مجلة الجامعة الإسلامية للعلوم التطبيقية

Detection of Retinopathy Diabetic Using Explainable AI: Interpretable Deep Learning Models in Clinical Practice

Turki Alghamdi

الكلمات مفتاحية: Diabetic Retinopathy; Explainable AI (XAI); Convolutional Neural Network (CNN); Grad-CAM; SHAP; Medical Image Interpretation.

التخصص العام: Engineering

التخصص الدقيق: Computer Networks

https://doi.org/10.63070/jesc.2025.018; Received 31 May 2025; Revised 15 June 2025; Accepted 04 July 2025. Available online 08 September 2025.
DownloadPDF
الملخص

Diabetic Retinopathy (DR) is a significant threat?to eyesight and blindness globally, particularly for those with a more extended diabetes history. Deep learning has achieved high accuracy for DR detection using fundus images; however, the "black-box" nature hinders its application in clinical practice, where interpretability is important. In this work, we propose a solution to the model transparency problem by introducing an XAI-enhanced diagnostic framework utilizing CNNs. We present an explainable deep learning framework based on a convolutional neural network (CNN), specifically ResNet-50, which has been fine-tuned on the APTOS 2019 Blindness Detection dataset. To narrow the interpretability gap, we utilize the Grad-CAM and SHAP visualization methods, which generate class-discriminative heatmaps and feature-attribution plots, respectively. The multi-class diabetes retinopathy (DR) classification result yielded an overall accuracy of 83% for the model. Importantly, the explanation agreement score with ophthalmologists is over 78%, indicating a high correlation between the AI-based saliency maps and expert-annotated lesion regions. Our findings show that XAI can not only maintain diagnostic accuracy but also enhance model interpretability, rendering AI-based DR screening systems more acceptable and usable in clinical practice. This study reinforces the importance of explainability as an integral part of implementing medical AI.

مراجع

[1]       Alavee, K. A., et al. Enhancing early detection of diabetic retinopathy through the integration of deep learning models and explainable artificial intelligence. IEEE Access, 2024. 12, 73950–73969. DOI: 10.1109/ACCESS.2024.3405570

[2]       Nandhini, S., Sowbarnikkaa, S., Mageshwari, J., & Saraswathy, C. An automated detection and multi-stage classification of diabetic retinopathy using convolutional neural networks. ViTECoN 2023 - 2nd IEEE International Conference on Vision Towards Emerging Trends in Communication and Networking Technologies, 2023. DOI: 10.1109/ViTECoN58111.2023.10157960

[3]       Mantaqa, M. N., Anjom, J., & Hossain, M. I. A. Diabetic retinopathy detection using a lightweight edge intelligence-based technique. BECITHCON 2024 - IEEE International Conference on Biomedical Engineering, Computer and Information Technology for Health, 2024. 113–118. DOI: 10.1109/BECITHCON64160.2024.10962647

[4]       Reddy, K. S., & Narayanan, M. An efficiency way to analyze diabetic retinopathy detection and classification using deep learning techniques. ICACITE 2023 - 3rd International Conference on Advance Computing and Innovative Technologies in Engineering, 2023. 1388–1392. DOI: 10.1109/ICACITE57410.2023.10182642

[5]       Herrero-Tudela, M., et al. An explainable deep-learning model reveals clinical clues in diabetic retinopathy through SHAP. Biomedical Signal Processing and Control, 2025. 102, 107328. DOI: 10.1016/j.bspc.2024.107328

[6]       Abushawish, I. Y., et al. Deep learning in automatic diabetic retinopathy detection and grading systems: A comprehensive survey and comparison of methods. IEEE Access, 2024. 12, 84785–84802. DOI: 10.1109/ACCESS.2024.3415617

[7]       Mehmood, Q., et al. Hybrid deep learning model for diabetic retinopathy severity detection and classification. Journal of Saidu Medical College, 2025. 15(2), 218–225. DOI: 10.52206/jsmc.2025.15.2.1149

[8]       Abdullah, A., et al. A literature analysis for the prediction of chronic kidney diseases. Journal of Computing & Biomedical Informatics, 2024. 7(02).

[9]       Islam, M. M., et al. Explainable machine learning for efficient diabetes prediction using hyperparameter tuning, SHAP analysis, partial dependency, and LIME. Engineering Reports, 2024. 7(1), e13080. DOI: 10.1002/eng2.13080

[10]     Hao, S., et al. Clinical evaluation of AI-assisted screening for diabetic retinopathy in rural areas of midwest China. PLOS ONE, 2022. 17(10), e0275983. DOI: 10.1371/journal.pone.0275983

[11]     Sushith, M., et al. A hybrid deep learning framework for early detection of diabetic retinopathy using retinal fundus images. Scientific Reports, 2025. 15, 15166. DOI: 10.1038/s41598-025-99309-w

[12]     Bidwai, P., et al. A systematic literature review on diabetic retinopathy using an artificial intelligence approach. Big Data and Cognitive Computing, 2022. 6(4), 152. DOI: 10.3390/bdcc6040152

[13]     Abini, M. A., & Priya, S. S. S. Detection and classification of diabetic retinopathy using pretrained deep neural networks. ICIET 2023 - International Conference on Innovations in Engineering and Technology, 2023. DOI: 10.1109/ICIET57285.2023.10220715

[14]     Khalid, N., & Deriche, M. Combining CNNs for the detection of diabetic retinopathy. ACIT 2023 - 24th International Arab Conference on Information Technology, 2023. DOI: 10.1109/ACIT58888.2023.10453830

[15]     Atwany, M. Z., Sahyoun, A. H., & Yaqub, M. Deep learning techniques for diabetic retinopathy classification: A survey. IEEE Access, 2022. 10, 28642–28655. DOI: 10.1109/ACCESS.2022.3157632

[16]     ]Shahzad, T., et al. Developing a transparent diagnosis model for diabetic retinopathy using explainable AI. IEEE Access, 2024. DOI: 10.1109/ACCESS.2024.3475550

[17]     Jagadesh, B. N., et al. Segmentation using the IC2T model and classification of diabetic retinopathy using the Rock Hyrax Swarm-based coordination attention mechanism. IEEE Access, 2023. 11, 124441–124458. DOI: 10.1109/ACCESS.2023.3330436

[18]     Shahzad, T., et al. Developing a transparent diagnosis model for diabetic retinopathy using explainable AI. IEEE Access, 2024. DOI: 10.1109/ACCESS.2024.3475550 (duplicate of #16)

[19]     Ali, S., et al. Visualizing research on explainable artificial intelligence for medical and healthcare. iCoMET 2023 - 4th International Conference on Computing, Mathematics and Engineering Technologies, 2023. DOI: 10.1109/iCoMET57998.2023.10099343

[20]     Qiao, L., Zhu, Y., & Zhou, H. Diabetic retinopathy detection using prognosis of microaneurysm and early diagnosis system for non-proliferative diabetic retinopathy based on deep learning algorithms. IEEE Access, 2020. 8, 104292–104302. DOI: 10.1109/ACCESS.2020.2993937

[21]     Rajarajeshwari, G., & Chemmalar Selvi, G. Application of artificial intelligence for classification, segmentation, early detection, early diagnosis, and grading of diabetic retinopathy from fundus retinal images: A comprehensive review. IEEE Access, 2024. DOI: 10.1109/ACCESS.2024.3494840

[22]     Zedadra, A., et al. Graph-aware multimodal deep learning for classification of diabetic retinopathy images. IEEE Access, 2025. DOI: 10.1109/ACCESS.2025.3564529

[23      Sovit Ranjan Rath. Diabetic retinopathy 224x224 Gaussian filtered dataset. Kaggle, 2023. Available: https://www.kaggle.com/datasets/sovitrath/diabetic-retinopathy-224x224-gaussian-filtered