Google’s DeepMind’s Health initiative will soon work to explore how artificial intelligence could save hours and hours of precious time in the treatment of oral, head, and neck cancers, the company announced on Tuesday.
This is obviously a big deal as 1 in 75 men and 1 in 150 women will be diagnosed with oral cancer during their lifetime — and oral cavity cancer has risen by 92 percent since the ‘70s. Head and neck cancer in general affects over 11,000 patients in the United Kingdom each year. (Google’s partnering with the Radiotherapy Department at University College London Hospitals Foundation). It’s the third between DeepMind and NHS.
Despite advances in radiotherapy, planning treatment that avoids vital nerves and organs in the cephalic and oral parts of the body still presents a time-consuming challenge to physicians. In order to avoid damaging healthy tissue, they must use a detailed process called segmentation, which provides a radiotherapy machine with a detailed map of which areas of the body to avoid treating.
This is where the A.I. comes in: using the scans from around 700 former patients, researchers at UCLH and Google hope to determine if machine learning could reduce the segmentation process from four hours to just one. While treatments will still ultimately be determined by the physicians, a successful A.I. could increase efficiency in the process. If the technology is successful, it could be applied to cancers in other areas of the body.
“Even though UCLH’s specialist team at its dedicated head and neck cancer center is a national leader in this process, there is still potential for innovation,” states the DeepMind blog. “We think machine learning could make a difference.”
DeepMind, which was founded in London in 2010, was acquired by Google in 2014. According to its website, approximately 10 percent of patients who use the National Health Service will experience a medical error — often the result of outdated technology.
While A.I. could make huge leaps in saving healthcare systems precious time and prevent fatal errors, it also raises questions of data ownership.
“In the U.S., you do not have control over your own data — there are no regulatory measures to ensure that information is not abused,” Mustafa Suleyman, the co-founder of Google DeepMind, told Inverse in July.
In May, DeepMind gained access to the health records of over 1.6 million British patients from the Royal Free NHS trust in order to build an early-detection app to assess an individual’s risk for kidney failure.
In accordance with UCLH standards, data from this project will only be available for research on radiotherapy imaging and the anonymized data will be destroyed at the conclusion of the project.
DeepMind previously partnered with Moorfields Eye Hospital NHS Foundation Trust to created an A.I. based retina-scanning program that would detect early signs of eye disease.