Neuro-Spectral Causal Fusion Network with Lesion Dependency Reasoning for Explainable Diabetic Retinopathy Detection
Abstract
Background: Diabetic Retinopathy (DR) is a progressive microvascular complication of diabetes and a leading cause of preventable vision impairment worldwide. Early and accurate identification of DR severity is essential for timely intervention and effective disease management. However, conventional retinal screening relies heavily on manual examination of fundus images, which is labor-intensive, subjective, and dependent on specialist expertise. Although recent deep-learning models have demonstrated promising diagnostic performance, many existing approaches inadequately capture lesion-level relationships, underutilize clinical information, and provide limited interpretability for clinical decision-making.
Aims: this study proposes a novel Neuro-Spectral Causal Fusion Network (NSCF-Net) for explainable diabetic retinopathy detection and severity grading.
Methods: The proposed framework integrates an adaptive Neuro-Spectral Enhancement Module to improve lesion visibility, a Lesion Dependency Reasoning Graph to model pathological interactions among retinal abnormalities, and a Dual-Path Hybrid Transformer to jointly learn local lesion characteristics and global retinal context. Furthermore, a Causal Multimodal Fusion Unit combines retinal image representations with clinically relevant parameters, including HbA1c level, blood pressure, age, and duration of diabetes. To improve transparency and clinical trustworthiness, an Explainable Lesion Attribution Module generates counterfactual attention maps and hierarchical saliency visualizations highlighting diagnostically significant retinal regions. The proposed framework was evaluated on the APTOS 2019 diabetic retinopathy dataset, consisting of 3,662 retinal fundus images distributed across five DR severity classes.
Results: Experimental results demonstrate the effectiveness of NSCF-Net, achieving 99.1% accuracy, 98.9% precision, 99.0% recall, and 98.8% F1-score. Comparative analyses and ablation studies further confirm the contribution of neuro-spectral enhancement, lesion dependency reasoning, multimodal fusion, and explainability components to overall performance improvement.
Conclusion: These findings indicate that NSCF-Net provides an accurate, interpretable, and clinically reliable framework for automated diabetic retinopathy screening, severity assessment, and computer-aided ophthalmic decision support.
Downloads
References
Deepa V, Sathish Kumar C, Cherian T, “Automated grading of diabetic retinopathy using CNN with hierarchical clustering of image patches by siamese network”, Phys Eng Sci Med, vol. 45(2), pp. 623–635, 2022, DOI:10.1007/s13246-022-01129-z
Irodi, A., Zhu, Z., Grzybowski, A., Wu, Y., Cheung, C. Y., Li, H., & Wong, T. Y. “The evolution of diabetic retinopathy screening”, Eye, vol.39(6), pp.1040-1046, 2025. DOI:10.1038/s41433-025-03633-4
Khan, Z., Gaidhane, A. M., Singh, M., Ganesan, S., Kaur, M., Sharma, G. C., ... & Samal, S. K. “Diagnostic accuracy of IDX-DR for detecting diabetic retinopathy: a systematic review and meta-analysis”, American journal of ophthalmology, Vol.273, pp. 192-204, 2025, DOI:10.1016/j.ajo.2025.02.022
Sivaprasad, S., Vujosevic, S. “Advances in diagnosing and treating diabetic retinopathy” Nat Rev Endocrinol vol. 22, pp. 477–489 ,2026, DOI:10.1038/s41574-026-01257-6
Vujosevic, S., Aldington, S. J., Silva, P., Hernández, C., Scanlon, P., Peto, T., & Simó, R., “Screening for diabetic retinopathy: new perspectives and challenges”, The Lancet Diabetes & Endocrinology, vol.8(4), pp.337-347, 2020, DOI:10.1016/S2213-8587(19)30411-5
Pushparani, D. S., Varalakshmi, J., Roobini, K., Hamshapriya, P., & Livitha, A., “Diabetic retinopathy-a review”, Current Diabetes Reviews, vol.21(7), Art. No.E310524230559. DOI:10.2174/0115733998296228240521151050
Dataset collection: https://www.kaggle.com/datasets/sovitrath/diabetic-retinopathy-224x224-2019-data?select=colored_images
Leontidis, G., Al-Diri, B., & Hunter, A., “A new unified framework for the early detection of the progression to diabetic retinopathy from fundus images”, Computers in biology and medicine, vol. 90, pp. 98-115, 2017, DOI:10.1016/j.compbiomed.2017.09.008
Qureshi, I., Ma, J., & Shaheed, K., “A hybrid proposed fundus image enhancement framework for diabetic retinopathy”, Algorithms, vol.12(1), 2019, DOI:/10.3390/a12010014
Alshayeji, M. H., Abed, S. E., & Sindhu, S. C., “Two-stage framework for diabetic retinopathy diagnosis and disease stage screening with ensemble learning”, Expert Systems with Applications, vol.225, Art. No.120206, 2023, DOI:10.1016/j.eswa.2023.120206
Romero-Oraá, R., Herrero-Tudela, M., López, M. I., Hornero, R., & García, M., “Attention-based deep learning framework for automatic fundus image processing to aid in diabetic retinopathy grading”, Computer Methods and Programs in Biomedicine, vol. 249, Art. No. 108160, 2024, DOI:10.1016/j.cmpb.2024.108160
Sushith, M., Sathiya, A., Kalaipoonguzhali, V., & Sathya, V., “A hybrid deep learning framework for early detection of diabetic retinopathy using retinal fundus images”, Scientific Reports, vol. 15(1), Art. No.15166, 2025, DOI:10.1038/s41598-025-99309-w
Hacisoftaoglu, R. E., Karakaya, M., & Sallam, A. B. “Deep learning frameworks for diabetic retinopathy detection with smartphone-based retinal imaging systems:, Pattern recognition letters, vol. 135, pp. 409-417, 2020, DOI:10.1016/j.patrec.2020.04.009
Kaushik, H., Singh, D., Kaur, M., Alshazly, H., Zaguia, A., & Hamam, H., “Diabetic retinopathy diagnosis from fundus images using stacked generalization of deep models”, IEEE Access, vol.9, 2021, pp. 108276-108292, 2021, DOI:10.1109/ACCESS.2021.3101142
Kahai, P., Namuduri, K. R., & Thompson, H., “A decision support framework for automated screening of diabetic retinopathy”, International journal of biomedical imaging, vol. 2006(1), Art. No. 045806, 2006, DOI:/10.1155/IJBI/2006/45806
Ainapur, S. S., “Automated diabetic retinopathy detection using a multi-step framework with stacked ensemble-based classification model”, Expert Systems with Applications, vol.284, Art. No.127709, 2025, DOI:10.1016/j.eswa.2025.127709
Rafid, A. U. I., Sanjana, S., Munir, M. B., & Sharmin, N., “An early-stage diagnosis of diabetic retinopathy based on ensemble framework”, Signal, Image and Video Processing, vol. 18(1), pp. 735-749, 2024, DOI:10.1007/s11760-023-02796-5
Lavanya, K., Thangamani, M., Ganthimathi, M., Priyanka, S., Peter, V. J., & Sapthika, J., “A Multi-Class Deep Neural Network Framework Driven Automated Classification of Diabetic Retinopathy Using Retinal Fundus Images”, Genetics and Molecular Research, vol. 25(1), 2026, DOI:10.4238/4j99yb84
Rakhlin, A., “Diabetic retinopathy detection through integration of deep learning classification framework”, BioRxiv, Art. No. 225508, 2017, DOI:10.1101/225508
Murugappan, M., Prakash, N. B., Jeya, R., Mohanarathinam, A., Hemalakshmi, G. R., & Mahmud, M, “A novel few-shot classification framework for diabetic retinopathy detection and grading”, Measurement, vol.200, Art. No.111485, 2022, DOI: 10.1016/j.measurement.2022.111485
Costa, P., Galdran, A., Smailagic, A., & Campilho, A. “A weakly-supervised framework for interpretable diabetic retinopathy detection on retinal images”, IEEE access, vol. 6, pp.18747-18758, 2018, DOI:10.1109/ACCESS.2018.2816003
Alshahrani, M., Al-Jabbar, M., Senan, E. M., Ahmed, I. A., & Saif, J. A. M., “Hybrid methods for fundus image analysis for diagnosis of diabetic retinopathy development stages based on fusion features”, Diagnostics, vol. 13(17), pp. 2783. DOI:10.3390/diagnostics13172783
Suganyadevi S., Seethalakshmi V. “FACNN: fuzzy-based adaptive convolution neural network for classifying COVID-19 in noisy CXR images”, Med Biol Eng Comput, vol. 62, pp. 2893–2909, 2024, DOI:10.1007/s11517-024-03107-x
G. Pradeep, S. Bala, N. P. Satheesh, M. Mahalakshmi, K. Balasamy and S. Suganyadevi, "An Effective Framework for Detecting Epileptic Seizures using CNN and Encrypted EEG Signals", International Conference on Sustainable Computing and Smart Systems (ICSCSS), Coimbatore, India, pp. 611-617, 2023, DOI:10.1109/ICSCSS57650.2023.10169196
S. Suganyadevi, K. Renukadevi, K. Balasamy and P. Jeevitha, "Diabetic Retinopathy Detection Using Deep Learning Methods," First International Conference on Electrical, Electronics, Information and Communication Technologies (ICEEICT), Trichy, India, pp. 1-6, 2022, DOI:10.1109/ICEEICT53079.2022.9768544.
L. Sowmiya, A. S. Rajasekaran, S. Suganyadevi, S. Sureshkumar, G. Subramaniam and R. Jaazieliah, "A Secure Authenticated Message Transfer in Healthcare Application," 2023 IEEE International Conference on Integrated Circuits and Communication Systems (ICICACS), Raichur, India, pp. 1-6, 2023, DOI:10.1109/ICICACS57338.2023.10099494.
Usha, S., Bala, S., Saranya, M.D. et al. “Pixelated disparity network for hepatocellular carcinoma recognition from ultrasound images”, Evolving Systems vol.16, no.113, 2025, DOI:10.1007/s12530-025-09737-2.
Dayana AM, Emmanuel WRS, “An enhanced swarm optimization-based deep neural network for diabetic retinopathy classification in fundus images”, MultimedTools Appl, vol. 81, pp.20611–20642, 2022, DOI:10.1007/s11042-022-12492-0
Luo X, Xu Q, Wang Z, Huang C, Liu C, Jin X, Zhang J. “A Lesion-Fusion Neural Network for Multi-View Diabetic Retinopathy Grading”, IEEE J Biomed Health Inform, Vol. 29(5), pp. 3184-3193, 2025, DOI:10.1109/JBHI.2024.3384251.
S. Suganyadevi, V. Pavatharani, K. Koushick, R. Manimaran, A. Mohammed Sameer and K. Murugan, "Multisalient Object Detection and Recognition using Deep Learning Techniques," International Conference on Applied Intelligence and Sustainable Computing (ICAISC), Dharwad, India, pp. 1-7, 2023, DOI:10.1109/ICAISC58445.2023.10200299.
Correra, Simona, Valeria Sorgente, Mario Cesarelli, Fabio Martinelli, Antonella Santone, and Francesco Mercaldo, "A Novel Convolutional Neural Network for Explainable Diabetic Retinopathy Detection and Grade Identification" Sensors, vol. 26, no. 8, pp.2510, 2026, DOI:10.3390/s26082510.
S. Suganyadevi, K. R. Sasiprabha, V. Vethavarna and A. S. Rajasekaran, "Multi-Scale Guided Pyramid Transformer with Uncertainty-Aware Deep Refinement for High-Precision Lung Segmentation and Multi-Class Disease Classification," Seventh International Conference on Research in Computational Intelligence and Communication Networks (ICRCICN), Kalyani, India, pp. 675-680, 2025, DOI:10.1109/ICRCICN68210.2025.11364701.
Rahaman, M., Muni, M.A., Tasnim, S. et al. “Explainable AI for diabetic retinopathy detection using vision transformers”, Sci Rep vol.16, Art. No. 27354, 2026, DOI:10.1038/s41598-026-56569-4.
Suganyadevi, S., Seethalakshmi, V. & Balasamy, K. “A review on deep learning in medical image analysis. Int J Multimed Info Retr, vol. 11, pp.19–38, 2022, DOI:10.1007/s13735-021-00218-1
Alanazi, Saad, and Rayan Alanazi. "Enhancing diabetic retinopathy detection through federated convolutional neural networks: Exploring different stages of progression." Alexandria Engineering Journal, vol. 120 pp.215-228, 2025, DOI:10.1016/j.aej.2025.02.026.
Suganyadevi, S., Seethalakshmi, V. CVD-HNet: Classifying Pneumonia and COVID-19 in Chest X-ray Images Using Deep Network. Wireless Pers Commun 126, 3279–3303 (2022). https://doi.org/10.1007/s11277-022-09864-y
Niu Y, Gu L, Zhao Y, Lu F. “Explainable Diabetic Retinopathy Detection and Retinal Image Generation” IEEE J Biomed Health Inform, vol. 26(1), pp. 44-55. https://doi.org/ 10.1109/JBHI.2021.3110593.
Yurdakul, M., Uyar, K., Taşdemír, Ş. & Atabaş, Í. Ropgcvit, “A novel explainable vision transformer for retinopathy of prematurity diagnosis”, IEEE Access, vol. 13, pp. 77064–77079, 2025, DOI:10.1109/ACCESS.2025.3564213.
Lalithadevi, B., Krishnaveni, S. “Diabetic retinopathy detection and severity classification using optimized deep learning with explainable AI technique” Multimed Tools Appl vol. 83, pp. 89949–90013, 2024, DOI:10.1007/s11042-024-18863-z
Tashkandi, Araek. "Eye Care: Predicting Eye Diseases Using Deep Learning Based on Retinal Images", Computation, vol. 13, no. 4: pp,91, 2025, DOI:10.3390/computation13040091.
Copyright (c) 2026 K. Venu, B. Thanga Parvathi, Kunchanapalli Rama Krishna, Yuvaraj S.
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution-ShareAlikel 4.0 International (CC BY-SA 4.0) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
.png)
.png)
.png)
.png)
.png)
