A Novel Topological Vector Space Framework for Early Diagnosis of Diabetic Retinopathy

Gyan Prasad  Paudel; Keshar Singh Rana

doi:10.48001/veethika.1004006

Authors

Gyan Prasad Paudel Graduate School of Science and Technology, Mid-Western University, Surkhet, Nepal https://orcid.org/0009-0007-9195-7703
Keshar Singh Rana Graduate School of Science and Technology, Mid-Western University, Surkhet, Nepal

DOI:

https://doi.org/10.48001/veethika.1004006

Keywords:

Diabetic Retinopathy (DR), Topological Vector Space Refined Generative Adversarial Networks (TVSRGAN), Fundus imaging, Early Diagnosis

Abstract

Diabetic retinopathy (DR) is a serious implications for diabetes mellitus issues that leaves a slow, progressive debilitation on the optical blood vessels, with the result of sight impairment and probably blindness. However, with early identification and appropriate treatment, severe visual impairment can be reduced. It developed automated techniques for DR detection using fundus imaging techniques. The present study proposes a new Topological Vector Space-refined Generative Adversarial Networks (TVSRGAN) model for retinal image-based early DR identification. Topological vector spaces (TVS) can function as the structural characteristics and be used in accommodating with other frameworks that have been determined. Its analysis data and processing where uncertainty and ambiguity have long existed. The dataset for DR detection was commonly collected from publicly accessible sources. DR is finally classified using TVSRGAN classifiers, which successfully manage the uncertainties included in medical statistics. The findings demonstrate that The accuracy (98.53\%) for the suggested model's outcome is assessed (98.53\%), precision (97.88\%), sensitivity (98.96\%) and specificity (98.88\%). A reliable and accurate solution for the purpose of initial identification and detection increases diagnostic precision and effectiveness over conventional models.

Downloads

Download data is not yet available.

References

Bilal, A., Zhu, L., Deng, A., Lu, H., & Wu, N. (2022). AI-based automatic detection and classification of diabetic retinopathy using U-Net and deep learning. Symmetry, 14(7), 1427. https://doi.org/10.3390/sym14071427 DOI: https://doi.org/10.3390/sym14071427

Kaggle. (n.d.). Diabetic retinopathy 224x224 Gaussian filtered data [Dataset]. Available at https://www.kaggle.com/datasets/sovitrath/diabetic-retinopathy-224x224-gaussian-filtered/data

Kropp, M., Golubnitschaja, O., Mazurakova, A., Koklesova, L., Sargheini, N., Vo, T., de Clerck, E., Polivka Jr, J., Potuznik, P., Polivka, J., & Stetkarova, I. (2023). Diabetic retinopathy as the leading cause of blindness and early predictor of cascading complications: Risks and mitigation. EPMA Journal, 14(1), 21–42. https://doi.org/10.1007/s13167-023-00314-8 DOI: https://doi.org/10.1007/s13167-023-00314-8

Lipi?ski, M. (2021). Morse-Conley-Forman theory for generalized combinatorial multivector fields on finite topological spaces [Doctoral dissertation]. https://doi.org/10.1007/s41468-022-00102-9 DOI: https://doi.org/10.1007/s41468-022-00102-9

Mohammedhasan, M., & U?uz, H. (2020). A new early-stage diabetic retinopathy diagnosis model using deep convolutional neural networks and principal component analysis. Traitement du Signal, 37(5). https://doi.org/10.18280/ts.370503 DOI: https://doi.org/10.18280/ts.370503

Nguyen, P. T., Huynh, V. B., Vo, K. D., Phan, P. T., Yang, E., & Joshi, G. P. (2021). An optimal deep learning-based computer-aided diagnosis system for diabetic retinopathy. Computers, Materials & Continua, 66(3), 2815–2830. https://doi.org/10.32604/cmc.2021.012315 DOI: https://doi.org/10.32604/cmc.2021.012315

Porwal, P., Pachade, S., Kokare, M., Deshmukh, G., Son, J., Bae, W., Liu, L., Wang, J., Liu, X., Gao, L., & Wu, T. (2020). IDRiD: Diabetic retinopathy–segmentation and grading challenge. Medical Image Analysis, 59, 101561. https://doi.org/10.1016/j.media.2020.101561 DOI: https://doi.org/10.1016/j.media.2019.101561

Sarki, R. (2021). Automatic detection of diabetic eye disease through deep learning using fundus images [Doctoral dissertation]. Victoria University. https://doi.org/10.1109/ACCESS.2020.3015258 DOI: https://doi.org/10.1109/ACCESS.2020.3015258

Sharafeldeen, A., Elsharkawy, M., Khalifa, F., Soliman, A., Ghazal, M., AlHalabi, M., Yaghi, M., Al-Rahmawy, M., Elmougy, S., Sandhu, H., & El-Baz, A. (2021). Precise higher-order reflectivity and morphology models for early diagnosis of diabetic retinopathy using OCT images. Scientific Reports, 11(1), 4730. https://doi.org/10.1038/s41598-021-83735-7 DOI: https://doi.org/10.1038/s41598-021-83735-7

Sundar, S., & Sumathy, S. (2023). Classification of diabetic retinopathy disease levels by extracting topological features using graph neural networks. IEEE Access, 11, 51435–51444. https://doi.org/10.1109/ACCESS.2023.3279393 DOI: https://doi.org/10.1109/ACCESS.2023.3279393

Thanikachalam, V., Kabilan, K., & Erramchetty, S. (2024). Optimized deep CNN for detection and classification of diabetic retinopathy and diabetic macular edema. BMC Medical Imaging, 24(1), 227. https://doi.org/10.1186/s12880-024-01406-1 DOI: https://doi.org/10.1186/s12880-024-01406-1

Vujosevic, S., Aldington, S., Silva, P., Hernández, C., Scanlon, P., Peto, T., & Simó, R. (2020). Screening for diabetic retinopathy: New perspectives and challenges. The Lancet Diabetes Endocrinology, 8(4), 337–347. https://doi.org/10.1016/S2213-8587(19)30411-5 DOI: https://doi.org/10.1016/S2213-8587(19)30411-5

Zhang, Z., Deng, C., & Paulus, Y. (2024). Advances in structural and functional retinal imaging and biomarkers for early detection of diabetic retinopathy. Biomedicines, 12(7), 1405. https://doi.org/10.3390/biomedicines12071405 DOI: https://doi.org/10.3390/biomedicines12071405