Eye Disease Detection Enhancement Using a Multi-Stage Deep Learning Approach
Eye diseases, a significant global health concern, require timely detection to prevent vision loss. The alarming prevalence of eye diseases necessitates immediate action through early diagnosis, making it urgent to develop an automatic detection system. Many researchers have been working to develop...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10707606/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846113846363684864 |
|---|---|
| author | Md Zahin Muntaqim Tangin Amir Smrity Abu Saleh Musa Miah Hasan Muhammad Kafi Taosin Tamanna Fahmid Al Farid Md Abdur Rahim Hezerul Abdul Karim Sarina Mansor |
| author_facet | Md Zahin Muntaqim Tangin Amir Smrity Abu Saleh Musa Miah Hasan Muhammad Kafi Taosin Tamanna Fahmid Al Farid Md Abdur Rahim Hezerul Abdul Karim Sarina Mansor |
| author_sort | Md Zahin Muntaqim |
| collection | DOAJ |
| description | Eye diseases, a significant global health concern, require timely detection to prevent vision loss. The alarming prevalence of eye diseases necessitates immediate action through early diagnosis, making it urgent to develop an automatic detection system. Many researchers have been working to develop such systems. Yet, existing solutions still face difficulties in achieving high-performance accuracy due to challenges like lacking feature effectiveness, high computational demands, and incomplete disease coverage. To overcome these challenges, we proposed a novel eye-disease detection system leveraging multi-stage deep learning technologies. In the study, we employed a preprocessing approach to ensure the system’s robustness against rotation and translation, enhancing its effectiveness across varied conditions. Then, we employed a lightweight three-stage deep learning approach for extracting effective features and specific advantages. In the procedure, Stage 1 focuses on extracting fine-grained features using deep learning layers where the layers can automatically learn and identify complex patterns associated with various eye diseases, improving feature effectiveness and overall system accuracy. Then, we employed stage 2, which is constructed with two branches, each composed of convolutional blocks and identity blocks; this stage extracts hierarchical features by concatenating the outputs of the two branches. This hierarchical approach captures both low-level and high-level features, enhancing the extracted features’ richness and robustness and leading to better classification performance. We concatenated the two branch features that fed into the classification module, producing a probabilistic eye disease presence map. By converting hierarchical features into precise disease predictions, this stage ensures accurate probabilistic outputs, aiding better decision-making and diagnosis. We evaluated the proposed model with OCT2017, Dataset-101, and Retinal OCT C8 datasets, demonstrating an accuracy improvement of up to 1% over existing state-of-the-art models in both multi-class and binary classification tasks. The lightweight design and reduced computational requirements of the model highlight its applicability for real-world deployment, particularly in resource-constrained environments. This computer-aided detection system offers a meaningful advancement in the field of automatic eye disease detection by providing a more accurate and efficient tool that can be deployed widely. |
| format | Article |
| id | doaj-art-1c7ee8b79c8640deb88d465de7c897b6 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-1c7ee8b79c8640deb88d465de7c897b62024-12-21T00:00:37ZengIEEEIEEE Access2169-35362024-01-011219139319140710.1109/ACCESS.2024.347641210707606Eye Disease Detection Enhancement Using a Multi-Stage Deep Learning ApproachMd Zahin Muntaqim0Tangin Amir Smrity1Abu Saleh Musa Miah2https://orcid.org/0000-0002-1238-0464Hasan Muhammad Kafi3https://orcid.org/0000-0002-1242-7277Taosin Tamanna4Fahmid Al Farid5https://orcid.org/0000-0003-2625-2348Md Abdur Rahim6https://orcid.org/0000-0003-2300-1420Hezerul Abdul Karim7https://orcid.org/0000-0002-7613-4596Sarina Mansor8https://orcid.org/0000-0002-4939-0631Department of Computer Science and Engineering, Bangladesh Army University of Science and Technology, Saidpur, Nilphamari, BangladeshDepartment of Computer Science and Engineering, Bangladesh Army University of Science and Technology, Saidpur, Nilphamari, BangladeshDepartment of Computer Science and Engineering, Bangladesh Army University of Science and Technology, Saidpur, Nilphamari, BangladeshDepartment of Computer Science and Engineering, Bangladesh Army University of Science and Technology, Saidpur, Nilphamari, BangladeshDepartment of Computer Science and Engineering, Bangladesh Army University of Science and Technology, Saidpur, Nilphamari, BangladeshFaculty of Engineering, Multimedia University, Cyberjaya, MalaysiaDepartment of Computer Science and Engineering, Pabna University of Science and Technology, Pabna, BangladeshFaculty of Engineering, Multimedia University, Cyberjaya, MalaysiaFaculty of Engineering, Multimedia University, Cyberjaya, MalaysiaEye diseases, a significant global health concern, require timely detection to prevent vision loss. The alarming prevalence of eye diseases necessitates immediate action through early diagnosis, making it urgent to develop an automatic detection system. Many researchers have been working to develop such systems. Yet, existing solutions still face difficulties in achieving high-performance accuracy due to challenges like lacking feature effectiveness, high computational demands, and incomplete disease coverage. To overcome these challenges, we proposed a novel eye-disease detection system leveraging multi-stage deep learning technologies. In the study, we employed a preprocessing approach to ensure the system’s robustness against rotation and translation, enhancing its effectiveness across varied conditions. Then, we employed a lightweight three-stage deep learning approach for extracting effective features and specific advantages. In the procedure, Stage 1 focuses on extracting fine-grained features using deep learning layers where the layers can automatically learn and identify complex patterns associated with various eye diseases, improving feature effectiveness and overall system accuracy. Then, we employed stage 2, which is constructed with two branches, each composed of convolutional blocks and identity blocks; this stage extracts hierarchical features by concatenating the outputs of the two branches. This hierarchical approach captures both low-level and high-level features, enhancing the extracted features’ richness and robustness and leading to better classification performance. We concatenated the two branch features that fed into the classification module, producing a probabilistic eye disease presence map. By converting hierarchical features into precise disease predictions, this stage ensures accurate probabilistic outputs, aiding better decision-making and diagnosis. We evaluated the proposed model with OCT2017, Dataset-101, and Retinal OCT C8 datasets, demonstrating an accuracy improvement of up to 1% over existing state-of-the-art models in both multi-class and binary classification tasks. The lightweight design and reduced computational requirements of the model highlight its applicability for real-world deployment, particularly in resource-constrained environments. This computer-aided detection system offers a meaningful advancement in the field of automatic eye disease detection by providing a more accurate and efficient tool that can be deployed widely.https://ieeexplore.ieee.org/document/10707606/Eye disease classificationdeep learning based classificationCNN-based classification |
| spellingShingle | Md Zahin Muntaqim Tangin Amir Smrity Abu Saleh Musa Miah Hasan Muhammad Kafi Taosin Tamanna Fahmid Al Farid Md Abdur Rahim Hezerul Abdul Karim Sarina Mansor Eye Disease Detection Enhancement Using a Multi-Stage Deep Learning Approach IEEE Access Eye disease classification deep learning based classification CNN-based classification |
| title | Eye Disease Detection Enhancement Using a Multi-Stage Deep Learning Approach |
| title_full | Eye Disease Detection Enhancement Using a Multi-Stage Deep Learning Approach |
| title_fullStr | Eye Disease Detection Enhancement Using a Multi-Stage Deep Learning Approach |
| title_full_unstemmed | Eye Disease Detection Enhancement Using a Multi-Stage Deep Learning Approach |
| title_short | Eye Disease Detection Enhancement Using a Multi-Stage Deep Learning Approach |
| title_sort | eye disease detection enhancement using a multi stage deep learning approach |
| topic | Eye disease classification deep learning based classification CNN-based classification |
| url | https://ieeexplore.ieee.org/document/10707606/ |
| work_keys_str_mv | AT mdzahinmuntaqim eyediseasedetectionenhancementusingamultistagedeeplearningapproach AT tanginamirsmrity eyediseasedetectionenhancementusingamultistagedeeplearningapproach AT abusalehmusamiah eyediseasedetectionenhancementusingamultistagedeeplearningapproach AT hasanmuhammadkafi eyediseasedetectionenhancementusingamultistagedeeplearningapproach AT taosintamanna eyediseasedetectionenhancementusingamultistagedeeplearningapproach AT fahmidalfarid eyediseasedetectionenhancementusingamultistagedeeplearningapproach AT mdabdurrahim eyediseasedetectionenhancementusingamultistagedeeplearningapproach AT hezerulabdulkarim eyediseasedetectionenhancementusingamultistagedeeplearningapproach AT sarinamansor eyediseasedetectionenhancementusingamultistagedeeplearningapproach |