International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | Cataract Detection and Risk Assessment using Deep Learning on Retinal Images |
|---|---|
| ABSTRACT | Cataract is one of the leading causes of blindness worldwide, particularly affecting elderly populations. Early and accurate detection of cataracts is crucial for preventing vision loss. This paper presents an intelligent web-based cataract detection system using machine learning, computer vision, and explainable artificial intelligence techniques. The proposed system accepts eye images from users, validates image authenticity, predicts cataract severity levels, and provides visual explanations using Grad- CAM heatmaps. The system is implemented using Flask as the backend framework, OpenCV for image processing, TensorFlow-based analysis logic, MongoDB for data storage, and an integrated chatbot powered by a Large Language Model (LLM) for medical assistance. Experimental analysis demonstrates that the system effectively classifies cataract stages such as Normal, Early, Moderate, and Severe Cataract, while offering interpretable visual insights to improve clinical trust and usability. |
| AUTHOR | DR.NARESH PATEL K M, SAANVI KARIBASAPPA BANKAPUR, CHAITRA S K, RAKSHIT G K Associate Professor, Department of Computer Science and Engineering, Bapuji Institute of Engineering and Technology, Davangere, Karnataka, India UG Student, Department of Computer Science and Engineering, Bapuji Institute of Engineering and Technology, Davangere, Karnataka, India |
| VOLUME | 177 |
| DOI | 10.15680/IJIRCCE.2025.1312073 |
| pdf/73_Cataract Detection and Risk Assessment using Deep Learning on Retinal Images.pdf | |
| KEYWORDS | |
| References | 1) Liu, X., Zhang, L., & Chen, Y. (2025). Multimodal Learning Framework for Early Cataract Detection Using Fundus Images and Clinical Parameters. Ophthalmic AI Re search Journal, 14(2), 112–125. 2) Sharma, R., Gupta, M., & Verma, A. (2024). Explainable AI for Cataract Detection Using Grad- CAM and ResNet50. International Journal of Medical Imaging, 18(4), 289–301. 3) Xu, H., Wang, Q., & Li, J. (2024). Dual-Stage Deep Learning Architecture for High Resolution Ocular Lesion Segmentation. Journal of Ophthalmic Deep Learning, 9(1), 45–59. 4) Wu, T., Huang, S., & Zhao, L. (2024). Scalable AI Platform for Cataract Management Using Cloud-Integrated Fundus Imaging. Healthcare Intelligence Systems, 7(3), 201–215. 5) Jagadale, S., Patil, R., & Kulkarni, V. (2024). Early Detection of Nuclear Cataract Us ing Circle Hough Transform and Hybrid Machine Learning Models. Ophthalmic Image Processing Review, 12(1), 77–89. 6) Novita, H. D., Sari, F., & Nugroho, R. (2024). Comparative Study of Traditional ML and CNNModels for Retinal Image Classification. Biomedical Vision and Computing, 16(2), 134–148. 7) Ibrahim, M., Hassan, A., & Noor, F. (2024). Federated Learning Approaches for Privacy Preserving Cataract Detection Across Multi-Center Clinics. AI in Ophthalmology, 5(2), 98–111 8) Patel, D., Mehta, R., & Shah, P. (2023). Attention-Based Convolutional Neural Networks for Enhanced Cataract Detection. Medical Imaging Advances, 11(4), 260–273. 9) Sait, M., Rahman, K., & Ali, S. (2023). Lightweight AI Models for Mobile-Based Cataract and Glaucoma Screening. Mobile Health Technologies Journal, 4(1), 55–70. 10) Yujie, S., & Fei, P. (2023). Enhanced k-NN Algorithm for Improved Cataract Classifica tion Using Optimized Distance Metrics. Pattern Recognition in Medicine, 8(3), 199–210. 11) Kemp, S. (2023). Digital Infrastructure and Mobile Penetration in Indonesia: Opportuni ties for AI-Driven Healthcare. Global Digital Insights Report, 2023 Edition, 1–22. 12) Brown, T., Silva, P., & Wong, J. (2023). Clinical Evaluation of AI-Assisted Fundus Screening Versus Slit-Lamp Examination. Journal of Ophthalmic Clinical Trials, 6(3), 150–165. 13) Kumar, A., Rajan, P., & Thomas, L. (2022). Transfer Learning Techniques for Cataract Staging Using Deep Convolutional Architectures. Computers in Medical Imaging, 10(2), 88–103. 14) Chen, Y., Luo, F., & Zhou, M. (2022). GAN-Based Data Augmentation for Cataract Clas sification from Fundus Images. Medical Image Synthesis and Analysis, 13(1), 41–56. 15) Matsuda, K., Ito, S., & Nakamura, Y. (2022). Multimodal Fusion of Ultrasound and Fun dus Imaging for Lens Opacity Assessment. Ophthalmic Diagnostics and Imaging, 15(2), 121–137. 16) Zhang, W., Li, X., & Han, Y. (2021). Multi-Scale CNN Architectures for Enhanced Oph thalmic Image Analysis. IEEE Transactions on Medical Imaging, 40(7), 1895–1908. 17) Singh, P., Das, R., & Banerjee, S. (2021). Dataset Bias and Generalization Challenges in Retinal Imaging AI Models. Journal of Medical Vision Research, 5(1), 33–48. 18) Nguyen, H., Tran, M., & Vo, K. (2020). Tele-Ophthalmology Platform with Automated AI-Based Image Triage. Digital Health Innovations, 9(4), 301–315. 19) Garcia, L., Moreno, J., & Alvarez, B. (2020). Fusion of Clinical Variables and Fundus Images for Eye Disease Prediction. Ocular Medicine and Analytics, 7(2), 92–108. 20) Alvarez, R., Torres, P., & Medina, L. (2020). Longitudinal Study of Cataract Progression and Visual Decline Over Time. Vision Science Reports, 18(1), 12–28. |
