Skip to main content

Table 4 Spearman’s correlation coefficients (rho) for the univariate association between influencing factors and convolutional neural network’s classification on calcified plaques with motion artifacts

From: Classification of moving coronary calcified plaques based on motion artifacts using convolutional neural networks: a robotic simulating study on influential factors

  Inception v3 ResNet101 DenseNet201
rho (95% CI) p value rho (95% CI) p value rho (95% CI) p value
Density 0.139 (0.083, 0.195) < 0.001 0.199 (0.061, 0.337) < 0.001 0.194 (0.074, 0.314) < 0.001
CT vendor 0.031 (− 0.017, 0.079) 0.249 − 0.049 (− 0.151, 0.053) 0.210 − 0.102 (− 0.192, − 0.012) 0.107
Velocity 0.191 (0.105, 0.277) < 0.001 0.169 (0.029, 0.309) < 0.001 0.163 (0.024, 0.302) < 0.001
Dose − 0.028 (− 0.081, 0.025) 0.518 0.028 (− 0.052, 0.108) 0.477 0.046 (− 0.010, 0.102) 0.239
Reconstruction 0.019 (− 0.031, 0.069) 0.312 0.118 (0.030, 0.206) 0.230 0.134 (0.023, 0.245) 0.222
  1. High, medium-1, medium-2, and low-density plaque were coded as 1–4, respectively, four CT systems (CT-A to CT-D) as 1–4; velocities from 0 to 60 mm/s coded as 0–6; dose level 40%, 80% and full dose coded as 1–3; recon method FBP, IR1 to IR3 coded as 1–4
  2. FBP filtered back projection, IR iterative reconstruction