On June 1, 2023, the State Food and Drug Administration announced that Tencent Miying’s product “Colon Polyp Electronic Endoscopic Image-Assisted Detection Software” was approved for marketing. This artificial intelligence-assisted detection product, which has passed the review of innovative medical devices, can help increase the polyp detection rate and assist clinicians in detecting colon polyps more efficiently and accurately, thus reducing the incidence and mortality of colon cancer.
Artificial intelligence provides real-time auxiliary reminders for clinicians
As early as 2018, Tencent Miying collaborated with the National Digestive Disease Clinical Research Center (Shanghai) to promote the application of AI technology in colon tumor screening. The study relies on the "National Colorectal Polyp Management" research project led by the National Digestive Disease Clinical Research Center (Shanghai). It is led by Professor Li Zhaoshen, academician of the Chinese Academy of Engineering and director of the Department of Gastroenterology, Changhai Hospital of Shanghai Naval Medical University, and is implemented by deputy director Professor Bai Yu. , and jointly participated with a number of tertiary hospitals.
"Colon Polyp Electronic Endoscope Image-Assisted Detection Software" needs to cooperate with colonoscopy. It imports video image signals from the video stream output by the electronic endoscope image processor, and analyzes the location of suspected polyps after deep learning algorithm analysis. Real-time marking is done in the video to remind doctors to pay attention to suspected lesions.
Clinical evaluation conducted at Zhejiang Provincial People's Hospital and Wenzhou Central Hospital using the clinical trial path showed that compared with conventional colorectal examination, colorectal endoscopy assisted by the "Colon Polyp Electronic Endoscopic Image-Assisted Detection Software" Examination can effectively increase the polyp detection rate.
According to GLOBOCAN2020 statistics, the number of new cases of colorectal cancer in my country has increased from 388,000 in 2015 to 555,000 in 2020. It is expected that by 2040, the number of new cases and deaths from colorectal cancer in my country will be nearly Multiply.
The ability of colonoscopists to detect adenomas is easily affected by technical level, fatigue level and alertness, and is closely related to individual differences among colonoscopists. The cumbersome and invasive nature of colonoscopy results in poor patient acceptance and compliance; the lack of per capita medical resources due to differences in regional economic levels and the difficulty in ensuring the quality of screening and other factors all restrict the early screening of colon tumors. Diagnosis and early treatment are promoted. Therefore, electronic endoscopy-assisted detection technologies and products based on artificial intelligence can assist doctors in accurately, real-time, and consistent detection of lesions and reduce missed diagnoses, which is especially significant for primary medical institutions that lack high-quality medical resources.
In 2018, as the builder of the national new generation artificial intelligence innovation and open platform for medical imaging, Tencent Miying participated in the construction of the professional committee on artificial intelligence for digestive endoscopy, as well as the industry specifications, technical standards and product standards for digestive endoscopy AI. and the writing of industry standards. This is the first professional committee related to artificial intelligence in the field of digestive diseases in China. As the chairman of the committee, Academician Li Zhaoshen said: "The establishment of the committee aims to gather experts in the industry, promote the standardization of the development of medical artificial intelligence, and verify the authenticity of medical AI. Clinical Value."
In 2020, Tencent Miying successfully promoted the establishment of the FG AI4H "endoscope" application working group, with Dr. Wu Jianrong as the leader of the application working group. This is also the first time that a Tencent expert has held a position in the ITU standardization working group. After five years of development, Tencent Miying's colon AI solution has achieved steady and substantial development thanks to active cross-border innovation with Shanghai Changhai Hospital and other "national teams".
This system leverages Tencent’s years of accumulated video analysis technology and image analysis advantages to help endoscopists draw a “hidden map” of the human digestive tract and accurately locate the coordinates of polyps. At the same time, the multi-center cooperation form of multi-industry experts and multi-hospital cooperation not only improves the quality of hospital image annotation, but also promotes the solution to the two major bottlenecks of the domestic lower gastrointestinal tract AI-assisted diagnosis system, the lack of effective training data and the lack of unified standards in the industry.
In the future, Tencent Miying will continue to lower industry thresholds by building a common technology open platform and industry-university-research cooperation platform, establish industry support systems such as technical standard systems and shared basic resource libraries, promote industry upstream and downstream cooperation, and promote the establishment of medical imaging Digital innovation in the entire application and scientific research industry promotes medical imaging AI results "from the laboratory to the bedside." At the same time, we actively respond to the construction of Digital China, accelerate the expansion and sinking of AI applications, promote the extension and expansion of high-quality medical resources to the grassroots, and accelerate the penetration of digitalization into the entire field of medical health, adding further help to solve the homogenization of my country's medical resources.
The above is the detailed content of Tencent Miying Colon AI approved for marketing to help early detection of colon cancer. For more information, please follow other related articles on the PHP Chinese website!