Intel opens developer contest to fight cancer with artificial intelligence tools

Company officials said the competition offers a total of $100,000 for three winners, with first place taking $50,000.
By Jack McCarthy
09:39 AM

Intel opened up a developers’ competition to create an artificial intelligence-based model for cervical cancer screening.

In the so-called Kaggle competition participants work to produce an algorithm that accurately identifies a woman’s cervix type based on images.

Early identification of cervical cancer can help prevent ineffectual treatments and allow healthcare providers to offer proper referrals for cases requiring more advanced treatment.

The competition is sponsored along with MobileODT, a maker of optical diagnostic devices and software services focused on early cancer detection.

[Also: Hospital datacenters: Extinct in 5 years?]

Intel said the competition is part of its strategy for enabling state-of-the-art AI in the industry by working, among other ways, to make AI training and tools broadly accessible to developers through the Intel Nervana AI Academy.

“We aim to challenge developers, data scientists and students to develop AI algorithms to help solve real-world challenges in industries including medical and healthcare,” Intel senior vice president Doug Fisher said.

Fisher added that MobileODT’s breakthrough optical diagnostic devices and software services, combined with Intel-based AI that Kagglers develop through this competition, will improve MobileODT’s quality assurance workflow.

“This will aid the ability to make real-time determinations on treatment, and provide a first-line response to women around the world to help detect cervical cancer early,” Fisher said.

The prize pool totals $100,000 for the top-three finishers, including $50,000 for the first-place competitor. 

Twitter: @HealthITNews


Like Healthcare IT News on Facebook and LinkedIn

Want to get more stories like this one? Get daily news updates from Healthcare IT News.
Your subscription has been saved.
Something went wrong. Please try again.