Navigation

Related Articles

Back to Latest Articles

Deep Learning, AI Could One Day Assist in Spotting Cancer


Digital Health Buzz!
@dighealthbuzz
Deep Learning, AI Could One Day Assist in...

Deep learning and artificial intelligence are on their way to bringing about a sea change in how we use computers in medicine. Neural networks have the power to work toward solutions using approaches they devise on their own — and it gives them incredible problem-solving capabilities. You can’t exactly plug more RAM into a human brain (yet), but you can combine a supercomputer cluster with neural networks that do diagnostic image processing. This mighty partnership gives the ability to apply the collective wisdom and insight of doctors and scientists worldwide to the collective processing power of every core in the cluster.

A year ago, the Office of the Vice President started the Cancer Moonshot. Its purpose was to make a “quantum leap” of progress in cancer prevention, diagnosis, and treatment. As part of the Moonshot, a good bit of money has been allocated to research scientists and programs nationwide. The Data Science Bowl is one such program, and awarding its prize is a critical milestone in support of the Cancer Moonshot. The event assembled both the data science and medical communities to develop AI and other algorithms that can detect lung cancer, as MIT Technology Review reports, in competition for a privately bankrolled $1M prize.

The winning team used a neural network capable of deep learning, and made sure to feed their AI sets of annotated images in order to provide more data points. The annotated images are useful, because we don’t always know why AI makes the choices it makes; annotations leave a trail of bread crumbs that the data scientists can use later to reconstruct the AI’s process. It also used an additional data set, and broke the Data Science Bowl challenge into two parts: identifying nodules from regular tissue, and then diagnosing the nodules that were cancerous.

This isn’t the first major AI to make a foray into diagnostic medical imaging. Watson has made many a partnership with prominent institutions like Sloan-Kettering and Weill Cornell. Deep learning has been used in an algorithm that could detect skin cancer in images with roughly the same accuracy as seasoned professional dermatologists. It’s also been applied to detecting a common cause of blindness in images of the retina.

Booz Allen Hamilton, the company that organized the contest, is making the winning algorithms available for free to the medical community so that everyone can benefit, according to the report.

https://www.extremetech.com/extreme/249212-deep-learning-ai-soon-assist-spotting-cancer

On – 12 May, 2017 By Jessica Hall

Leave your vote

0 points
Upvote Downvote

Total votes: 0

Upvotes: 0

Upvotes percentage: 0.000000%

Downvotes: 0

Downvotes percentage: 0.000000%

Show Comments (0)

Comments

Related Articles

Artificial Intelligence

The Increasing Importance of Mobile Technology in Healthcare

Mobile devices have become ever-present in our daily lives, and it is difficult to participate fully in activities of the global economy and 21st century life without access to...

Posted on by Digital Health Buzz!
Artificial Intelligence

Technology and Healthcare Collide to Bring Artificial Intelligence to the Medical World

  Every day, an incredible amount of data is produced in the world of healthcare. So, it’s no wonder that the leaders of the artificial intelligence industry see this...

Posted on by Digital Health Buzz!

Subscribe to Digital Health Buzz!

Subscribe to our email newsletter to receive useful articles and special offers.

We won't spam you, promise!

Hey there!

Sign in

Forgot password?
Close
of

Processing files…