AdaptiveSwin-CNN: Adaptive Swin-CNN Framework with Self-Attention Fusion for Robust Multi-Class Retinal Disease Diagnosis
Retinal diseases account for a large fraction of global blinding disorders, requiring sophisticated diagnostic tools for early management. In this study, the author proposes a hybrid deep learning framework in the form of AdaptiveSwin-CNN that combines Swin Transformers and Convolutional Neural Netw...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-02-01
|
| Series: | AI |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2673-2688/6/2/28 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850081644766035968 |
|---|---|
| author | Imran Qureshi |
| author_facet | Imran Qureshi |
| author_sort | Imran Qureshi |
| collection | DOAJ |
| description | Retinal diseases account for a large fraction of global blinding disorders, requiring sophisticated diagnostic tools for early management. In this study, the author proposes a hybrid deep learning framework in the form of AdaptiveSwin-CNN that combines Swin Transformers and Convolutional Neural Networks (CNNs) for the classification of multi-class retinal diseases. In contrast to traditional architectures, AdaptiveSwin-CNN utilizes a brand-new Self-Attention Fusion Module (SAFM) to effectively combine multi-scale spatial and contextual options to alleviate class imbalance and give attention to refined retina lesions. Utilizing the adaptive baseline augmentation and dataset-driven preprocessing of input images, the AdaptiveSwin-CNN model resolves the problem of the variability of fundus images in the dataset. AdaptiveSwin-CNN achieved a mean accuracy of 98.89%, sensitivity of 95.2%, specificity of 96.7%, and F1-score of 97.2% on RFMiD and ODIR benchmarks, outperforming other solutions. An additional lightweight ensemble XGBoost classifier to reduce overfitting and increase interpretability also increased diagnostic accuracy. The results highlight AdaptiveSwin-CNN as a robust and computationally efficient decision-support system. |
| format | Article |
| id | doaj-art-503b82e445874a79a3b651b1af20810d |
| institution | DOAJ |
| issn | 2673-2688 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | AI |
| spelling | doaj-art-503b82e445874a79a3b651b1af20810d2025-08-20T02:44:40ZengMDPI AGAI2673-26882025-02-01622810.3390/ai6020028AdaptiveSwin-CNN: Adaptive Swin-CNN Framework with Self-Attention Fusion for Robust Multi-Class Retinal Disease DiagnosisImran Qureshi0College of Computer and Information Sciences, Imam Mohammad Ibn Saud Islamic University (IMSIU), Riyadh 11432, Saudi ArabiaRetinal diseases account for a large fraction of global blinding disorders, requiring sophisticated diagnostic tools for early management. In this study, the author proposes a hybrid deep learning framework in the form of AdaptiveSwin-CNN that combines Swin Transformers and Convolutional Neural Networks (CNNs) for the classification of multi-class retinal diseases. In contrast to traditional architectures, AdaptiveSwin-CNN utilizes a brand-new Self-Attention Fusion Module (SAFM) to effectively combine multi-scale spatial and contextual options to alleviate class imbalance and give attention to refined retina lesions. Utilizing the adaptive baseline augmentation and dataset-driven preprocessing of input images, the AdaptiveSwin-CNN model resolves the problem of the variability of fundus images in the dataset. AdaptiveSwin-CNN achieved a mean accuracy of 98.89%, sensitivity of 95.2%, specificity of 96.7%, and F1-score of 97.2% on RFMiD and ODIR benchmarks, outperforming other solutions. An additional lightweight ensemble XGBoost classifier to reduce overfitting and increase interpretability also increased diagnostic accuracy. The results highlight AdaptiveSwin-CNN as a robust and computationally efficient decision-support system.https://www.mdpi.com/2673-2688/6/2/28convolution neural networkfundus imagingmulti-class retinal disease classificationmulti-scale features fusionSwin Transformer |
| spellingShingle | Imran Qureshi AdaptiveSwin-CNN: Adaptive Swin-CNN Framework with Self-Attention Fusion for Robust Multi-Class Retinal Disease Diagnosis AI convolution neural network fundus imaging multi-class retinal disease classification multi-scale features fusion Swin Transformer |
| title | AdaptiveSwin-CNN: Adaptive Swin-CNN Framework with Self-Attention Fusion for Robust Multi-Class Retinal Disease Diagnosis |
| title_full | AdaptiveSwin-CNN: Adaptive Swin-CNN Framework with Self-Attention Fusion for Robust Multi-Class Retinal Disease Diagnosis |
| title_fullStr | AdaptiveSwin-CNN: Adaptive Swin-CNN Framework with Self-Attention Fusion for Robust Multi-Class Retinal Disease Diagnosis |
| title_full_unstemmed | AdaptiveSwin-CNN: Adaptive Swin-CNN Framework with Self-Attention Fusion for Robust Multi-Class Retinal Disease Diagnosis |
| title_short | AdaptiveSwin-CNN: Adaptive Swin-CNN Framework with Self-Attention Fusion for Robust Multi-Class Retinal Disease Diagnosis |
| title_sort | adaptiveswin cnn adaptive swin cnn framework with self attention fusion for robust multi class retinal disease diagnosis |
| topic | convolution neural network fundus imaging multi-class retinal disease classification multi-scale features fusion Swin Transformer |
| url | https://www.mdpi.com/2673-2688/6/2/28 |
| work_keys_str_mv | AT imranqureshi adaptiveswincnnadaptiveswincnnframeworkwithselfattentionfusionforrobustmulticlassretinaldiseasediagnosis |