Selected article for: "ground truth and lung segmentation"

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_15
    Snippet: Preprocessing of 2D UNet All the CT volumes were preprocessed in a unified manner before training the 2D UNet for lung segmentation. First, the unit of measurement was converted to the Hounsfield Unit (HU) and the value was linearly normalized from 16-bit to 8-bit (i.e., 0-255) after determining the threshold of a HU window (e.g., -1 200-600 HU). After that, all the CT volumes were resampled into a same spatial resolution (e.g., 368×368), by whi.....
    Document: Preprocessing of 2D UNet All the CT volumes were preprocessed in a unified manner before training the 2D UNet for lung segmentation. First, the unit of measurement was converted to the Hounsfield Unit (HU) and the value was linearly normalized from 16-bit to 8-bit (i.e., 0-255) after determining the threshold of a HU window (e.g., -1 200-600 HU). After that, all the CT volumes were resampled into a same spatial resolution (e.g., 368×368), by which the CT volumes could be aligned without the influence of the cylindrical scanning bounds of CT scanners. This step was applied to the obtained ground-truth lung masks as well.

    Search related documents:
    Co phrase search for related documents
    • CT scanner and HU window: 1
    • CT scanner and lung segmentation: 1
    • CT scanner and spatial resolution: 1
    • CT volume and ground truth: 1, 2, 3, 4, 5
    • CT volume and lung mask: 1, 2, 3, 4
    • CT volume and lung segmentation: 1, 2, 3, 4, 5, 6, 7, 8, 9
    • CT volume and spatial resolution: 1, 2
    • ground truth and lung mask: 1, 2, 3, 4, 5
    • ground truth and lung segmentation: 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12
    • ground truth and spatial resolution: 1, 2, 3, 4, 5
    • lung mask and spatial resolution: 1, 2
    • lung segmentation and spatial resolution: 1, 2