To help automate a tedious but important part of biology lab work.

What it does

Detects and counts WBC of certain subtypes.

How we built it

Trained a Faster R-CNN object detection model to detect and count white blood cells and then integrated it to the front end using flask and javascript.

Challenges we ran into

Getting enough data to train an object detection model. Sending the image to the back end.

Accomplishments that we're proud of

Being able to get a count of various white blood cell types.

What we learned

How to do transfer learning with faster r-cnn and how to integrate an ML model into flask with javascript.

What's next for Online White Blood Cell Detection and Counting

With more data this model can perform at the same level of a human manually counting the blood cells or better. This technology can be applied to practically any cell type and can be used to automate the the tedious process of manually identifying/counting cells.

Built With

Share this project: