AI detects 20% more breast cancer cases than experienced doctors – study
[ad_1]
Artificial intelligence detected more cases of breast cancer than doctors with years of experience. AI has also almost halved the workload of doctors who were engaged in deciphering mammograms of patients with early stages of cancer, reports CNN with reference to a study published in the journal The Lancet Oncology. However, this does not mean that in the near future it will be a computer, and not a doctor, who will establish an oncodiagnosis. Although research shows that artificial intelligence is safe to use to detect breast cancer, and it can make the work of doctors even more efficient. Photo: agsandrew/Depositphotos Researchers looked at mammograms of more than 80,000 women in Sweden who underwent the study from April 2021 to July 2022. Half of the mammograms were “read” by AI before the doctor’s analysis. The other half was examined by two doctors without the use of AI. All doctors participating in the study were considered to be very experienced. The group where the scans were read by a radiologist with AI detected 20% more cancers than the group where the mammograms were read by two radiologists without additional technical assistance. Overall, the AI-assisted screenings led to cancer detection in 6 cases per 1,000 women screened, compared to 5 per 1,000 with the standard approach. The group that used AI had an additional advantage: a 44% reduction in the burden on doctors. The researchers estimated that if radiologists read about 50 mammograms per hour, it would take one radiologist four to six months less to read about 40,000 screening exams with AI than it would take two radiologists. “The greatest potential of artificial intelligence at this time is that it can allow radiologists to be less burdened by excessive reading,” said study co-author Dr. Kristina Long, an associate professor of diagnostic radiology at Lund University in Sweden. According to the Radiological Society of North America, there is a shortage of radiologists in Europe and the United States. If further research shows that the AI technology actually works, it could help alleviate some of the staffing problems as well as increase the efficiency of radiologists. Demand for radiologists is expected to increase as the world’s population ages and requires even more research. Many radiologists see these possibilities as good news, not as a threat to their work. “Our goal is to use mammography to detect breast cancer as early as possible to give each patient the best prognosis,” said Dr. Stamatia Destounis, a radiologist who specializes in breast imaging at Elizabeth Wende Breast Care in Rochester, New York, and who did not participate in this study. Any technology that can help with breast screening can make a big difference According to the American Cancer Society, the incidence of breast cancer is increasing by 0.5% per year, although there is no corresponding increase in the number of deaths. Although breast cancer is still the No. 2 killer of women who die from cancer, second only to lung cancer, more women are surviving than decades ago, largely because of effective screening. When breast cancer is detected at an early stage, a person’s chances of survival increase significantly. However, mammography is not perfect, experts say. This is a very subjective study. According to the National Cancer Institute, screening mammograms miss about 20% of breast cancers. Detecting the complex structure of breast cancer is extremely difficult, even after many years of specialized training. In fact, the radiologist must detect the tumor in the middle of a white background. “Artificial intelligence may one day help with this detection, but the radiologist’s job is much more than pattern recognition,” said Dr. Laura Hickok, a breast radiologist at NYU Langone Perlmutter Cancer Center, who was not involved in the new study. . Radiologists already use a relatively crude type of computerized image analysis called CAD, developed in the 1990s, which can recognize patterns in mammograms. According to Laura Hickok, the AI model looks at images differently than the human eye, is trained on different material, and can make different predictions based on what it can see and what it can’t. Although artificial intelligence is still a developing technology, artificial intelligence has begun to capture the imagination of scientists. It is used for drug discovery and development and helps doctors communicate better with patients. Several artificial intelligence programs are also being developed to help doctors detect cancer. One program at MIT was created to detect high risk of future breast cancer based on current mammograms, something doctors can’t do now. Many of these programs are real prospects, according to Hickok. We will remind you that mammography is a method of early diagnosis of mammary gland pathology, which allows you to detect tumors from 0.3 cm with a probability of 75-95%. Previously, “UP.Zhyttia” told how to detect breast cancer in the early stages. Read also: WHO urged caution in using artificial intelligence in the field of health care
[ad_2]
Original Source Link
