登录
 机构网站
  1. 首页
  2. 情报产品
  3. 快讯详情

《MedRixv，3月1日，（第2版更新）Deep learning-based model for detecting 2019 novel coronavirus pneumonia on high-resolution computed tomography: a prospective study》

  • 来源专题：COVID-19科研动态监测
  • 编译者： zhangmin
  • 发布时间：2020-03-02

  • Deep learning-based model for detecting 2019 novel coronavirus pneumonia on high-resolution computed tomography: a prospective study

    Jun Chen, Lianlian Wu, Jun Zhang, Liang Zhang, Dexin Gong, Yilin Zhao, Shan Hu, Yonggui Wang, Xiao Hu, Biqing Zheng, Kuo Zhang, Huiling Wu, Zehua Dong, Youming Xu, Yijie Zhu, Xi Chen, Lilei Yu, Honggang Yu

    doi: https://doi.org/10.1101/2020.02.25.20021568

    Abstract

    Background: Computed tomography (CT) is the preferred imaging method for diagnosing 2019 novel coronavirus (COVID19) pneumonia. Our research aimed to construct a system based on deep learning for detecting COVID-19 pneumonia on high resolution CT, relieve working pressure of radiologists and contribute to the control of the epidemic. Methods: For model development and validation, 46,096 anonymous images from 106 admitted patients, including 51 patients of laboratory confirmed COVID-19 pneumonia and 55 control patients of other diseases in Renmin Hospital of Wuhan University (Wuhan, Hubei province, China) were retrospectively collected and processed.

    *注，本文为预印本论文手稿，是未经同行评审的初步报告，其观点仅供科研同行交流，并不是结论性内容，请使用者谨慎使用.

  • 原文来源：https://www.medrxiv.org/content/10.1101/2020.02.25.20021568v2
15浏览量
原文链接
相关报告

  • 《MedRixv，2月10日，（第2版更新）Transmission and epidemiological characteristics of Novel Coronavirus (2019-nCoV)-Infected Pneumonia(NCIP):preliminary evidence obtained in comparison with 2003-SARS》
    • 来源专题：COVID-19科研动态监测
    • 编译者：zhangmin
    • 发布时间：2020-02-11
    • Transmission and epidemiological characteristics of Novel Coronavirus (2019-nCoV)-Infected Pneumonia(NCIP):preliminary evidence obtained in comparison with 2003-SARS Rongqiang Zhang, Hui Liu, Fengying Li, Bei Zhang, Qiling Liu, Xiangwen Li, Limei Luo doi: https://doi.org/10.1101/2020.01.30.20019836 Abstract [Abstract] Objectives Latest epidemic information of Novel Coronavirus (2019-nCoV)-Infected Pneumonia (NCIP) was collected and a detailed statistical analysis was carried out to make comparison with 2003-SARS in order to provide scientific reference for the prevention and control of 2019-nCoV. Methods The information of NCIP and 2003-SARS from websites of NHCPRC and the World Health Organization was collected, and then the transmission dynamics of the two kinds of infectious diseases were analyzed. The information of 287 confirmed NCIP patients obtained from the website of health committees of 16 provinces. A descriptive epidemiological analysis method was employed to carefully analyze the epidemic characteristics. Subsequently, the NCIP epidemic data in Wuhan and other inland regions of China was analyzed separately and compared. A multivariate function model was constructed based on the confirmed NCIP case data. Results The growth rate of new cases and deaths of NCIP were significantly faster than those of 2003-SARS. The number of confirmed cases in Wuhan and other inland areas both showed increasing trends. 287 confirmed NCIP cases aged 9 months to 90 years and the average age was (42.38 ±15.97) years. The gender ratio (M: F) was 1.35: 1. The numbers of NCIP patients in Wuhan and other inland areas were in line with Y=0.7209 x3-11.97x2+59.129x (R2=0.9858) and Y=2.2169 x3-39.74x2+158.88x (R2=0.9357)，respectively, with good fitting effects judging by their R2 values. Conclusions The fatality rate of NCIP is lower than that of 2003-SARS and the cure rate is higher. The age of NCIP patients is mainly concentrated in the 30-50 years old (68.29%). The harm of the first-generation NCIP patients is indeed higher than that of secondary cases. *注，本文为预印本论文手稿，是未经同行评审的初步报告，其观点仅供科研同行交流，并不是结论性内容，请使用者谨慎使用.
    48浏览量
    原文链接

  • 《MedRixv，3月3日，Machine learning-based CT radiomics model for predicting hospital stay in patients with pneumonia associated with SARS-CoV-2 infection: A multicenter study》
    • 来源专题：COVID-19科研动态监测
    • 编译者：zhangmin
    • 发布时间：2020-03-04
    • Machine learning-based CT radiomics model for predicting hospital stay in patients with pneumonia associated with SARS-CoV-2 infection: A multicenter study Xiaolong Qi, Zicheng Jiang, QIAN YU, Chuxiao Shao, Hongguang Zhang, Hongmei Yue, Baoyi Ma, Yuancheng Wang, Chuan Liu, Xiangpan Meng, Shan Huang, Jitao Wang, Dan Xu, Junqiang Lei, Guanghang Xie, Huihong Huang, Jie Yang, Jiansong Ji, Hongqiu Pan, Shengqiang Zou, Shenghong Ju doi: https://doi.org/10.1101/2020.02.29.20029603 Abstract Abstract Objectives To develop and test machine learning-based CT radiomics models for predicting hospital stay in patients with pneumonia associated with SARS-CoV-2 infection. Design Cross-sectional Setting Multicenter Participants A total of 52 patients with laboratory-confirmed SARS-CoV-2 infection and their initial CT images were enrolled from 5 designated hospitals in Ankang, Lishui, Zhenjiang, Lanzhou, and Linxia between January 23, 2020 and February 8, 2020. *注，本文为预印本论文手稿，是未经同行评审的初步报告，其观点仅供科研同行交流，并不是结论性内容，请使用者谨慎使用.
    12浏览量
    原文链接