gGoogle’s artificial intelligence algorithm to help detect breast cancer has become part of commercial mammograms.
On November 28, the company announced that it had licensed its artificial intelligence technology to iCADa medical technology company that provides breast cancer screening services to healthcare facilities around the world.
While iCAD already includes AI-based strategies in its cancer screening services, it will now also integrate Google’s algorithm, which The Google Tested with researchers at Northwestern University. “It’s an inflection point for us,” says Greg Corrado, co-founder of the Google Brain team and principal scientist in the AI healthcare team at Google. “We’re moving from academic research to being able to deploy our algorithm in the real world.”
Earlier study Published in 2020 on natureGoogle’s mammogram algorithm performed better than the radiologist in recording fewer false positives and false negatives in reading the images. The study included mammograms from more than 91,000 women in the US and UK. In the US, where most women ages 50 to 74 are recommended to be screened every two years, Google’s system reduced the false positive rate by 6%, and in the UK where Women ages 50 to 70 are advised to get screened every three years, at a rate of 1.2%. The machine learning algorithm also reduced false positives by 9% in the US and nearly 3% in the UK
This feature will now be commercially available for the first time to the 7,500 mammography sites globally, including University Health Systems, that use iCAD services. While Corrado declined to explain how Google’s algorithm differs from those being tested by other researchers and companies in the field, he said the system incorporates data from a wide range of images, even those of breast tissue, to improve the machine learning process. iCAD and Google will continue to develop and improve the technology as part of the partnership agreement.
Read more: How artificial intelligence is changing medical imaging to improve patient care
The algorithm is not designed to replace radiologists, at least not in the near term. But in Europe, says Stacey Stevens, president and CEO of iCAD, that could help ease the burden on the radiologist, since many countries (including the UK) require two readings of a mammogram. iCAD is working with health regulators to get the appropriate authorization so that the company’s AI-based interpretation could eventually be one of them, she says. In the US, Stevens expects to launch the first product that includes the Google algorithm in early 2024.
Stevens also predicts that the AI-based system will bring mammography to more people around the world, especially in low-resource areas that cannot support the infrastructure required to host hardware related to storing mammography images. With Google’s cloud-based storage capabilities, she says, “we have the ability to expand into new geographies and new regions of the world and extend our tools across more patients in regions of the world that are constrained by infrastructure challenges.”
As with any machine learning system, the more data from mammograms that is fed into the algorithm, the better it will be at detecting the smallest differences that distinguish normal tissue from potentially cancerous tissue. Women who receive mammograms using the AI-based system will have their information fed back to the algorithm, minus any identifying data. Currently, most people who undergo mammograms likely do not realize that an AI system may be in the background complementing the radiologist, because, at present, no regulatory agencies have signed off on an entirely AI-based interpretation of mammograms. But as more AI algorithms like Google enter the market, that may change, and radiologists may end up arguing with patients about how to interpret their images.
Read more: How researchers are working to make IVF more effective
Eventually, such machine-based readings could start to pull out patterns that the human eye can’t see. Stevens says iCAD’s current AI-based algorithm is already detecting microcalcifications in breast tissue that scientists are beginning to link to an increased risk of heart disease. If this association is confirmed, mammograms could also become a tool for assessing heart disease risk in women.
In the meantime, adding an AI perspective to mammograms could begin to improve how women’s risk of developing breast cancer is determined. AI systems can better distinguish, for example, the differences that are unique to certain racial and ethnic groups; In the United States, African American women are more likely to develop more aggressive types of breast cancer and more likely to die from the disease than other women, so training an AI system to track the first signs of these cancers could yield better results. “We’ve found that there are many cases of women who have had what look like normal mammograms, but there are things in those pictures that cannot be seen with the human eye,” Stevens says. If these differences can be picked up by an AI algorithm, these women could be sent for additional screening to see if they are at a higher risk of developing cancer. This can put them on the path to receiving treatment sooner, which ultimately leads to a better chance of survival. It could also mean less expensive medical services, which could translate into cost savings for the health system. “We’re in the early stages of assessing breast cancer risk using AI, but we’re excited about its potential,” Stevens says.
More must-read books from TIME
Discussion about this post