Retinal disease identification using upgraded CLAHE filter and transfer convolution neural network
Retinal tissue plays a crucial part in human vision. Infections of retinal tissue and delayed treatment or untreated infection could lead to loss of vision. Additionally, the diagnosis is prone to errors when huge dataset is involved. Therefore, a fully automated model of identification of retinal d...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Korean Institute of Communication Sciences
2022
|
| Subjects: | |
| Online Access: | http://eprints.utm.my/104298/1/TanTianSwee2022_RetinalDiseaseIdentificationsingpgradedCLAHE.pdf |
| _version_ | 1796867629693009920 |
|---|---|
| author | Mohammed Sheet, Sinan S. Tan, Tian-Swee As’ari, M. A. W. Hitam, Wan Hazabbah Sia, Joyce S. Y. |
| author_facet | Mohammed Sheet, Sinan S. Tan, Tian-Swee As’ari, M. A. W. Hitam, Wan Hazabbah Sia, Joyce S. Y. |
| author_sort | Mohammed Sheet, Sinan S. |
| collection | ePrints |
| description | Retinal tissue plays a crucial part in human vision. Infections of retinal tissue and delayed treatment or untreated infection could lead to loss of vision. Additionally, the diagnosis is prone to errors when huge dataset is involved. Therefore, a fully automated model of identification of retinal disease is proposed to reduce human interaction while retaining its high accuracy classification results. This paper introduces an enhanced design of a fully automatic multi-class retina diseases prediction system to assist ophthalmologists in making speedy and accurate investigation. Retinal fundus images, which have been used in this study, were downloaded from the stare website (157 images from five classes: BDR, CRVO, CNV, PDR, and Normal). The five files were categorized according to their annotations conducted by the experienced specialists. The categorized images were first processed with the proposed upgraded contrast-limited adaptive histogram filter for image brightness enhancement, noise reduction, and intensity spectrum normalization. The proposed model was designed with transfer learning method and the fine-tuned pre-trained RESNET50. Eventually, the proposed framework was examined with performance evaluation parameters, recorded a classification rate with 100% sensitivity, 100% specificity, and 100% accuracy. The performance of the proposed model showed a magnificent superiority as compared to the state-of-the-art studies. |
| first_indexed | 2024-03-05T21:30:09Z |
| format | Article |
| id | utm.eprints-104298 |
| institution | Universiti Teknologi Malaysia - ePrints |
| language | English |
| last_indexed | 2024-03-05T21:30:09Z |
| publishDate | 2022 |
| publisher | Korean Institute of Communication Sciences |
| record_format | dspace |
| spelling | utm.eprints-1042982024-02-04T02:41:14Z http://eprints.utm.my/104298/ Retinal disease identification using upgraded CLAHE filter and transfer convolution neural network Mohammed Sheet, Sinan S. Tan, Tian-Swee As’ari, M. A. W. Hitam, Wan Hazabbah Sia, Joyce S. Y. TK Electrical engineering. Electronics Nuclear engineering Retinal tissue plays a crucial part in human vision. Infections of retinal tissue and delayed treatment or untreated infection could lead to loss of vision. Additionally, the diagnosis is prone to errors when huge dataset is involved. Therefore, a fully automated model of identification of retinal disease is proposed to reduce human interaction while retaining its high accuracy classification results. This paper introduces an enhanced design of a fully automatic multi-class retina diseases prediction system to assist ophthalmologists in making speedy and accurate investigation. Retinal fundus images, which have been used in this study, were downloaded from the stare website (157 images from five classes: BDR, CRVO, CNV, PDR, and Normal). The five files were categorized according to their annotations conducted by the experienced specialists. The categorized images were first processed with the proposed upgraded contrast-limited adaptive histogram filter for image brightness enhancement, noise reduction, and intensity spectrum normalization. The proposed model was designed with transfer learning method and the fine-tuned pre-trained RESNET50. Eventually, the proposed framework was examined with performance evaluation parameters, recorded a classification rate with 100% sensitivity, 100% specificity, and 100% accuracy. The performance of the proposed model showed a magnificent superiority as compared to the state-of-the-art studies. Korean Institute of Communication Sciences 2022 Article PeerReviewed application/pdf en http://eprints.utm.my/104298/1/TanTianSwee2022_RetinalDiseaseIdentificationsingpgradedCLAHE.pdf Mohammed Sheet, Sinan S. and Tan, Tian-Swee and As’ari, M. A. and W. Hitam, Wan Hazabbah and Sia, Joyce S. Y. (2022) Retinal disease identification using upgraded CLAHE filter and transfer convolution neural network. ICT Express, 8 (1). pp. 142-150. ISSN 2405-9595 http://dx.doi.org/10.1016/j.icte.2021.05.002 DOI : 10.1016/j.icte.2021.05.002 |
| spellingShingle | TK Electrical engineering. Electronics Nuclear engineering Mohammed Sheet, Sinan S. Tan, Tian-Swee As’ari, M. A. W. Hitam, Wan Hazabbah Sia, Joyce S. Y. Retinal disease identification using upgraded CLAHE filter and transfer convolution neural network |
| title | Retinal disease identification using upgraded CLAHE filter and transfer convolution neural network |
| title_full | Retinal disease identification using upgraded CLAHE filter and transfer convolution neural network |
| title_fullStr | Retinal disease identification using upgraded CLAHE filter and transfer convolution neural network |
| title_full_unstemmed | Retinal disease identification using upgraded CLAHE filter and transfer convolution neural network |
| title_short | Retinal disease identification using upgraded CLAHE filter and transfer convolution neural network |
| title_sort | retinal disease identification using upgraded clahe filter and transfer convolution neural network |
| topic | TK Electrical engineering. Electronics Nuclear engineering |
| url | http://eprints.utm.my/104298/1/TanTianSwee2022_RetinalDiseaseIdentificationsingpgradedCLAHE.pdf |
| work_keys_str_mv | AT mohammedsheetsinans retinaldiseaseidentificationusingupgradedclahefilterandtransferconvolutionneuralnetwork AT tantianswee retinaldiseaseidentificationusingupgradedclahefilterandtransferconvolutionneuralnetwork AT asarima retinaldiseaseidentificationusingupgradedclahefilterandtransferconvolutionneuralnetwork AT whitamwanhazabbah retinaldiseaseidentificationusingupgradedclahefilterandtransferconvolutionneuralnetwork AT siajoycesy retinaldiseaseidentificationusingupgradedclahefilterandtransferconvolutionneuralnetwork |