AI helps breast cancer screening
a19: today's health
AI helps breast cancer screening
more than 10 third tier hospitals across the country have entered clinical pilot trials
information times (Xie Jingjing) "Ai + medical" is a blue ocean field to be developed. Recently, "Tencent search" officially released the breast cancer screening AI system, Announced the first time in China to use artificial intelligence to distinguish benign and malignant breast tumors, and automatically generate breast image reports and data system (BI RADS) classification reports. It is reported that at present, "seek shadow" has entered the clinical pre-trial in more than 10 third-class hospitals across the country. In the future, it is expected that early screening, early diagnosis and early treatment of breast tumors will facilitate the accurate selection and adjustment of detection points; The test space plays a greater role
the younger incidence of breast cancer, the early screening of initial diagnosis is the key
"due to the dietary habits tend to be high-fat and oily, the increased pressure of life and work, and the increase of active and passive smoking, the growth rate of breast cancer incidence rate in China in recent years is in the forefront of the world, especially in Beijing, Shanghai, Guangzhou and other cities incidence rate, which is close to the high incidence level of developed countries in Europe and the United States." Professor lvweiming, director of thyroid and breast surgery of the First Affiliated Hospital of Sun Yat sen University, pointed out that breast cancer patients in China have the characteristics of early onset age and late treatment period. The average age of onset of female breast cancer is about 10 years younger than that of European and American countries, and the peak age of onset is 45 to 55 years old. Due to their insufficient attention and lack of effective screening, the stage of domestic breast cancer at the initial diagnosis is late
lvweiming said that mammography is a common breast tumor screening method at home and abroad. Doctors need to spend a lot of energy on multi image comparison diagnosis. In the case of dense breast glands, which often lead to damage to machine abundance, accurately identifying glands and lesions is a big challenge for the theme index of China Securities founder Fubang insurance to be customized by founder Fubang Fund Management Co., Ltd. The emergence of artificial intelligence medical image analysis technology brings a problem-solving idea for mammography
it is reported that the "seeking shadow" jointly developed by Tencent and the First Affiliated Hospital of Sun Yat sen University, Sun Yat Sen Memorial Hospital of Sun Yat sen University, Guangdong Provincial Hospital of traditional Chinese medicine, Guangdong maternal and child health hospital and Guangdong Second People's hospital has entered clinical pilot trials in Guangdong Second people's Hospital and more than 10 other third-class hospitals across the country. Experts said that it will help clinicians find breast tumors more accurately and efficiently, improve the diagnosis level of early breast cancer in grass-roots hospitals, and help patients obtain medical services of early screening, early diagnosis and early treatment
difficult cases + expert argumentation improve the efficiency of "watching films"
it is reported that the "shadow seeking" breast tumor screening AI system enhances the resolution of difficult cases through a large number of multi center data learning and expert argumentation and annotation
compared with traditional naked eye screening, this system has achieved two major breakthroughs: first, the traditional mammography requires doctors to observe the patient's breast image, and then diagnose the condition according to their own experience. "Shadow finding" can even turn into other failure situations to automatically identify and locate suspicious lesions, mark the location of tumor foci and calcification foci, and help doctors quickly find suspicious points. Secondly, it can further distinguish the risk degree of benign and malignant tumors, and automatically generate breast image reports and data system (BI RADS) classification reports. AI technology cooperates with doctors, which greatly improves the efficiency of doctors' viewing films and reduces the occurrence of "missed diagnosis"
according to the test statistics of large samples, non homologous and multi center, the sensitivity of "shadow seeking" breast tumor screening AI system to detect breast calcification and malignant tumors reached 99% and 90.2% respectively, and the sensitivity and specificity of benign and malignant breast tumors were 87% and 96% respectively
Copyright © 2011 JIN SHI