Retinal Disease Classification Using Deep Learning and Nanotechnology with a Multi-class CNN Approach and Explainable AI
J. Environ. Nanotechnol., Volume 15, No 2 (June 2026) pp. 98-109
Abstract
Retinal diseases such as myopia, choroidal neovascularization, and tessellated retina are significant causes of vision impairment, making early and accurate diagnosis essential for effective clinical intervention. This work proposes a multi-class retinal disease classification framework that integrates deep learning with nanotechnology-inspired principles to achieve high diagnostic precision and interpretability. A Convolutional Neural Network (CNN) is constructed to emulate key nanotechnology concepts, including nanoscale sensitivity, pixel-level precision, and multi-scale feature perception, enabling the detection of subtle retinal structural variations that are often difficult to identify through conventional image analysis. Fundus images are classified using an optimized CNN architecture capable of extracting fine-grained micro- and nano-level visual features. To enhance clinical transparency, Explainable Artificial Intelligence (XAI) techniques, specifically LIME (Local Interpretable Model-agnostic Explanations), are incorporated to provide visual explanations highlighting diagnostically relevant retinal regions influencing model predictions. Experimental results demonstrate strong performance, achieving a classification accuracy of 94.92% with a low test loss of 0.0836, while the explainability analysis confirms alignment with clinically meaningful features. The study is limited by a small dataset size and minor class imbalance, comprising 393 fundus images for broader clinical generalization. By conceptually bridging nanotechnology and deep learning for retinal image analysis, this study establishes a scalable and interpretable framework for automated retinal disease classification, contributing to precision ophthalmology and next-generation AI-assisted diagnostic systems. A key novelty of this study is the integration of nanotechnology with CNN architecture to improve retinal fundus image detection performance.
Full Text
Reference
Ancysophia, Thomas, M., Esakkiammal, S., Jayanthi, N., Kamalarajan, P. and Yamini, G., Nanotechnology in Biomedical Image Processing Using En- semble Deep Learning Approach, 2024 2nd IEEE Int. Conf. Adv. Inform. Commun., Computer, IOT Technol., 1, 220-225(2024).
https://doi.org/10.1109/ICAICCIT64383.2024.10912299
Anvesh, K. and Reshmi, B. M., Optimising CNN Architecture for Accurate Detection of Tessellated Retinal Disease Using Fundus Images, J. Inform. Knowledge Manage., 24(5), 2550050(2025).
https://doi.org/10.1142/S0219649225500509
Barrett, E. K., Fard, C. M., Hannah, K. N., Moens, C. V., Perry, L. E., Ruddy, B. E., Shah, S. D., Lan, T. S., Wilson, T. J., Mark, R., Cai, L., Laura, B. E. and Mehdi, B., Mobile sensing: Leveraging machine learning for efficient human behavior modeling, 2020 Syst. Inform. Eng. Des. Sympos., 1–7(2020).
https://doi.org/10.1109/SIEDS49339.2020.9106648
Cai, Q., Jiachi, Y., Belal, J., Hao, W., Chandraman, P., Rasul, A. F. R., Sidam, A., Sinan, S., Sultan, A., Umer, M., Aseel, A., Essa, S., Arkook, B., Yas, A., Dalir, H. and Elham, H., Comprehensive Study and Design of Graphene Transistor, Micromach., 15(3), 406(2024).
https://doi.org/10.3390/mi15030406
El-Hag, N. A., Sedik, A., El-Shafai, W., Khalaf, A. A. M., El- Fishawy, A. S. and El-Samie, F. E. A. Classification of retinal images based on convolutional neural network, Micro. Res. Tech., 84(3), 394-414(2021).
https://doi.org/10.1002/jemt.23596
Giriraddi, G., Patil, M., & Joshi, V. (2024). Nanoparticles Characterization Using Non-learning and Learning Based Methods, Recent Trends Mach. Learn. IOT Smart Cities Appli., 1182, 281-293(2025).
https://doi.org/10.1007/978-981-97-8865-1_24
Ismail, M., Rasheed, M., Mahata, C., Kang, M. and Kim, S., Nano-crystalline ZnO memristor for neuromorphic computing: Resistive switching and conductance modulation, J. Alloys Compds., 960, 170846(2023).
https://doi.org/10.1016/j.jallcom.2023.170846
Jaberi-Douraki, M., Meyer, E., Riviere, J., Gedara, N. I. M., Jessica, K., Gerald, W. J. and Xu, X., Pulmonary adverse drug event data in hypertension with implications on COVID-19 morbidity, Sci. Rep., 11, 13349 (2021).
https://doi.org/10.1038/s41598-021-92734-7
Jahanian, M., Sahel, S. H., Zahra, D. A., Sadeghi, K., Niakan, K. S. R., Seyed, A. M. and Mahnaz, A., (2024). Machine learning approaches for recognition and classification of nanomaterial morphology, Mater. Today Commun., 41, 110818(2024).
https://doi.org/10.1016/j.mtcomm.2024.110818
Krishna, R., Suganya, R., Sai, M. Y., Asha, A., Jayanthi, D. and Naveen, K. M., Retinal Disease Classification in Optical Coherence Tomography Images Using a CNN Algorithm, 2024 IEEE Global Innov. Energy Syst. Technol., 1-6(2024).
https://doi.org/10.3390/diagnostics10080565
Krishnamoorthy, U. and Balasubramani, S., Intelligent Nanomaterial Image Characterizations: A Com- prehensive Review on AI Techniques that Power the Present and Drive the Future of Nanoscience, Adv, Theory Simulations, 7(12), 2400479(2024).
https://doi.org/10.1002/adts.202400479
Luo, Y., Mei, Z., Yibo, Q. and Chen, Y., SC-SNet: a novel transformer-CNN fusion architecture for enhanced segmentation and classification on high- resolution semiconductor micro-scale defects, Appl. Intel., 55(6), 439(2025).
https://doi.org/10.1007/s10489-024-06122-5
Mahum, R., Saeed, U. R., Ofonime, D. O., Amerah, A., Talha, M. and Hafiz, T. R., A Novel Hybrid Approach Based on Deep CNN to Detect Glaucoma Using Fundus Imaging, Electron., 11(1), 26(2021).
https://doi.org/10.3390/electronics11010026
Millagaha, G. N. I., Xuan, X., Robert, D., Santosh, A. and Majid, J. D., Global Trends in Cancer Nanotechnology: A Qualitative Scientific Mapping Using Content-based and Bibliometric Features for Machine Learning Text Classification, Cancers, 13(17), 4417(2021).
https://doi.org/10.3390/cancers13174417
Mondal, M. A., Mithra, D., Dhar, A., Saha, A., Das, S. and Ghosh, P., Nanotechnology Driven Advanced Imaging and Classification of Brain Tumours, Manus. Prep., 17(3), 03008(2025).
http://doi.org/10.21272/jnep.17(3).03008
Nandipati, M., Olukayode, F. and Salil, D., Bridging Nanomanufacturing and Artificial Intelligence—A Comprehensive Review, Mater., 17(7), 1621(2024
https://doi.org/10.3390/ma17071621
Saha, S., Janardhan, V. and Shaun, F., A fast and fully automated system for glaucoma detection using color fundus photographs, Sci. Rep., 13(1), 18408(2023).
https://doi.org/10.1038/s41598-023-44473-0
Sowmya, S. V. and Rimal, I. S. R., Advanced Nanoparticle Segmentation: A Deep Learning Approach using NS-Net on SEM Images., 2024 9th IEEE Int. Conf. Commun. Electron. Syst., 365-372(2024).
https://doi.org/10.1109/ICCES63552.2024.10859621
Sur, S., Sudhakara, R. M., Divya, P., Amit, B., Manu, F., Sachin, S. and Awasthi, A., Nanostructure analysis in polymeric materials for retinoblastoma tumor imaging using ensemble machine learning technique, Opt. Quanta. Electron., 55(11), 940(2023).
https://doi.org/10.1007/s11082-023-05167-z
Tayal, A., Gupta, J., Solanki, A., Bisht, K., Nayyar, A. and Masud, M., DL-CNN-based approach with image processing techniques for diagnosis of retinal diseases, Multimedia Syst., 28(4), 1417-1438(2022).
https://doi.org/10.1007/s00530-021-00769-7
Tripathy, A., Akshata, Y. P., Subhra, M. and Shyam, S. M., Convergence of Nanotechnology and Machine Learning: The State of the Art, Challenges, and Perspectives, Int. J. Mol. Sci., 25(22), 12368(2024).
https://doi.org/10.3390/ijms252212368
Wang, L., Li, B., Pan, J., Zhang, C. and Wang, T., Optical coherence tomography image recognition of diabetic retinopathy based on deep transfer learning, J. Radi. Res. Appl. Sci., 17(3), 101026(2024).
https://doi.org/10.1016/j.jrras.2024.101026
Yao, L. and Chen, Q., Machine learning in nanomaterial electron microscopy data analysis, Intel. Nanotechnol., 279-305(2023).
https://doi.org/10.1016/B978-0-323-85796-3.00010-X
Zhang, J., Lee, W. K. and Ge, M., Sub-10-second fly-scan nano-tomography using machine learning, Commun. Mater., 3(1), 91 (2022).
https://doi.org/10.1038/s43246-022-00313-8
Zhou, L., Yao, A. M., Wu, Y., Hu, Z., Huang, Y. and Hong, Z., Machine learning-assisted prediction of cathode materials for Zn‐ion batteries, Adv. Theory Simulations, 4(9), 2100196(2021).
