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.
This new data poisoning tool lets artists fight back against generative AI
The tool, called Nightshade, messes up training data in ways that could cause serious damage to image-generating AI models.
Rogue superintelligence and merging with machines: Inside the mind of OpenAI’s chief scientist
An exclusive conversation with Ilya Sutskever on his fears for the future of AI and why they’ve made him change the focus of his life’s work.
The Biggest Questions: What is death?
New neuroscience is challenging our understanding of the dying process—bringing opportunities for the living.
Driving companywide efficiencies with AI
Advanced AI and ML capabilities revolutionize how administrative and operations tasks are done.
Get the latest updates from
MIT Technology Review
Discover special offers, top stories, upcoming events, and more.