MEDX-Vision Smart Diagnosis Through Deep Learning
Authors/Creators
- 1. Assistant Professor, Department of Computer Science, Agni College of Technology, Chennai (Tamil Nadu), India.
Contributors
Contact person:
Researchers:
- 1. Assistant Professor, Department of Computer Science, Agni College of Technology, Chennai (Tamil Nadu), India.
- 2. Department of Computer Science, Agni College of Technology, Chennai (Tamil Nadu), India.
Description
Abstract: Medx-Vision is an AI-powered mobile application that simplifies chest disease detection by analyzing X-ray images and providing easy-to-understand diagnostic results. Using a Convolutional Neural Network (CNN) trained on the NIH Chest X-ray dataset, the system identifies conditions like pneumonia and cardiomegaly with high accuracy. The backend, built with Flask, preprocesses images and returns predictions with confidence scores, which are formatted into laymanfriendly messages. The Android app, developed using Jetpack Compose, enables users to upload or capture images and view results through a clean, intuitive interface. Designed for accessibility, Medx-Vision bridges the gap between complex medical AI and everyday users, making early diagnosis more available in underserved areas.
Files
E109305050725.pdf
Files
(466.9 kB)
| Name | Size | Download all |
|---|---|---|
|
md5:303aee67c158418289ffe8f367c87f9d
|
466.9 kB | Preview Download |
Additional details
Identifiers
- DOI
- 10.54105/ijpmh.E1093.06020126
- EISSN
- 2582-7588
Dates
- Accepted
-
2026-01-15Manuscript received on 06 May 2025 | First Revised Manuscript received on 27 June 2025 | Second Revised Manuscript received on 25 December 2025 | Manuscript Accepted on 15 January 2026 | Manuscript published on 30 January 2026.
References
- Wang, X., Peng, Y., Lu, L., Lu, Z., Bagheri, M., & Summers, R. M. (2017). Title: "ChestX-ray8: Hospital- scale Chest X-ray Database and Benchmarks on Weakly- Supervised Classification and Localization of Common Thorax Diseases."Paper Link (arXiv). DOI: https://doi.org/10.1109/CVPR.2017.369
- François Chollet, "Deep Learning with Python," Manning Publications, 2017. Official site: https://www.tensorflow.org
- LeNet-5: Yann LeCun et al., 1998 VG GNet: Simonyan & Zisserman (2014) ResNet: Kaiming He et al. (2015). http://vision.stanford.edu/cs598_spring07/papers/Lecun98.pdf , works remain significant, see the declaration
- Flask Documentation: https://flask.palletsprojects.com/en/stable/
- https://flask.palletsprojects.com/
- FastAPI (if applicable): https://fastapi.tiangolo.com/
- Postman API https://learning.postman.com/
- Android+Retrofit Testing: Docs: https://developer.android.com/
- Litjens, G. et al. (2017)- A survey on deep learning in medical image analysis. Link DOI: https://doi.org/10.1016/j.media.2017.07.005
- Selvaraju et al., "Grad-CAM: Visual Explanations from Deep Networks" (2016). DOI: https://doi.org/10.1109/ICCV.2017.74
- NGROK: https://ngrok.com/
- Render / Vercel / Heroku (for backend hosting): Their documentation pages. https://render.com/docs/render-vs-vercelcomparison