Reuters news agency published a three-dimensional visual image of the presence of cancer hidden in the tissues of the breast, after it was discovered by the artificial intelligence system, and the agency said that this image was released by Northwestern University in Chicago on January 1, 2020.
Researchers in the United States and Britain said that a system of artificial intelligence in Google had proven similar accuracy to the accuracy of radiologists in the discovery of women who developed breast cancer based on mammograms, and showed efficiency in reducing errors.
The study, published in the journal Nature on Wednesday, is the latest research to show that AI has the potential to improve the accuracy of screening for breast cancer that affects one out of every 8 women in the world.
The American Cancer Society says that the percentage of error in radiologists in diagnosing breast cancer through X-ray imaging is 20 percent, and that half of the women who underwent examination over a 10-year period were mistakenly diagnosed with the disease.
Muzyar Etmadi, one of the participants in preparing the study from Northwestern University School of Medicine, said that the results of the study, which was developed in cooperation with the (Deep Mind) unit for Google’s artificial intelligence of Alphabet, which merged with Google Health in September, represents a significant progress in the possibility of early detection of cancer Breast.
The team, which included researchers from the Imperial College London and the National Health Service in Britain, trained the system to identify breast cancer on tens of thousands of mammograms.
They then compared the system’s expectations with the actual results for a group of 25,856 mammograms in Britain and 3,097 in the United States.
The study showed that the artificial intelligence system was able to determine the incidence of cancer with a degree similar to the accuracy of radiologists, while reducing the number of false positive results by 5.7% in the group in the United States and by 2.1% in those in Britain.
Also, the erroneous negative results, which tests were wrongly classified as normal, were reduced by 9.4% in the American group and 2.7% in the British group.
These differences reflect the methods of reading the results of mammograms. In the United States, only one x-ray expert reads the results and tests are conducted every year or two. As for Britain, the exams are conducted every 3 years, and each of them is examined by two x-ray experts. When they differ, a third expert is consulted.