echemi logo
Product
  • Product
  • Supplier
  • Inquiry
    Home > Medical News > Medical World News > Several hospitals jointly launched novel coronavirus pneumonia CT image AI qualitative diagnosis system

    Several hospitals jointly launched novel coronavirus pneumonia CT image AI qualitative diagnosis system

    • Last Update: 2020-02-24
    • Source: Internet
    • Author: User
    Search more information of high quality chemicals, good prices and reliable suppliers, visit www.echemi.com
    The novel coronavirus pneumonia affects every citizen's heart How to use artificial intelligence technology to help hospitals cope with the epidemic? On January 28, on the fourth day of the lunar new year, Wang Yongjun, executive vice president of Tiantan Hospital, and he Kunlun, vice president of PLA General Hospital jointly initiated the task of "new coronavirus pneumonia CT image Artificial Intelligence Aided Diagnosis" by the Ministry of industry and information technology After receiving the task of "new coronavirus pneumonia CT image Artificial Intelligence Aided Diagnosis" by the Ministry of industry and information technology, using the strong technical force of the artificial intelligence research center of Tiantan Hospital, the task of "new generation artificial intelligence industry innovation key task" by the Ministry of industry and information technology was unveiled Beijing ande Medical Intelligence Technology Co., Ltd immediately organized and launched scientific research At present, biomind "new crown" pneumonia CT image AI qualitative auxiliary diagnosis system (hereinafter referred to as "new crown" Ai qualitative diagnosis system) has been launched, which is jointly developed by more than 30 designated treatment hospitals and put into use in succession The novel coronavirus pneumonia diagnostic system is jointly launched by Tiantan hospital, PLA General Hospital and BioMind It is the AI diagnostic system for the real industry and the new AI pneumonia The novel coronavirus pneumonia is novel coronavirus pneumonia because the new AI diagnostic system can not only achieve "pneumonia diagnosis" but also further differentiate the new crown pneumonia from other pneumonia (viral pneumonia, bacterial pneumonia, etc.) The novel coronavirus pneumonia system only needs ten seconds, and the coincidence rate between the diagnosis results of new crown pneumonia and the positive results of nucleic acid detection is over 95.5% Example of interface of biomind "new crown" Ai qualitative diagnosis system "This system is a real case from the front line of the epidemic, and then applied to the AI system of the front line of the epidemic." According to Wu Zhenzhou, technical director of the artificial intelligence research center of Tiantan Hospital, the early research and development includes Wuhan Jinyintan hospital, Wuhan Third Hospital, Suizhou Central Hospital, Xiantao first people's Hospital, Wuhan Red Cross Hospital, Wuhan fifth hospital, Wuhan Wuchang hospital, Wuhan Jiangxia first people's Hospital, Wuhan Huangpi people's Hospital, Wenzhou City More than 30 designated hospitals such as central hospital participated in the treatment There is no love or affection Its R & D process has been greatly supported by relevant leaders of the Ministry of industry and information technology and the Department of science and technology, Beijing Municipal Bureau of economy and information technology and the software department At present, the system has been open to all designated hospitals in China for free Any designated hospital can contact the Ministry of industry and information technology system or biomind directly, and will give free deployment as soon as possible Both software and hardware work in the hospital, and the data will not be discharged, so as to ensure patient privacy and medical data security The National Health Council novel coronavirus pneumonia diagnosis and treatment plan includes CT imaging as one of the diagnostic criteria With the development of the situation of epidemic prevention and control, a large number of suspected cases appear, and the explosive demand makes the front-line doctors overwhelmed Novel coronavirus pneumonia novel coronavirus pneumonia is a new method for rapid identification and diagnosis of new crown pneumonia because of its high false negative rate and difficult image identification The novel coronavirus pneumonia CT imaging is a significant step in the early diagnosis, early isolation and early treatment, "said Ma Lin, director of the radiology department of the General Hospital of the PLA." in this situation, how to make use of AI to identify the new crown pneumonia's image is of great importance The novel coronavirus pneumonia novel coronavirus pneumonia is not easy to identify The imaging findings of new crown pneumonia are also specific, but it is not easy to distinguish the new crown pneumonia from the common pneumonia only from the imaging point of view, said Fan Yanqing, director of the radiology department of Wuhan golden Yin hospital "If we only do simple pneumonia screening, the clinical value is still limited Our goal is to novel coronavirus pneumonia Wu Zhenzhou said that novel coronavirus pneumonia and other pneumonia were laid down by the technical superiority of being good at multiple diseases synchronous analysis "Why do we have confidence in our ability to analyze multiple diseases simultaneously?" According to Li Jingjue, CEO of biomind in China, earlier, biomind took the lead in the world in the qualitative diagnosis of more than 60 kinds of nervous system diseases (brain tumors, small vessel diseases, middle cerebral apoplexy), more than 10 kinds of heart diseases, and 8 kinds of breast diseases The accuracy rate of diagnosis is more than 90%, and that of some diseases is more than 96% Novel coronavirus pneumonia diagnostic system based on novel coronavirus pneumonia is not only a qualitative diagnosis of new crown pneumonia but also a classification diagnosis of various pneumonia (new crown pneumonia, other viral pneumonia, bacterial pneumonia, fungal pneumonia) and so on AI is a new diagnostic system Wu Zhenzhou stressed, "this is unique in the industry There are essential differences between screening detection and simultaneous analysis of multiple diseases and qualitative diagnosis, both in technical difficulty and clinical significance " At the same time, the clinical application of this system can fully cover the whole clinical cycle of early diagnosis, treatment evaluation and follow-up "Data is the foundation of medical AI products This is even more true under the epidemic " Wu Zhenzhou said that novel coronavirus pneumonia patients with positive nucleic acid tests (the standard of etiological diagnostic gold) were collected from the multi center and more than 30 designated hospitals for treatment during the research and development process More than 20000 cases of other pneumonia data were confirmed by clinical diagnosis, which constituted a high-quality data set and analyzed the synchronization of multiple diseases "To undertake glorious mission in special period, we should take more responsibility We should never neglect the quality of R & D data because of urgent task." Wu Zhenzhou said that the research and development of medical AI is highly dependent on data quality, which directly determines the product value Wu Zhenzhou introduced the novel coronavirus pneumonia CT image data to strict quality control, while marking the team from the PLA General Hospital dozens of top experts In other words, AI itself cannot exist independently Only through high-quality data learning and the combination of application scenarios, can AI be "smart" Liu Yaou, executive deputy director of Radiology Department of Tiantan Hospital (presided over the work), said, "only by checking the quality from the data source can we have the premise of real clinical value." "We will never fight a war without preparation The whole team is well prepared for the task." Wu Zhenzhou said that this time, the most capable R & D backbone was mobilized, and the system comprehensively covered the complete clinical cycle of early diagnosis, treatment evaluation and follow-up Specifically, it mainly includes the following functions: First, the novel coronavirus pneumonia can detect early milking signs and other grim shadows of millimeter grade new crown pneumonia The novel coronavirus pneumonia differential diagnosis accuracy rate (the coincidence rate of positive results with nucleic acid test) can reach more than 95.5% based on the sensitivity of pneumonia detection to nearly 100% Secondly, the "intelligent quantitative analysis" function realizes accurate quantitative analysis and dynamic evaluation of lesions, provides quantitative indicators and timely risk early warning for the progress of the disease, assists imaging doctors to judge the stage of lesions and the severity of the disease, and provides basis for clinical timely targeted treatment At the same time, the "intelligent follow-up" function can quickly realize the automatic transfer of multiple image examinations and accurate registration and analysis of lesions, assist doctors to quickly make a series of important work, such as treatment effect evaluation, pre discharge evaluation of patients and post discharge rehabilitation follow-up With the deepening of the outbreak, the number of cured patients will continue to increase, "intelligent follow-up" function will provide rich and accurate indicators for accurate monitoring of treatment outcome, close observation of patients' prognosis, evaluation of lung structure and function damage Real clinical scenario application example of biomind "new crown" Ai qualitative diagnosis system Novel coronavirus pneumonia is still the gold standard for diagnosis of new crown pneumonia, but there is a short negative plate that can be positive and negative, which increases the risk of infection CT + AI can quickly diagnose and gain valuable time for epidemic prevention and control "Under the epidemic, time is life CT + AI must be an indispensable and effective tool for epidemic prevention and control " Li said Secondly, the efficiency improvement brought by AI can help reduce the waiting time of patients as much as possible If patients wait in line for examination and results in the hospital for a long time, the risk of cross infection is huge CT + AI can carry out depth interpretation and second level operation of CT image through depth learning, and the time for issuing the report has accelerated from dozens of minutes to a few minutes.
    This article is an English version of an article which is originally in the Chinese language on echemi.com and is provided for information purposes only. This website makes no representation or warranty of any kind, either expressed or implied, as to the accuracy, completeness ownership or reliability of the article or any translations thereof. If you have any concerns or complaints relating to the article, please send an email, providing a detailed description of the concern or complaint, to service@echemi.com. A staff member will contact you within 5 working days. Once verified, infringing content will be removed immediately.

    Contact Us

    The source of this page with content of products and services is from Internet, which doesn't represent ECHEMI's opinion. If you have any queries, please write to service@echemi.com. It will be replied within 5 days.

    Moreover, if you find any instances of plagiarism from the page, please send email to service@echemi.com with relevant evidence.