaDepartment of Mathematics, Faculty of Mathematics and Natural Science, Universitas Indonesia, Depok 16424, IndonesiaDepartment of Biology, Faculty of Mathematics and Natural Science, Universitas Indonesia, Depok 16424, IndonesiaDepartment of Ophthalmology, Faculty of Medicine, Universitas Indonesia, Jakarta Pusat 10430, IndonesiaDepartment of Ophthalmology, Faculty of Medicine, Universitas Indonesia, Jakarta Pusat 10430, IndonesiaDepartment of Mathematics, Faculty of Mathematics and Natural Science, Universitas Indonesia, Depok 16424, IndonesiaFundus image is an image that captures the back of the eye (retina), which plays an important role in the detection of a disease, including diabetic retinopathy (DR). It is the most common complication in diabetics that remains an important cause of visual impairment, especially in the young and economically active age group. In patients with DR, early diagnosis can effectively help prevent the risk of vision loss. DR screening was performed by an ophthalmologist by analysing the lesions on the fundus image. However, the increasing prevalence of DR is not proportional to the availability of ophthalmologists who can read fundus images. It can lead to delayed prevention and management of DR. Therefore, there is a need for an automated diagnostic system as it can help ophthalmologists increase the efficiency of the diagnostic process. This paper provides a deep learning approach with the concatenate model for fundus image classification with three classes: no DR, non-proliferative diabetic retinopathy (NPDR), and proliferative diabetic retinopathy (PDR). The model architecture used is DenseNet121 and Inception-ResNetV2. The feature extraction results from the two models are combined and classified using the multilayer perceptron (MLP) method. The method that we propose gives an improvement compared to a single model with the results of accuracy, and average precision and recall of 91% and 90% for the F1-score, respectively. This experiment demonstrates that our proposed deep-learning approach is effective for the automatic DR classification using fundus photo data.https://www.mdpi.com/2079-9292/11/1/23diabetic retinopathydensenet121inception-resnetv2concatenate |
| spellingShingle | Radifa Hilya Paradisa Alhadi Bustamam Wibowo Mangunwardoyo Andi Arus Victor Anggun Rama Yudantha Prasnurzaki Anki Deep Feature Vectors Concatenation for Eye Disease Detection Using Fundus Image Electronics diabetic retinopathy densenet121 inception-resnetv2 concatenate |
| title | Deep Feature Vectors Concatenation for Eye Disease Detection Using Fundus Image |
| title_full | Deep Feature Vectors Concatenation for Eye Disease Detection Using Fundus Image |
| title_fullStr | Deep Feature Vectors Concatenation for Eye Disease Detection Using Fundus Image |
| title_full_unstemmed | Deep Feature Vectors Concatenation for Eye Disease Detection Using Fundus Image |
| title_short | Deep Feature Vectors Concatenation for Eye Disease Detection Using Fundus Image |
| title_sort | deep feature vectors concatenation for eye disease detection using fundus image |
| topic | diabetic retinopathy densenet121 inception-resnetv2 concatenate |
| url | https://www.mdpi.com/2079-9292/11/1/23 |
| work_keys_str_mv | AT radifahilyaparadisa deepfeaturevectorsconcatenationforeyediseasedetectionusingfundusimage AT alhadibustamam deepfeaturevectorsconcatenationforeyediseasedetectionusingfundusimage AT wibowomangunwardoyo deepfeaturevectorsconcatenationforeyediseasedetectionusingfundusimage AT andiarusvictor deepfeaturevectorsconcatenationforeyediseasedetectionusingfundusimage AT anggunramayudantha deepfeaturevectorsconcatenationforeyediseasedetectionusingfundusimage AT prasnurzakianki deepfeaturevectorsconcatenationforeyediseasedetectionusingfundusimage |