Skip to main content

Table 3 Classification accuracy of Inception v3, ResNet101 and DenseNet201 convolutional neural network on calcified plaques with motion artifacts on four CT systems

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
CT-A 90.2 ± 3.1% 92.2 ± 2.3% 92.0 ± 1.8%
CT-B 89.8 ± 2.7% 88.0 ± 5.3% 89.3 ± 5.6%
CT-C 91.0 ± 2.8% 90.9 ± 2.6% 90.7 ± 2.4%
CT-D 91.8 ± 0.8% 91.2 ± 3.6% 91.1 ± 2.6%
  1. Variables are displayed as mean ± standard deviation