RETINA ANALYSIS APP

##plugins.themes.bootstrap3.article.sidebar##

pdf
Published Jun 6, 2025

##plugins.themes.bootstrap3.article.main##

Prof. Yogendra Patil
Associate Professor, Department of Computer Engineering, MMIT, Pune, Maharashtra, India
Manasi Konde
U.G. Student, Department of Computer Engineering, MMIT, Pune, Maharashtra, India.
Pallavi Jadhav
U.G. Student, Department of Computer Engineering, MMIT, Pune, Maharashtra, India.
Ashwini Bhadane
U.G. Student, Department of Computer Engineering, MMIT, Pune, Maharashtra, India.
Vaishnavi Gade
U.G. Student, Department of Computer Engineering, MMIT, Pune, Maharashtra, India.

Abstract

The Retina Image Analysis Android Application is an AI-powered mobile health (mHealth) solution designed to assist users in the early detection of retina-related disorders through deep learning and interactive guidance. Developed using Java/XML for Android and integrated with Firebase Realtime Database and Authentication, the app allows users to upload retina images from their device gallery and complete a symptom-based questionnaire. The core diagnostic process utilizes a Convolutional Neural Network (CNN) model deployed via TensorFlow Lite, which classifies retina images into disease categories and generates confidence scores in real-time.


To enhance interpretability and user support, the application includes an NLP-based chatbot assistant that responds to natural language queries, explains disease outcomes, and offers customized recommendations. The system further employs the Google Maps API to identify and display nearby retina specialists and eye hospitals based on the user's location, thus bridging the gap between digital diagnosis and clinical consultation.


This solution demonstrates how mobile AI, when combined with cloud-based data handling, chatbot interaction, and geolocation services, can empower patients with accurate health insights, promote early intervention, and reduce dependency on in-person screenings, especially in remote or underserved regions.

##plugins.themes.bootstrap3.article.details##

Issue
Vol 12 No 5 (2025): Volume 12 Issue 5
Section
Articles

References

[1]. A. Sharma, R. Singh, and M. Bhattacharya, "DeepRetina: Automated Detection of Retinal Diseases Using Deep Convolutional Neural Networks," IEEE Access, vol. 8, pp. 123456–123465, 2020. doi: 10.1109/ACCESS.2020.2987365.
[2]. L. Chen, Y. Wu, and S. Zhang, "Mobile-Based Diabetic Retinopathy Diagnosis Using Lightweight CNN Models," in Proc. IEEE EMBC, 2021, pp. 3120–3124. doi: 10.1109/EMBC2021.9629467.
[3]. S. Patel, D. Khanna, and R. Prasad, "An NLP-Based Virtual Assistant for Healthcare Applications," IEEE J. Biomed. Health Inform., vol. 26, no. 1, pp. 88–96, Jan. 2022. doi: 10.1109/JBHI.2022.3120012.
[4]. J. M. Andrews and T. Nakamura, "EyeDiseaseNet: A Transfer Learning Approach for Retina Disease Classification," Comput. Biol. Med., vol. 124, p. 104000, 2020. doi: 10.1016/j.compbiomed.2020.104000.
[5]. P. Raj and A. Dubey, "Real-Time Disease Detection from Fundus Images Using Android Platform," in Proc. IEEE TENSYMP, 2021, pp. 155–159. doi: 10.1109/TENSYMP50017.2021.9496213.
[6]. K. Iyengar and H. S. Ahmed, "A Review on Deep Learning Techniques in Ophthalmology," IEEE Rev. Biomed. Eng., vol. 16, pp. 56–72, 2023. doi: 10.1109/RBME.2023.3251783.
[7]. R. Mehta and M. Kulkarni, "An Intelligent Symptom Checker and Visual Diagnostic Tool for Eye Disorders," J. Med. Syst., vol. 48, no. 1, pp. 1–12, 2024. doi: 10.1007/s10916-024-01932-z.
[8]. F. Al-Rawi, H. Singh, and N. Bashir, "AI-Driven Mobile Applications for Early Eye Disease Screening in Rural Populations," in Proc. IEEE GHTC, 2022, pp. 501–506. doi: 10.1109/GHTC53405.2022.9885342.
[9]. A. Nayak, S. Wang, and P. Gupta, "Multimodal AI Assistants for Personalized Health Recommendations," IEEE Trans. Artif. Intell., vol. 4, no. 1, pp. 18–26, 2025. doi: 10.1109/TAI.2025.0034521.
[10]. G. Brown, A. Tiwari, and J. Dawson, "Hybrid Deep Learning for Multi-Class Retinal Disease Detection," IEEE Trans. Neural Netw. Learn. Syst., vol. 34, no. 3, pp. 1887–1898, 2023. doi: 10.1109/TNNLS.2023.3284567.
[11]. H. Shah and P. Desai, "Chatbots in Healthcare: Conversational AI for Symptom Checking and Disease Prediction," in Proc. IEEE ICASSP, 2022, pp. 1200–1205. doi: 10.1109/ICASSP43922.2022.9746690.
[12]. Y. Lin, X. Jiang, and N. Kumar, "Secure and Scalable Mobile Health Framework Using Firebase," IEEE Access, vol. 10, pp. 109810–109822, 2022. doi: 10.1109/ACCESS.2022.3191054.
[13]. E. Kumar, M. Jain, and A. Shah, "Disease Detection in Retina Images Using Multi-Scale Feature Extraction," IEEE Intell. Syst., vol. 38, no. 1, pp. 37–45, 2023. doi: 10.1109/MIS.2023.120312.
[14]. B. Li, H. Xu, and T. Wang, "Offline AI for Medical Diagnostics in Remote Settings Using Android TFLite," IEEE Embedded Systems Lett., vol. 15, no. 2, pp. 66–69, 2023. doi: 10.1109/LES.2023.3277829.
[15]. A. Sengupta and N. Ghosh, "Geolocation Services for Mobile Health Monitoring Systems," IEEE Systems J., vol. 17, no. 2, pp. 1222–1230, 2023. doi: 10.1109/JSYST.2023.3100248.