Google's machine learning to study radiotherapy for oral cancers

Google’s machine-learning division, DeepMind, is partnering with the U.K.’s National Health Service through the University College London Hospitals NHS Foundation Trust in an effort to treat oral cancers more efficiently, according to Fortune.  

The company previously partnered with another British health system, Moorfields Eye Hospital, to perfect eye disease-detection.

DeepMind’s executives hope this partnership could help shave up to three hours off an existing four-hour radiology treatment, according to a statement. That’s because the machines used in the treatment would begin to learn how to better target and kill cancer cells in and around the mouth without damaging surrounding healthy cells.

After being exposed to enough data, the machines could draw its own conclusions about the best way to perform the task at hand, instead of relying on (possibly faulty and less precise) human information.

The machine will start learning on about 700 scans of former oral cancer patients whose identifying markers have been obscured. Check out Fortune to see how Google, DeepMind and the NHS have gotten into trouble with non-anonymized data before. 

Caitlin Wilson,

Senior Writer

As a Senior Writer at TriMed Media Group, Caitlin covers breaking news across several facets of the healthcare industry for all of TriMed's brands.

Around the web

The nuclear imaging isotope shortage of molybdenum-99 may be over now that the sidelined reactor is restarting. ASNC's president says PET and new SPECT technologies helped cardiac imaging labs better weather the storm.

CMS has more than doubled the CCTA payment rate from $175 to $357.13. The move, expected to have a significant impact on the utilization of cardiac CT, received immediate praise from imaging specialists.

The all-in-one Omni Legend PET/CT scanner is now being manufactured in a new production facility in Waukesha, Wisconsin.

Trimed Popup
Trimed Popup