Oct 2026· IEEE journal of biomedical and health informatics· Vol PP, pp. 1-14· 0 citations
Medicine
TL;DR
An explainable transformer-based fine-tuned model for retinal disease classification that uses a Vision Transformer architecture enhanced with a Multiple Instance Learning (MIL) mechanism is proposed, enabling it to simultaneously predict multiple co-existing pathologies.
Abstract
Retinal diseases are a leading cause of visual impairment globally. Early detection is crucial for effective management, and recent advances in ocular imaging and deep learning have facilitated the development of automated diagnostic systems. Traditional deep learning methods often struggle to effectively capture the overall structural context of the retina and the subtle, localised pathological features required for accurate multi label classification. Moreover, their decision-making processes typically lack transparency, limiting clinical trust and adoption. In this study, we propose an explainable transformer-based fine-tuned model for retinal disease classification that uses a Vision Transformer architecture enhanced with a Multiple Instance Learning (MIL) mechanism. The model is fine-tuned on the multi label retinal disease (MuReD) dataset, enabling it to simultaneously predict multiple co-existing pathologies. Experimental evaluation on the MuReD dataset demonstrates state-of-the-art performance, with the proposed fine-tuned MIL-VT achieving an ML_F1 (multi label F1) score of 0.672, representing an approximately 10 percentage-point increase over recent transformer-based baselines, alongside higher ML_mAP (multi label mAP) and comparable AUC scores. Additionally, we evaluate our model's performance on an independent Eye Disease Image (EDI) dataset, where it maintains better accuracy, achieving a macro-average F1 of approximately 0.92, highlighting its robust generalisation across datasets. An ablation study further validates the effectiveness of the MIL head and selective fine-tuning strategy, showing their substantial contributions to performance gains. To enhance clinical interpretability, we incorporate Grad CAM visualisations that highlight pathological regions associated with each predicted condition. The combination of better classification performance, explainability, and cross-dataset robustness underscores the potential of our proposed framework to improve automated retinal disease screening in diverse clinical settings.
Eye diseases are a leading cause of global vision impairment, yet detection is often hindered by limited resources and geographic barriers. While Deep Learning (DL) offers automated diagnostic solutions, its black-box nature challenges clinical trust. This research investigates whether interpretability can be integrate...
Nuzhat Tarannum Ibrahimy, M. Ibn Ibrahimy· Asian Journal of Electrical...· 0 citations
Visual impairment affects over 2.2 billion people globally, with 1 billion cases preventable through early detection. This research aims to address early detection challenges by explicitly developing a classification model for eye diseases using fundus images. We employed the Vision Transformer (ViT-B/16) with fine-tun...
Results show that the proposed framework provides a good trade-off between classification performance, computational requirements and interpretability and shows potential for automated OCT-based retinal disease screening support.
Mithun Vijayan, Goutham Veerapu, N. S.· Frontiers in Artificial Inte...· 0 citations
Undiagnosed ocular conditions in initial phases can progressively impair vision, potentially leading to critical visual dysfunctions. Fundus imaging has enabled the identification of several retinal disorders, notably diabetic retinopathy, glaucoma, and age-related macular degeneration. However, manual evaluation of th...
Onur Ceylan, A. Utku· Fırat Üniversitesi Mühendisl...· 0 citations
A relational, hybrid deep learning model that integrates convolutional, transformer-based, and graph attention models to classify binary and multiclass DR and demonstrates that performance and interpretability are enhanced by a combination of local, global, and relational representations in automated screening of DR.
Muradul Islam, Marisa Parvez Oishy, Ferdaus Anam Jibon et al.· Microvascular Research· 0 citations
An automated deep-learning framework for the multi-class classification of retinal fundus images into four categories: cataract, diabetic retinopathy, glaucoma, and normal is presented, demonstrating the potential of transfer-learning-based deep neural networks for scalable and accessible preliminary retinal disease sc...
Ankit Pandit and Aakash Patel· International Journal of Adv...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.