SE-Fundusnet: A Channel Attention-Based Deep ‎Learning Architecture for Papilledema Detection and ‎Classification

  • Authors

    • Rajalingam Arumuganainar Department of Engineering and Technology,‎ University of Technology and Applied ‎Sciences, ‎ Shinas, Sultanate of Oman
    • Navaprakash. N Department of Electronics and Communication Engineering,‎ Saveetha School of Engineering, Saveetha Institute of Medical and Technical Sciences,‎ Saveetha University, Chennai, Tamil Nadu, India
    • G. Charulatha Department of Electronics and Communication Engineering,‎ Saveetha School of Engineering, Saveetha Institute of Medical and Technical Sciences,‎ Saveetha University, Chennai, Tamil Nadu, India
    • V. Suresh Kumar Department of Electronics and Communication Engineering,‎ Saveetha School of Engineering, Saveetha Institute of Medical and Technical Sciences,‎ Saveetha University, Chennai, Tamil Nadu, India
    • K. Sathish Department of Electronics and Communication Engineering,‎ Saveetha School of Engineering, Saveetha Institute of Medical and Technical Sciences,‎ Saveetha University, Chennai, Tamil Nadu, India
    • M. Ramkumar Prabhu Department of Electronics and Communication Engineering,‎ Saveetha School of Engineering, Saveetha Institute of Medical and Technical Sciences,‎ Saveetha University, Chennai, Tamil Nadu, India
    https://doi.org/10.14419/kgcxv072

    Received date: July 31, 2025

    Accepted date: September 1, 2025

    Published date: October 19, 2025

  • Papilledema Detection; Fundus Imaging; Deep Learning; Channel Attention; Convolutional Neural Networks; ‎Medical Imaging

  • Abstract

    Papilledema is characterized by enlargement of the optic disc resulting from increased intracranial ‎pressure, and represents a critical clinical finding that demands immediate medical attention. A new deep ‎learning method for automatically identifying papilledema from fundus images is presented in this work. ‎A Hybrid Centric convolutional neural network (HCCNN) architecture is introduced that incorporates ‎squeeze-and-excite (SE) channel attention mechanisms and parallel feature extraction to effectively ‎capture diagnostically relevant features. The model employs different kernel sizes across parallel ‎processing pathways to simultaneously extract fine-grained details and broader contextual features. ‎Experimental results demonstrate excellent performance, with an overall accuracy of 96.98%, sensitivity ‎of 95.48% and specificity of 97.74%. Ablation studies confirm the effectiveness of the SE blocks, which ‎improve detection accuracy by 4.3%, particularly for subtle presentations. This work represents a ‎significant step toward developing reliable computer-aided diagnostic tools for papilledema, potentially ‎enhancing early detection and monitoring of this vision-threatening condition‎.

  • References

    1. J.S. Xie, L. Donaldson, E. Margolin, Papilledema: a review of etiology, pathophysiology, diagnosis, and management, Surv. Ophthalmol. 67 (2022) 1135–1159. https://doi.org/10.1016/j.survophthal.2021.11.007.
    2. Reier, L., Fowler, J.B., Arshad, M., Hadi, H., Whitney, E., Farmah, A.V. and Siddiqi, J., 2022. Optic disc edema and elevated intracranial pressure (ICP): a comprehensive review of papilledema. Cureus, 14(5). https://doi.org/10.7759/cureus.24915.
    3. Kwok, J.M., Mandell, D.M. and Margolin, E.A., 2021. Papilledema in a patient with intracranial hypotension. Journal of Neuro-Ophthalmology, 41(4), pp. e708-e710. https://doi.org/10.1097/WNO.0000000000001112.
    4. Rambabu, L., Edmiston, T., Smith, B.G., Kohler, K., Kolias, A.G., Bethelehem, R.A., Keane, P.A., Marcus, H.J., Hutchinson, P.J. and Bashford, T., 2025. Detecting papilloedema as a marker of raised intracranial pressure using artificial intelligence: a systematic review. medRxiv, pp.2025-02. https://doi.org/10.1101/2025.02.14.25322289.
    5. Sathish, K., 2025, February. Investigation of Impedance Tube-based Parameter Estimation Techniques with Data Generation for Underwater Acous-tic Applications. In 2025 International Conference on Electronics and Renewable Systems (ICEARS) (pp. 154-159). IEEE. https://doi.org/10.1109/ICEARS64219.2025.10940315.
    6. Prabhu, M., Sathishkumar, A., Sasi, G., ... Lau Chee Yong, Shanker, M.C., Selvakumarasamy K, “Monkeypox Detection using CSA based K-Means Clustering with Swin Transformer Model”, Journal of Machine and Computing, 4(2), pp. 400–407 (2024). https://doi.org/10.53759/7669/jmc202404038.
    7. Latha, G., Priya, P.A. & Smitha, V.K. Enhanced diabetic retinopathy detection and exudates segmentation using deep learning: A promising approach for early disease diagnosis. Multimedia Tools and Applications 83, 77785–77808 (2024). https://doi.org/10.1007/s11042-024-18629-7.
    8. Üzen, H., Turkoglu, M., Aslan, M. and Hanbay, D., 2023. Depth-wise Squeeze and Excitation Block-based Efficient-Unet model for surface defect detection. The Visual Computer, 39(5), pp.1745-1764. https://doi.org/10.1007/s00371-022-02442-0.
    9. Kokulu, M. and Göker, H., 2023. Detection of papilledema severity from color fundus images using transfer learning approaches. https://doi.org/10.29002/asujse.1280766.
    10. Avramidis, K., Rostami, M., Chang, M. Y., & Narayanan, S. S. (2022). Automating Detection of Papilledema in Pediatric Fundus Images with Ex-plainable Machine Learning. International Conference on Information Photonics, 3973–3977. https://doi.org/10.1109/ICIP46576.2022.9897529.
    11. Saba, T., Akbar, S., Kolivand, H., Kolivand, H., & Bahaj, S. A. (2021). Automatic detection of papilledema through fundus retinal images using deep learning. Microscopy Research and Technique, 84(12), 3066–3077. https://doi.org/10.1002/jemt.23865.
    12. Akbar, S., Akram, M. U., Sharif, M., Tariq, A., & Yasin, U. U. (2017). Decision Support System for Detection of Papilledema through Fundus Ret-inal Images. Journal of Medical Systems, 41(4), 1–16. https://doi.org/10.1007/s10916-017-0712-9.
    13. Salaheldin, A. M., Abdel Wahed, M., Talaat, M., & Saleh, N. (n.d.). An evaluation of AI-based methods for papilledema detection in retinal fun-dus images. Biomedical Signal Processing and Control. https://doi.org/10.1016/j.bspc.2024.106120.
    14. Wiharto, A.E.P.S., Squeeze-excitation half U-Net and synthetic minority oversampling technique oversampling for papilledema image classifica-tion. Int J Artif Intell ISSN, 2252(8938), p.1411.
    15. Fatima, K.N., Hassan, T., Akram, M.U., Akhtar, M. and Butt, W.H., 2017. Fully automated diagnosis of papilledema through robust extraction of vascular patterns and ocular pathology from fundus photographs. Biomedical optics express, 8(2), pp.1005-1024. https://doi.org/10.1364/BOE.8.001005.
    16. Kapileswar, N., 2025, June. Federated Deep Learning-Driven Cloud-IoT Framework for Real-Time Healthcare Monitoring and Privacy-Preserving Anomaly Detection. In 2025 3rd International Conference on Self Sustainable Artificial Intelligence Systems (ICSSAS) (pp. 1866-1871). IEEE. https://doi.org/10.1109/ICSSAS66150.2025.11080854.
    17. Kim, U. (2018, August 1). Machine learning for Pseudopapilledema.
    18. Huda, S., Liu, K., Abdelrazek, M., Ibrahim, A., Alyahya, S., Al-Dossari, H. and Ahmad, S., 2018. An ensemble oversampling model for class im-balance problem in software defect prediction. IEEE access, 6, pp.24184-24195. https://doi.org/10.1109/ACCESS.2018.2817572.
    19. Maniraj, S.P., Rose, J.D., Arunachalam, R., K Rangasamy,, Vishal P P & Selvakumarasamy K, “Polar Region Climate Dynamics: Deep Learning and Remote Sensing Integration for Monitoring Arctic and Antarctic Changes. Remote Sens Earth Syst Sci 7, 582–595 (2024). https://doi.org/10.1007/s41976-024-00147-7.
    20. N. Kapileswar et al, "DeepCurrent: An Attention-Driven Graph Neural Network for Energy-Efficient Routing and Data Aggregation in UIoT Networks," 2025 International Conference on Modern Sustainable Systems (CMSS), Shah Alam, Malaysia, 2025, pp. 716-720, doi: 10.1109/CMSS66566.2025.11182394.
    21. Wang, K., Jiang, P., Meng, J. and Jiang, X., 2022. Attention-based DenseNet for pneumonia classification. Irbm, 43(5), pp.479-485. https://doi.org/10.1016/j.irbm.2021.12.004.
    22. Kumar, R.L., Kakarla, J., Isunuri, B.V. and Singh, M., 2021. Multi-class brain tumor classification using residual network and global average pool-ing. Multimedia Tools and Applications, 80(9), pp.13429-13438. https://doi.org/10.1007/s11042-020-10335-4.
    23. Chopade, P.B., Kota, P.N., Jadhav, B.D., Ghate, P.M. and Kulkarni, S.S., 2025. Retinopathy Disease Detection and Classification Using a Coordi-nate Attention Module-Based Convolutional Neural Network with Leaky Rectified Linear Unit. IIUM Engineering Journal, 26(1), pp.129-147. https://doi.org/10.31436/iiumej.v26i1.3194.
    24. J. Simon et al, "Dual-Branch GAN-Driven Super-Resolution for Low-Dose CT Image Enhancement under Radiological Noise Constraints," 2025 International Conference on Modern Sustainable Systems (CMSS), Shah Alam, Malaysia, 2025, pp. 710-715, doi: 10.1109/CMSS66566.2025.11182514
    25. Malla, P.P., Sahu, S. and Alutaibi, A.I., 2023. Classification of tumor in brain MR images using deep convolutional neural network and global aver-age pooling. Processes, 11(3), p.679. https://doi.org/10.3390/pr11030679.
    26. D. Sheela, N. P. G. Bhavani, C. Prameeladevi and Ch. Sarada Devi, "Linear Tapered Wavelength Division Multiplexing (WDM) Phasor Array to Improve Coupling Efficiency," Proc. of 6th Int. Conf. on 2025 Devices for Integrated Circuit Devices, pp. 203–208, 2025. https://doi.org/10.1109/DevIC63749.2025.11012459.
    27. Szanto, D., Erekat, A., Woods, B., Wang, J.K., Garvin, M., Johnson, B.A., Kardon, R., Linton, E. and Kupersmith, M.J., 2025. Deep Learning Ap-proach Readily Differentiates Papilledema, NAION, and Healthy Eyes. American Journal of Ophthalmology. https://doi.org/10.1016/j.ajo.2025.05.036.

  • Downloads

  • How to Cite

    Arumuganainar , R. ., N, N., Charulatha , G. ., Kumar , V. S. ., Sathish , K. ., & Prabhu , M. R. . (2025). SE-Fundusnet: A Channel Attention-Based Deep ‎Learning Architecture for Papilledema Detection and ‎Classification. International Journal of Basic and Applied Sciences, 14(6), 425-434. https://doi.org/10.14419/kgcxv072