• Laser & Optoelectronics Progress
  • Vol. 55, Issue 6, 061701 (2018)
Guoyin Ren1, Xiaoqi Lü1, Nan Yang2、*, Dahua Yu1, Xiaofeng Zhang1, and Tao Zhou1
Author Affiliations
  • 1School of Information Engineering, Inner Mongolia University of Science and Technology, Baotou, Inner Mongolia 0 14010, China
  • 2Baotou Medical College, Baotou, Inner Mongolia 0 14010, China
  • show less
    DOI: 10.3788/LOP55.061701 Cite this Article Set citation alerts
    Guoyin Ren, Xiaoqi Lü, Nan Yang, Dahua Yu, Xiaofeng Zhang, Tao Zhou. Application of Improved Voxels Growth Algorithm in Cardiac Local Vascular Extraction[J]. Laser & Optoelectronics Progress, 2018, 55(6): 061701 Copy Citation Text show less
    Flow chart of finding the edge of the voxel according to similarity table
    Fig. 1. Flow chart of finding the edge of the voxel according to similarity table
    Topology constraint diagram of voxels in blood vessels
    Fig. 2. Topology constraint diagram of voxels in blood vessels
    (a) Three-dimensional reconstruction of thoracic cavity and (b) extracted local blood vessel cluster
    Fig. 3. (a) Three-dimensional reconstruction of thoracic cavity and (b) extracted local blood vessel cluster
    Extraction of local blood vessels from cardiac local AABB bounding box
    Fig. 4. Extraction of local blood vessels from cardiac local AABB bounding box
    Segmentation results before and after the algorithm improving. (a) Before improving; (b) after improving
    Fig. 5. Segmentation results before and after the algorithm improving. (a) Before improving; (b) after improving
    SimilaritymeasureOperatingRaRbRcRdReAdjacent voxelnumbersSimilar voxelnumbers
    MeansquareerrorBeforeregistration1189.251147.691123.431114.161101.87268
    Afterregistration3487.813479.153427.483404.9733871.362617
    CorrelationcoefficientBeforeregistration0.971520.971020.967850.965480.962292612
    Afterregistration0.992410.992160.991780.990040.984592618
    MattersinformationBeforeregistration-1.02594-1.02234-1.02119-1.02101-1.020782611
    Afterregistration-1.37748-1.37536-1.37493-1.37299-1.371792615
    Table 1. Comparative evaluation for similarity measure
    FigurenumberTraditional voxels growth algorithmImproved voxels growth algorithm
    SensitivitySpecificityAccuracyKappaSensitivitySpecificityAccuracyKappa
    10.59740.74770.87850.76640.81120.90120.92140.8785
    20.63480.63360.88260.82040.81050.90160.91140.8568
    30.68520.81250.87890.73440.79290.91480.93220.8897
    40.53740.77560.86640.80100.81880.92480.94830.8924
    50.72590.79780.89970.84520.83540.93210.93240.8899
    Averagevalue0.63480.84890.83470.83270.81370.91240.92470.8814
    Table 2. Segmentation accuracy evaluation
    Algorithms andattributesSize of boundingbox (x, y, z)Number of voxelsin volumeNumber ofvoxels on surfaceVoxels growth timeinside model /sVoxels growthtime of surface /s
    Automatic voxelsgrowth algorithm(28, 40, 23)266252957103.895.83
    Semi-automatic voxelsgrowth algorithm(3, 5.3, 2)31523455.591.46
    Improved voxelsgrowth algorithm(3, 5.3, 2)31523453.781.12
    Table 3. Voxel growth evaluation before and after algorithm improving
    Guoyin Ren, Xiaoqi Lü, Nan Yang, Dahua Yu, Xiaofeng Zhang, Tao Zhou. Application of Improved Voxels Growth Algorithm in Cardiac Local Vascular Extraction[J]. Laser & Optoelectronics Progress, 2018, 55(6): 061701
    Download Citation