Public urged to help cancer researchers by playing online game

People will be asked to trace the outlines of tongue images to train a computer algorithm to recognise oral cancer.
The AcCELLerate game
Jamie Harris7 July 2021

Scientists have turned to the public to help with their latest cancer research in the form of an online citizen science game.

AcCELLerate tasks users with tracing the outline of a series of fluorescent dye-stained tongue images which become increasingly complex, using their computer mouse or finger on a smartphone.

The project is designed to train a computer algorithm to recognise oral cancers in medical images, improving its ability to differentiate between healthy and cancerous cells.

[xdelx]

“I’m really excited that the public will be contributing to my work on oral cancer,” said Dr Priyanka Bhosale, from King’s College London’s Centre for Stem Cells and Regenerative Medicine.

“The outcomes of the public training the AI will help me assess tumour tissue samples in a faster and more reliable way.”

Over time, it is hoped the tool can be used to advance research into other cancers.

The game forms part of the Royal Society Summer Science 2021 event and can be found at citizen.cellari.io/.

Create a FREE account to continue reading

eros

Registration is a free and easy way to support our journalism.

Join our community where you can: comment on stories; sign up to newsletters; enter competitions and access content on our app.

Your email address

Must be at least 6 characters, include an upper and lower case character and a number

You must be at least 18 years old to create an account

* Required fields

Already have an account? SIGN IN

By clicking Sign up you confirm that your data has been entered correctly and you have read and agree to our Terms of use , Cookie policy and Privacy notice .

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.

Thank you for registering

Please refresh the page or navigate to another page on the site to be automatically logged in