Selected article for: "AUC value and ROC curve"

Author: Chuansheng Zheng; Xianbo Deng; Qing Fu; Qiang Zhou; Jiapei Feng; Hui Ma; Wenyu Liu; Xinggang Wang
Title: Deep Learning-based Detection for COVID-19 from Chest CT using Weak Label
  • Document date: 2020_3_17
  • ID: ll4rxd9p_37
    Snippet: To our knowledge, this is the first study to perform weakly-supervised computer-aided COVID-19 detection with a large number of CT volumes from the frontline hospital at the present epidemic period. By designing an effective weakly-supervised deep learning-based algorithm and training it on CT volumes collected before Jan 23, 2020 with only patient-level labels, the testing results on 131 CT scans collected from Jan 24, 2020, to Feb 6, 2020, were.....
    Document: To our knowledge, this is the first study to perform weakly-supervised computer-aided COVID-19 detection with a large number of CT volumes from the frontline hospital at the present epidemic period. By designing an effective weakly-supervised deep learning-based algorithm and training it on CT volumes collected before Jan 23, 2020 with only patient-level labels, the testing results on 131 CT scans collected from Jan 24, 2020, to Feb 6, 2020, were very impressive, e.g., the PR AUC value was 0.975. On the ROC curve, the algorithm obtained sensitivity and specificity values larger than 0.9, which were both clinically applicable.

    Search related documents:
    Co phrase search for related documents