RetinaVision: XAI-Driven Augmented Regulation for Precise Retinal Disease Classification using deep learning framework
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912919623565312 |
|---|---|
| author | Noor, Mohammad Tahmid Abrar, Shayan Mahi, Jannatul Adan Mia, Md Parvez Hridoy, Asaduzzaman Ghosh, Samanta |
| author_facet | Noor, Mohammad Tahmid Abrar, Shayan Mahi, Jannatul Adan Mia, Md Parvez Hridoy, Asaduzzaman Ghosh, Samanta |
| contents | Early and accurate classification of retinal diseases is critical to counter vision loss and for guiding clinical management of retinal diseases. In this study, we proposed a deep learning method for retinal disease classification utilizing optical coherence tomography (OCT) images from the Retinal OCT Image Classification - C8 dataset (comprising 24,000 labeled images spanning eight conditions). Images were resized to 224x224 px and tested on convolutional neural network (CNN) architectures: Xception and InceptionV3. Data augmentation techniques (CutMix, MixUp) were employed to enhance model generalization. Additionally, we applied GradCAM and LIME for interpretability evaluation. We implemented this in a real-world scenario via our web application named RetinaVision. This study found that Xception was the most accurate network (95.25%), followed closely by InceptionV3 (94.82%). These results suggest that deep learning methods allow effective OCT retinal disease classification and highlight the importance of implementing accuracy and interpretability for clinical applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_19324 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | RetinaVision: XAI-Driven Augmented Regulation for Precise Retinal Disease Classification using deep learning framework Noor, Mohammad Tahmid Abrar, Shayan Mahi, Jannatul Adan Mia, Md Parvez Hridoy, Asaduzzaman Ghosh, Samanta Computer Vision and Pattern Recognition Artificial Intelligence Early and accurate classification of retinal diseases is critical to counter vision loss and for guiding clinical management of retinal diseases. In this study, we proposed a deep learning method for retinal disease classification utilizing optical coherence tomography (OCT) images from the Retinal OCT Image Classification - C8 dataset (comprising 24,000 labeled images spanning eight conditions). Images were resized to 224x224 px and tested on convolutional neural network (CNN) architectures: Xception and InceptionV3. Data augmentation techniques (CutMix, MixUp) were employed to enhance model generalization. Additionally, we applied GradCAM and LIME for interpretability evaluation. We implemented this in a real-world scenario via our web application named RetinaVision. This study found that Xception was the most accurate network (95.25%), followed closely by InceptionV3 (94.82%). These results suggest that deep learning methods allow effective OCT retinal disease classification and highlight the importance of implementing accuracy and interpretability for clinical applications. |
| title | RetinaVision: XAI-Driven Augmented Regulation for Precise Retinal Disease Classification using deep learning framework |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2602.19324 |