We were inspired by the reality that Covid-19 is a highly contagious viral disease, therefore, rapid and effective identification of the disease is imperative in order to determine the proper medical protocol.

What it does

Develop a model that can identify COVID-19 in chest x-ray images given data including lung images of healthy patients and patients with COVID-19 or Pneumonia that will aim to increase diagnosis accuracy and decrease the time taken to diagnose a patient, ultimately increasing the efficiency in hospitals to reduce overcrowding.

How we built it

Our modeling approach is making use of Google Cloud Platform AutoML Vision to develop a high-quality end-to-end image classification model for covid-19 Detection using Chest X-Ray Images. It helps us achieve faster performance and more accurate predictions.

We also coded a web application capable version in JavaScript, HTML, and CSS.

Challenges we ran into

Google Vision was/is experiencing issues with its Edge WebUI Model export, and since it is down, it restricted our ability to deploy the model in a web/mobile application form. However, we are able to deploy it over Cloud.

Accomplishments that we're proud of

Built cloud-based and web-based machine learning models with great model performance for covid-19 detection.

What we learned

How to use Google Cloud Platform AutoML Vision to build automation image classification.

What's next for CoviSure - Vision Detection for COVID-19

We would like to expand the predictive capability of our model by training it on other x-ray imaging of various diseases that affect the lungs and respiratory systems that can be identified through x-rays so we can better and more effectively diagnose Covid-19.

Built With

Share this project: