DeepMind is furthering its cancer research efforts with a newly announced partnership. Today, the London-based Google subsidiary said it has been given access to mammograms from roughly 30,000 women that were taken at Jikei University Hospital in Tokyo, Japan between 2007 and 2018. It’ll use that data to refine its artificially intelligent (AI) breast cancer detection algorithms.
Over the course of the next five years, DeepMind researchers will review the 30,000 images, along with 3,500 images from magnetic resonance imaging (MRI) scans and historical mammograms provided by the U.K.’s Optimam (an image database of over 80,000 scans extracted from the NHS’ National Breast Screening System), to investigate whether its AI systems can accurately spot signs of cancerous tissue.
The collaboration builds on DeepMind’s work with the Cancer Research UK Imperial Center at Imperial College London, where it has already analyzed roughly 7,500 mammograms.
“The involvement of the Jikei University Hospital in a global research partnership will help take us one step closer to developing technology that could ultimately transform care for the millions of people who develop breast cancer around the world every year,” said professor Ara Darzi, director of the Cancer Research UK Imperial Center.
Dominic King, clinical lead of DeepMind Health, noted in a blog post that training DeepMind’s AI system on datasets from other countries would help mitigate algorithmic bias that might inadvertently crop up.
“Bias can occur when you train an AI system on data which doesn’t accurately reflect the people it is being designed for, and it’s a serious problem,” he said. “In the field of mammography … there can be considerable variations in breast density between ethnic groups. Bias in our AI system could therefore result in breast cancers being misidentified or even missed altogether if the technology is not set up to reflect these differences.”
DeepMind is involved in several health-related AI projects, including an ongoing trial at the U.S. Department of Veterans Affairs that seeks to predict when patients’ conditions will deteriorate during a hospital stay. Previously, it partnered with the U.K.’s National Health Service to develop an algorithm that could search for early signs of blindness.
And in a paper presented at the Medical Image Computing & Computer Assisted Intervention conference last month, DeepMind researchers said they’d developed an AI system capable of segmenting CT scans with “near-human performance.” They plan to deploy the model, which they say has the potential to reduce the time to diagnosis, in a clinical environment in the next year.
Google has more broadly invested heavily in AI health care applications. This spring, the Mountain View company’s Medical Brain team said they’d created an AI system that could predict the likelihood of hospital readmission and that they had used it in June to forecast mortality rates at two hospitals with 90 percent accuracy.
In February, scientists from Google and Verily Life Sciences, its health-tech subsidiary, created a machine learning network that could accurately deduce basic information about a person, including their age and blood pressure, and whether they were at risk of suffering a major cardiac event like a heart attack.
Verily, a research division within Google parent Alphabet, is also developing automated systems to tackle sleep apnea, pharmaceutical drug discovery, blood collection, and health insurance.