A Google artificial intelligence (AI) system proved as good as expert radiologists at detecting women with breast cancer by screening mammograms and showed promise at reducing errors, researchers in the US and UK reported.
The study, published on Wednesday in the journal Nature, is the latest to show that AI has the potential to improve the accuracy of screening for breast cancer, which affects one in eight women globally.
Radiologists miss about 20 percent of breast cancers in mammograms, the American Cancer Society says, and half of all women who get the screenings over a 10-year period have a false positive result.
The findings of the study, developed with Alphabet Inc’s DeepMind AI unit, which merged with Google Health in September last year, represent a major advance in the potential for the early detection of breast cancer, said Mozziyar Etemadi, one of its coauthors from Northwestern Medicine in Chicago.
The team, which included researchers at Imperial College London and the UK’s National Health Service, trained the system to identify breast cancers on tens of thousands of mammograms.
They then compared the system’s performance with the actual results from a set of 25,856 mammograms from the UK and 3,097 from the US.
The study showed that the AI system could identify cancers with a similar degree of accuracy to expert radiologists, while reducing the number of false positive results by 5.7 percent in the US-based group and by 1.2 percent in the UK-based group.
It also cut the number of false negatives, where tests are wrongly classified as normal, by 9.4 percent in the US group and by 2.7 percent in the UK group.
The differences reflect the ways in which mammograms are read.
In the US, only one radiologist reads the results and the tests are done every one to two years. In the UK, the tests are done every three years and each is read by two radiologists. When they disagree, a third is consulted.
In a separate test, the group pitted the AI system against six radiologists and found it outperformed them at accurately detecting breast cancers.
Connie Lehman, head of the breast imaging department at Harvard Medical School’s Massachusetts General Hospital, said the results were in line with findings from several groups using AI to improve cancer detection in mammograms, including her own work.
The notion of using computers to improve cancer diagnostics is decades old and computer-aided detection (CAD) systems are commonplace in mammography clinics, yet CAD programs have not improved performance in clinical practice.
The issue is that CAD programs are trained to identify things human radiologists can see, whereas with AI, computers learn to spot cancers based on the actual results of thousands of mammograms, Lehman said.
That has the potential to “exceed human capacity to identify subtle cues that the human eye and brain aren’t able to perceive,” Lehman added.
Although computers have not been “super helpful” so far, “what we’ve shown at least in tens of thousands of mammograms is the tool can actually make a very well-informed decision,” Etemadi said.
However, the study has some limitations.
Most of the tests were done using the same type of imaging equipment and the US group contained a lot of patients with confirmed breast cancers.
Crucially, the team has yet to show the tool improves patient care, said Lisa Watanabe, chief medical officer of CureMetrix, whose AI mammogram program won US approval last year.
“AI software is only helpful if it actually moves the dial for the radiologist,” she said.
Etemadi agreed that those studies are needed, as is regulatory approval, a process that could take several years.
An American scientist convicted of lying to US authorities about payments from China while he was at Harvard University has rebuilt his research lab in Shenzhen, China, to pursue technology the Chinese government has identified as a national priority: embedding electronics into the human brain. Charles Lieber, 67, is among the world’s leading researchers in brain-computer interfaces. The technology has shown promise in treating conditions such as amyotrophic lateral sclerosis and restoring movement in paralyzed people. It also has potential military applications: Scientists at the Chinese People’s Liberation Army have investigated brain interfaces as a way to engineer super soldiers by boosting
Indonesian police have arrested 13 people after shocking images of alleged abuse against small children at a daycare center went viral, sparking outrage across the nation, officials said on Monday. Police on Friday last week raided Little Aresha, a daycare center in Yogyakarta on Java island, following a report from a former employee. CCTV footage circulating on social media showed children, most younger than two, lying on the floor wearing only diapers, their hands and feet bound with rags. The police have confirmed that the footage is authentic. Police said they also found 20 children crammed into a room just 3m by 3m. “So
A highway bomb attack in a restive region of southwestern Colombia on Saturday killed 14 people and injured at least 38, the latest spate of violence ahead of next month’s presidential election. Authorities blamed the attack in the Cauca department — a conflict-ridden, coca-growing region — on dissidents of the now-disbanded FARC guerrilla army, who have been sowing violence across the country. “Those who carried out this attack ... are terrorists, fascists and drug traffickers,” Colombian President Gustavo Petro said on social media. “I want our very best soldiers to confront them,” he added. The leftist leader blamed the bombing
From post offices and parks to stations and even the summit of Mount Fuji, Japan’s vending machines are ubiquitous, but with the rapid pace of inflation cooling demand for their drinks, operators are being forced to rethink the business. Last month beverage giant DyDo Group Holdings announced it would remove about 20,000 vending machines — about 7 percent of their stock nationwide — by January next year, to “reconstruct a profitable network.” Pokka Sapporo Food & Beverage, based in Nagoya, also said last month it would sell its 40,000-machine operation to Osaka-based Lifedrink Co. “The strength of the vending machine
RSS