Skip to main content

Advertisement

Table 3 Analysis of 4800 Random Forest segmentations with available ground truth

From: Automated quality control in image segmentation: application to the UK Biobank cardiovascular magnetic resonance imaging study

Class Acc. TPR FPR MAE
     DSC MSD RMS HD
      mm mm mm
LVC 0.968 0.997 0.330 0.042 0.906 2.514 11.09
  0.975 0.962 0.011     
LVM 0.454 0.956 0.571 0.125 0.963 2.141 11.83
  0.972 0.962 0.012     
RVC 0.868 0.957 0.352 0.057 1.140 2.790 15.23
  0.969 0.977 0.040     
Av. 0.763 0.970 0.418 0.075 1.003 2.482 12.72
  0.972 0.967 0.032     
WH 0.954 0.966 0.148 0.035 1.156 2.762 12.52
  0.978 0.984 0.027     
  1. 4800 RF segmentation at various depths [5 40] and 500 trees. Manual contours were available through Biobank Application 2964. Classes are LV Cavity (LVC), LV Myocardium (LVM), RV Cavity (RVC), an average over the classes (Av.) and a binary segmentation of the whole heart (WH). First row for each class shows the binary classification accuracy for ‘poor’ and ‘good’ segmentations in the Dice Similarity Coefficient (DSC) ranges [0.0 0.7) and [0.7 1.0] respectively. Second row for each class shows the binary classification accuracy for ‘poor’ and ‘good’ segmentations in the Mean Surface Distance (MSD) ranges [>2.0mm] and [0.0mm 2.0mm] respectively. True-positive and false-positive rates are also shown. We report mean absolute errors (MAE) on the predictions of DSC and additional surface-distance metrics: root-mean-squared surface distance (RMS) and Hausdorff distance (HD)