Skip to main content

Table 2 The area under receiver operating characteristic curves of 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

Plaque density

Inception v3

ResNet101

DenseNet201

High

0.952 (0.939–0.964)

0.972 (0.962–0.980)

0.970 (0.960–0.978)

Medium-1

0.951 (0.939–0.962)

0.955 (0.943–0.965)

0.962 (0.951–0.972)

Medium-2

0.980 (0.970–0.989)

0.974 (0.969–0.981)

0.976 (0.970–0.982)

Low

0.982 (0.976–0.986)

0.981 (0.974–0.992)

0.986 (0.982–0.994)

  1. The data is expressed as area under the curve (95% confidence interval)
Back to article page

BMC Medical Imaging

ISSN: 1471-2342

Contact us