echemi logo
Product
  • Product
  • Supplier
  • Inquiry
    Home > Medical News > Medical Science News > Tencent Healthcare has teamed up with Microbank to set up a joint laboratory to learn how to solve privacy problems.

    Tencent Healthcare has teamed up with Microbank to set up a joint laboratory to learn how to solve privacy problems.

    • Last Update: 2020-09-29
    • Source: Internet
    • Author: User
    Search more information of high quality chemicals, good prices and reliable suppliers, visit www.echemi.com
    Guide: The two sides will jointly attack medical federal learning, explore intelligent applications in the medical field. On August 21, 2020, Tencent Healthcare and Microbank announced the establishment of a joint laboratory, combining Tencent Tianying Laboratory's technology accumulation in medical imaging, medical machine learning and natural language processing, as well as the leading technology of microbank AI team in federal learning.
    Tencent Vice President of Medical Dr. Wenda Wu pointed out that the medical scene data privacy issues are very important to deal with, technological progress to bring innovation to medical care at the same time, but also to take into account privacy protection, so that the industry to win a healthy development, so that users have access to a convenient and safe environment to use.
    's federal learning framework for medical privacy and data security has brought new solutions, the establishment of joint laboratories will help both sides to focus on technological advantages, deep into the application of medical federal learning, and break through the AI-medical innovation technology landing problems.
    Federal learning not only protects the data privacy of different institutions, but also enhances the efficiency of machine learning Microbank AI team is a leader in federal learning technology, and the driving force of micro-bank AI team to lead the "federal learning" research and apply it to the business is Professor Yang Qiang, chief artificial intelligence officer of micro-bank, he is also one of the first international AI experts to study "federal learning."
    Professor Yang Qiang said that the principle of federal learning is an encrypted distributed machine learning technology, the participants can not disclose the underlying data and the underlying data encryption (confusion) form of the model, but also a win-win machine learning method.
    "Federal Learning" allows multiple participants to collaborate without revealing privacy locally, while "migration learning" is a way to move "knowledge" learned from existing issues to new issues, and "federal migration learning" is a combination of "migration learning" and "federal learning" to help different institutions break down barriers, jointly build AI models, and the data is not local, user privacy is best protected.
    micro-banking has been in the financial, medical and other industries to apply new technology.
    Joint Laboratory, the two sides will continue to pool their strengths and resources, focusing on medical imaging-assisted diagnosis, medical big data, medical machine learning models and other aspects of in-depth cooperation, the two sides will study in the protection of multi-party (such as hospitals, enterprises, etc.) data collaborative learning, so as to break the limits of data silos.
    particularly, the medical federal learning framework is expected to be a "good solution" to the problem during an outbreak when many AI technologies are unable to be implemented due to the absolute privacy of patient data.
    Professor Yang Qiang of Microbank said that based on the joint laboratory cooperation project of big data and artificial intelligence, the joint laboratory will actively explore the tracking, diagnosis and prognosis of new corona pneumonia under the framework of medical federal learning, for example, in the normal examination of the epidemic and the source of the disease, to explore whether the user is at risk of infection in the case of protecting the privacy of users and to be indicated in both green code and red code.
    In addition, The Joint Laboratory will create a federal learning framework-based diagnostic model for CT images of new coronary pneumonia, allowing hospitals around the world to learn together and model together without revealing privacy, thereby greatly improving the diagnostic accuracy of hospitals with scarce cases.
    At the same time, medical federal learning as a basic technical framework, can tap and use medical health data, build different medical scenario applications, such as through federal learning to help e-health card to protect user privacy modeling, health insurance fund fees, personal and institutional denial of payment identification, etc., to help the medical and health industry development, improve the quality of medical services.
    last year, Tencent Tianying Laboratory and Microbank cooperated in the fields of medical big data, medical imaging-assisted diagnosis, and effectively improved the efficiency of medical workers through the transformation of AI technology.
    Joint Laboratory Researchers Zhao Ruihui and Zhu Ze jointly developed a "stroke risk prediction model" based on the medical federal learning framework, which successfully solves the medical industry's information silos and privacy challenges, enabling accurate prediction of diseases under the protection of data privacy in different hospitals, with an accuracy rate of up to 80%.
    addition, through federal learning techniques, data resources for large triple-A hospitals can help smaller hospitals with fewer cases of lack of medical services improve their model forecasts by 10-20%.
    the work in the form of a paper (paper link:) and was FL-IJCAI'20 high score.
    , the work won Tencent's Top 10 Micro-Innovation Projects Award.
    Dr. Zheng Yefeng, head of Tencent Tianying Laboratory, pointed out that the establishment of a joint laboratory between the two sides will help accelerate the research and application of federal learning technology in the medical field, especially in the post-epidemic era, the medical field of AI and big data and other technologies application transformation demand surge, I hope that the two sides can further accelerate the breakthrough of medical innovation technology, and effectively enhance the development of AI medical business.
    .
    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.