Skip to Content

DeepMind Will Use AI to Streamline Targeted Cancer Treatment

Machine learning could cut the time it takes to plan a patient’s radiotherapy treatment by hours.
August 31, 2016

Working out how to zap a tumor with radiation is a laborious process for physicians. Google’s machine-learning division, DeepMind, thinks AI can help ease the burden.

When medics apply radiotherapy to a cancer patient, they have to carefully determine which parts of the body should be exposed to radiation in order to kill the tumor while ensuring that as much healthy surrounding tissue as possible is preserved. The process, known as segmentation, requires the doctor to manually draw areas that can and can’t be treated onto a 3-D scan of the patient’s tumor site. The process is particularly complex for head and neck cancers, in which the tumor often sits immediately next to many important anatomical features.

Now, though, DeepMind will work with University College Hospital in London to develop an artificial-intelligence system that can automate the process. DeepMind will analyze 700 anonymized scans from former patients who suffered from head and neck cancers. They hope to create an algorithm that can learn how physicians make decisions about this part of the treatment process, ultimately segmenting the scans automatically.

“Clinicians will remain responsible for deciding radiotherapy treatment plans, but it is hoped that the segmentation process could be reduced from up to four hours to around an hour,” explains DeepMind.

In time, the DeepMind team hopes, the same algorithm might find application in treating cancers elsewhere in the body.

IBM’s Watson supercomputer has also been applying machine learning to personalized cancer treatment, though its approach is a little more bookish. It’s currently drawing on 600,000 medical evidence reports and 1.5 million patient records and clinical trials to help doctors develop better treatment plans for cancer patients.

This isn’t DeepMind’s first foray into medical research, either—in fact, this is the third project that it’s announced in collaboration with the U.K.’s National Health Service. After coming under fire earlier in the year when an app project appeared to provide DeepMind with free access to 1.6 million patients’ records, the research outfit recently announced that it was helping to spot the early signs of visual degeneration by sifting through a million eye scans.

Perhaps it’s working its way down the body.

(Read more: DeepMind, “DeepMind’s First Medical Research Gig Will Use AI to Diagnose Eye Disease”)

Keep Reading

Most Popular

light and shadow on floor
light and shadow on floor

How Facebook and Google fund global misinformation

The tech giants are paying millions of dollars to the operators of clickbait pages, bankrolling the deterioration of information ecosystems around the world.

This new startup has built a record-breaking 256-qubit quantum computer

QuEra Computing, launched by physicists at Harvard and MIT, is trying a different quantum approach to tackle impossibly hard computational tasks.

wet market selling fish
wet market selling fish

This scientist now believes covid started in Wuhan’s wet market. Here’s why.

How a veteran virologist found fresh evidence to back up the theory that covid jumped from animals to humans in a notorious Chinese market—rather than emerged from a lab leak.

protein structures
protein structures

DeepMind says it will release the structure of every protein known to science

The company has already used its protein-folding AI, AlphaFold, to generate structures for the human proteome, as well as yeast, fruit flies, mice, and more.

Stay connected

Illustration by Rose WongIllustration by Rose Wong

Get the latest updates from
MIT Technology Review

Discover special offers, top stories, upcoming events, and more.

Thank you for submitting your email!

Explore more newsletters

It looks like something went wrong.

We’re having trouble saving your preferences. Try refreshing this page and updating them one more time. If you continue to get this message, reach out to us at customer-service@technologyreview.com with a list of newsletters you’d like to receive.