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 | A Lightweight and Justifiable Deep Learning Framework for Diagnosing Multiple Classes of Retinal Disease |
|---|---|
| ABSTRACT | Global healthcare systems face a serious issue due to the sharp rise in retinal disorders such Diabetic Macular Edema (DME) and Choroidal Neovascularization (CNV). Optical Coherence Tomography (OCT) manual diagnosis is labor-intensive, prone to inter-observer variability, and frequently constrained by the availability of skilled ophthalmologists. In order to increase diagnostic accuracy while minimizing computing overhead, this research introduces "NeuroRetina," an automated, energy-efficient deep learning architecture. The suggested technique divides OCT scans into eight different categories using the MobileNetV3-Large architecture. In contrast to traditional "black-box" models, NeuroRetina incorporates Grad-CAM (Gradient-weighted Class Activation Mapping) to improve therapeutic trust by offering visual explainability. The suggested approach has excellent classification accuracy and operating efficiency appropriate for real-time deployment, according to experimental research. |
| TITLE | |
| AUTHOR | MOHAMMED SAAD A, PAVITHRA P KURDEKAR, MOHAMMED SADIQ KHAZI, VINAY H PATIL, CHAITHRA G S UG Students, Dept. of CSE, Jain Institute of Technology, Davangere, Karnataka, India Assistant Professor, Dept. of CSE, Jain Institute of Technology, Davangere, Karnataka, India |
| VOLUME | 177 |
| DOI | DOI: 10.15680/IJIRCCE.2025.1312119 |
| pdf/119_A Lightweight and Justifiable Deep Learning Framework for Diagnosing Multiple Classes of Retinal Disease.pdf | |
| KEYWORDS | |
| References | 1. D. S. Kermany et al., "Identifying Medical Diagnoses and Treatable Diseases by Image-Based Deep Learning," Cell, vol. 172, no. 5, pp. 1122-1131, 2018. 2. S. Rahman et al., "A Lightweight CNN for Multiclass Retinal Disease Screening with Explainable AI," Journal of Personalized Medicine, vol. 15, no. 8, Aug. 2025. 3. A. Howard et al., "Searching for MobileNetV3," Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019. 4. M. Al-Sarem et al., "Retinal Disease Detection by OCT-Based Deep Learning," 2024 International Conference on AI and Quantum Computation (ICAIQSA), IEEE, Dec. 2024. 5. R. R. Selvaraju et al., "Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization," ICCV, 2017. 6. Y. Zhang and L. Wang, "MedNetV3: A Deep Learning Model for Medical Image Analysis," 2024 ICCWAMTIP, IEEE, Feb. 2025. 7. A. Kumar et al., "Optimized Detection using MobileNet V3 Architecture," 2024 2nd International Conference on Disruptive Technologies (ICDT), IEEE, 2024. |
