Google AI System Could Improve Breast Cancer Detection
2020-01-07
LRC
TXT
大字
小字
滚动
全页
1A Google artificial intelligence system was as good as expert radiologists at discovering which women had breast cancer in a new study.
2The system made the findings from thousands of mammogram images, researchers in the United States and Britain reported.
3This is the newest study to show that artificial intelligence, or AI, may improve the accuracy of mammograms.
4Breast cancer affects one in eight women around the world.
5The study was published in the journal Nature.
6The American Cancer Society says radiologists miss about 20 percent of breast cancers in mammograms.
7And many women who get the tests have a false positive result at some point.
8A false positive result shows a woman with cancer even though she does not have it.
9The findings of the study were developed with DeepMind AI, which joined with Google Health in September.
10The study results represent a big step toward the possibility of early breast cancer detection, said Mozziyar Etemadi.
11He is one of the study writers and based at Northwestern Medicine in Chicago.
12The team included researchers at Imperial College London and Britain's National Health Service.
13Together, they trained the AI system to identify breast cancers on tens of thousands of mammograms.
14They then compared the AI system's performance with the actual results from a set of 25,856 mammograms in the United Kingdom and 3,097 from the United States.
15The study showed the AI system could identify cancers with a similar level of accuracy to expert radiologists.
16At the same time, it reduced the number of false positive results by 5.7 percent in the American patients and 1.2 percent in the British patients.
17It also cut the number of false negatives, where tests are wrongly listed as normal, by 9.4 percent in the American group, and 2.7 percent in the British group.
18These results show differences in how mammograms are read.
19In the U.S., only one radiologist reads the results and the tests are done every one to two years.
20In Britain, the tests are done every three years, and each is read by two radiologists.
21When they disagree, a third radiologist reads it.
22In a separate test, the researchers put the AI system against six radiologists and found it performed better at correctly detecting breast cancers.
23Connie Lehman is chief of the breast imaging department at Harvard's Massachusetts General Hospital.
24She said the results agree with findings from many groups using AI to improve cancer detection in mammograms, including her own work.
25The idea of using computers to improve cancer detection has been around for years.
26And computer-aided detection or CAD systems are common in mammography health centers, but CAD has not improved performance in health practice.
27The issue, Lehman said, is that current CAD programs were trained to identify things human radiologists can see.
28But with AI, computers learn to find cancers based on the actual results of thousands of mammograms.
29So AI has the possibility of going beyond human ability to identify small signs the human eye and brain cannot.
30Mozziyar Etemadi added that the study has shown, in tens of thousands of mammograms, that AI can "make a very well-informed decision."
31The study has some limitations.
32Most of the tests were done using the same type of imaging equipment, and the U.S. group had a lot of patients with confirmed breast cancers.
33Importantly, the team has not yet shown that the tool improves patient care, said Dr. Lisa Watanabe.
34She is chief medical officer of CureMetrix, a company whose AI mammogram program won U.S. approval last year.
35She noted that AI is only helpful if it creates noticeable progress for radiologists.
36Etemadi agreed that those studies are needed, as is regulatory approval, a process that could take many years.
37I'm Alice Bryant.
1A Google artificial intelligence system was as good as expert radiologists at discovering which women had breast cancer in a new study. The system made the findings from thousands of mammogram images, researchers in the United States and Britain reported. 2This is the newest study to show that artificial intelligence, or AI, may improve the accuracy of mammograms. Breast cancer affects one in eight women around the world. The study was published in the journal Nature. 3The American Cancer Society says radiologists miss about 20 percent of breast cancers in mammograms. And many women who get the tests have a false positive result at some point. A false positive result shows a woman with cancer even though she does not have it. 4The findings of the study were developed with DeepMind AI, which joined with Google Health in September. 5The study results represent a big step toward the possibility of early breast cancer detection, said Mozziyar Etemadi. He is one of the study writers and based at Northwestern Medicine in Chicago. 6The team included researchers at Imperial College London and Britain's National Health Service. Together, they trained the AI system to identify breast cancers on tens of thousands of mammograms. 7They then compared the AI system's performance with the actual results from a set of 25,856 mammograms in the United Kingdom and 3,097 from the United States. 8The study showed the AI system could identify cancers with a similar level of accuracy to expert radiologists. At the same time, it reduced the number of false positive results by 5.7 percent in the American patients and 1.2 percent in the British patients. 9It also cut the number of false negatives, where tests are wrongly listed as normal, by 9.4 percent in the American group, and 2.7 percent in the British group. 10These results show differences in how mammograms are read. In the U.S., only one radiologist reads the results and the tests are done every one to two years. In Britain, the tests are done every three years, and each is read by two radiologists. When they disagree, a third radiologist reads it. 11Seeing the signs 12In a separate test, the researchers put the AI system against six radiologists and found it performed better at correctly detecting breast cancers. 13Connie Lehman is chief of the breast imaging department at Harvard's Massachusetts General Hospital. She said the results agree with findings from many groups using AI to improve cancer detection in mammograms, including her own work. 14The idea of using computers to improve cancer detection has been around for years. And computer-aided detection or CAD systems are common in mammography health centers, but CAD has not improved performance in health practice. 15The issue, Lehman said, is that current CAD programs were trained to identify things human radiologists can see. But with AI, computers learn to find cancers based on the actual results of thousands of mammograms. So AI has the possibility of going beyond human ability to identify small signs the human eye and brain cannot. 16Mozziyar Etemadi added that the study has shown, in tens of thousands of mammograms, that AI can "make a very well-informed decision." 17A few limitations 18The study has some limitations. Most of the tests were done using the same type of imaging equipment, and the U.S. group had a lot of patients with confirmed breast cancers. 19Importantly, the team has not yet shown that the tool improves patient care, said Dr. Lisa Watanabe. She is chief medical officer of CureMetrix, a company whose AI mammogram program won U.S. approval last year. 20She noted that AI is only helpful if it creates noticeable progress for radiologists. 21Etemadi agreed that those studies are needed, as is regulatory approval, a process that could take many years. 22I'm Alice Bryant. 23Reuters News Service reported this story. Alice Bryant adapted it for Learning English. Hai Do was the editor. 24_______________________________________________________________ 25Words in This Story 26radiologist - n. a doctor whose expertise is using some forms of radiation (such as X-rays) to diagnose and treat diseases 27mammogram - n. a photograph of a woman's breasts made by X-rays 28accuracy - n. the quality of having no errors or mistakes 29detection - n. the act or process of discovering, finding, or noticing something 30false positive - n. a test result which incorrectly indicates that a particular condition is present 31false negative - n. a test result which incorrectly indicates that a particular condition is absent