Skip to content

[TBENCH ‘23] CoviDetector: A Transfer Learning-based Semi Supervised Approach to detect Covid-19 using CXR Images

Notifications You must be signed in to change notification settings

dasanik2001/CoviDetector

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 

Repository files navigation

CoviDetector

CoviDetector: A Transfer Learning-based Semi Supervised Approach to detect Covid-19 using CXR Images

Code for this project is accessible on Github

Features

  • Application Prototype for the proposed study on COVID-19 Classification.
  • Built using the Semi-Supervised Learning and Transfer Learning models trained on Several Datasets.
  • The user will be able to upload the Chest X-Ray and the app will be diagnosing with the help of Deep Learning.
  • Supported on Android. iOS support will be available soon.

How to use the application

  1. Download or clone the repository:
git clone https://github.com/dasanik2001/CoviDetector.git
cd CoviDetectorApp
  1. Open CoviDetector in Android Studio.
  2. Build the project & run either on a simulator or a physical android device.

Data

The Datasets for this study are acquired from the following:

  1. COVID CXR Image Dataset (Research)
  2. DLAI3 Hackathon Phase3 COVID-19 CXR Challenge
  3. COVID-19 Radiography Database
  4. Covid19 Detection

Highlights

  • CoviDetector is new semi-supervised approach based on transfer learning & clustering.
  • CoviDetector generates models with improved accuracy and require less training data.
  • CXR images are given to the deep learning model to evaluate CoviDetector.
  • CoviDetector utilizes the GradCam to interpret the output in a graphical form.
  • Developed an Android app to offer a user-friendly interface.

Warning

The copyright of the shared work is reserved. Reference should be cite to the CoviDetector article for use in academic studies.

Cite this work

@article{CHOWDHURY2023100119,
title = {CoviDetector: A transfer learning-based semi supervised approach to detect Covid-19 using CXR images},
journal = {BenchCouncil Transactions on Benchmarks, Standards and Evaluations},
volume = {3},
number = {2},
pages = {100119},
year = {2023},
issn = {2772-4859},
doi = {https://doi.org/10.1016/j.tbench.2023.100119},
url = {https://www.sciencedirect.com/science/article/pii/S2772485923000364},
author = {Deepraj Chowdhury and Anik Das and Ajoy Dey and Soham Banerjee and Muhammed Golec and Dimitrios Kollias and Mohit Kumar and Guneet Kaur and Rupinder Kaur and Rajesh Chand Arya and Gurleen Wander and Praneet Wander and Gurpreet Singh Wander and Ajith Kumar Parlikad and Sukhpal Singh Gill and Steve Uhlig},
}

About

[TBENCH ‘23] CoviDetector: A Transfer Learning-based Semi Supervised Approach to detect Covid-19 using CXR Images

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages