American magazine "Wired" reported that early research confirmed that Google's algorithm can improve the quality and accuracy of breast exams with "mammogram" x-rays.
One of every eight women will be diagnosed with breast cancer during their lifetime, according to the magazine, which is concerned with emerging technologies in the field of culture, health, and others.
In an attempt to speed up the detection process, researchers tried the deep learning algorithm to identify breast cancer in scanners with the accuracy of the radiologist herself or better.
Although the study is still in its early stages, it may eventually help reduce the results of erroneous examinations in the United States and alleviate the shortage of the number of technicians and radiologists in Britain, according to the article published by the journal for the journalist Nicole Kobe.
And according to the definition of the Wikipedia website, deep learning is a new field of research dealing with finding theories and algorithms that allow the machine to learn on its own by simulating neurons in the human body. It is one of the branches of science that deals with artificial intelligence.
Algorithms are a set of rules and orders that are implemented sequentially and orderly to solve a specific problem.
And since early detection of the disease is a key factor in treatment, women over the age of fifty are being examined in the United States and Britain even if they do not show signs of developing breast cancer.
Negative screening results can be incorrect and then the cancer may be fatal.
In cooperation with the British National Health Service, Google's DeepMind is developing artificial intelligence so that it can read retinal exams and detect neck cancer.
Researchers from the British Imperial College for Cancer Research, Northwestern University, the Syrian County Hospital Royal and the Google Medical Service used the deep learning system that DeepMind developed on two different sets of data related to breast exams, one from the United States and one from Britain.
The researchers concluded that artificial intelligence can help read mammograms X-ray images accurately.
In her article, Nicole Kobe, quoting Google Medical Service Director Dominic King, said that what had been achieved was another step in trying to answer some of the questions that are essential in presenting the results on the ground.
"This is another step that brings us closer to our endeavor to apply this type of technology safely and effectively," she said.
The study says that the AI model can predict breast cancer as accurate as an experienced radiologist. In comparison with human experts, the system was able to reduce the rates of false positive test results by 5.7% in the United States and 1.2% in Britain, and by 9.4% in relation to negative results in the United States and 2.7% in Britain.
However, these results do not necessarily reflect how such examinations are actually read.
The study indicates that the DeepMind algorithm works better than a radiologist alone, and it is not inferior compared to the performance of two of them.
Despite the success of the study in its findings, artificial intelligence cannot completely replace radiologists, but it may help them in their work, as Caroline Rubin, deputy head of the clinical radiology department at the Royal College of Radiologists, asserts.