How efficient is artificial intelligence in screening for breast cancer?
September 06, 2016 Source: Lei Feng Net
Window._bd_share_config={ "common":{ "bdSnsKey":{ },"bdText":"","bdMini":"2","bdMiniList":false,"bdPic":"","bdStyle":" 0","bdSize":"16"},"share":{ }};with(document)0[(getElementsByTagName('head')[0]||body).appendChild(createElement('script')) .src='http://bdimg.share.baidu.com/static/api/js/share.js?v=89860593.js?cdnversion='+~(-new Date()/36e5)];
Breast cancer is a malignant tumor that occurs in the epithelial tissues of the breast gland and has been one of the terrorist killers that threaten women's health. Previously, in the screening of the disease, doctors mostly used the mammography test, but this method usually requires breast biopsy to assist, which brings unnecessary pain to women.
Â
However, through the efforts of researchers, the future AI will significantly reduce the discomfort caused by breast disease detection for women.
Today, researchers from the Houston Methodist Hospital say they have developed an AI software that is 30 times faster than a normal doctor when interpreting mammograms, and its accuracy is as high as 99%. They published the study in the cancer journal. The results show that the AI ​​software can intuitively translate X-ray images into diagnostic information, so that doctors can quickly judge the patient's condition so as not to delay the disease.
Â
In order to test the strength of this software, the R&D team engaged in a man-machine battle, and directly arranged AI X-ray images and pathological tissue section reports of 500 breast cancer patients. At the same time, the team also arranged various related medical discoveries to try to confuse AI. However, this task can not help but have the AI ​​of the wild, and within a few hours it successfully completed the task. On the other hand, the two old drivers in the breast cancer industry took 50-70 hours to get the diagnosis of 50 patients. From this we can imagine how terrible this AI software is in terms of efficiency.
Â
So why do developers think of doing this? It turned out that the cruel data shocked them. Data from the Centers for Disease Control and Prevention (CDC) and the Cancer Society show that approximately 12.1 million people in the United States receive mammograms each year, but almost half of them are suspected of being "false positives." This has caused a large number of women to receive breast biopsy (about 1.6 million per year) for peace of mind, and 20% of them are not ill at all.
Â
In addition to reducing patient suffering and saving physician time, the software can also keep rising anti-cancer costs. The National Cancer Institute predicts that by 2020, the country’s spending on cancer will reach an unprecedented $158 billion, which is an astronomical figure.
Â
According to data from the research firm Grand View, although the correct rate of biopsy results is only 60%-80%, the market size of breast biopsy equipment will reach 911 million US dollars by 2024. Researchers at Johns Hopkins University also say that the amount of money that is wasted on the simplest non-invasive breast cancer is as much as $35 million a year.
Â
The researchers are also confident in the AI ​​software, they hope that the software can better help doctors to assess the patient's condition, but also hope to reduce the pain of patient biopsy with fire eyes.
Monensin Premix
Monensin Granular,Monensin Growth Promoter,Monensin Antibiotics,Monensin Feed Additives
Shandong Shengli Bioengineering Co., Ltd , https://www.shenglipharm.com