Chinese Journal of Lasers, Volume. 49, Issue 24, 2407207(2022)

Study on Tooth Cone Beam CT Image Reconstruction Based on Improved U-net Network

Haoxin Liu1,2,3,4, Yuanmeng Zhao1,2,3,4、*, Cunlin Zhang1,2,3,4, Fengxia Zhu1,2,3,4, and Moxuan Yang1,2,3,4
Author Affiliations
  • 1Department of Physics, Capital Normal University, Beijing 100048, China
  • 2Key Laboratory of Terahertz Optoelectronics, Ministry of Education, Beijing 100048, China
  • 3Beijing Key Laboratory for Terahertz Spectroscopy and Imaging, Beijing 100048, China
  • 4Beijing Advanced Innovation Center for Imaging Theory and Technology, Beijing 100048, China
  • show less
    Figures & Tables(10)
    Schematic diagram of U-net network[17]
    Schematic diagram of spatial attention mechanism module[21]
    Schematic diagram of improved U-net network
    Names of vertices and edges of voxel elements from isosurface extraction and 14 topological structures[22]
    Using Labelme to annotate datasets
    MIoU parameters of U-net models
    Recognition results of U-net models. (a) Images to be recognized; (b) recognition results using original U-net model; (c) recognition results using improved U-net model
    Recognition result of image with dental fillings. (a) Image to be recognized; (b) recognition result using improved U-net model
    Reconstruction result of oral CBCT data using MicroDicom Viewer
    Reconstruction result of oral CBCT data using proposed algorithm
    Tools

    Get Citation

    Copy Citation Text

    Haoxin Liu, Yuanmeng Zhao, Cunlin Zhang, Fengxia Zhu, Moxuan Yang. Study on Tooth Cone Beam CT Image Reconstruction Based on Improved U-net Network[J]. Chinese Journal of Lasers, 2022, 49(24): 2407207

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Save article for my favorites
    Paper Information

    Category: Optical Diagnostics and Therapy

    Received: Aug. 16, 2022

    Accepted: Oct. 21, 2022

    Published Online: Dec. 19, 2022

    The Author Email: Zhao Yuanmeng (zhao.yuanmeng@cnu.edu.cn)

    DOI:10.3788/CJL202249.2407207

    Topics