Skip to main content

Table 2 Dice’s coefficient (DC) values of different burn depth in different models

From: Burn image segmentation based on Mask Regions with Convolutional Neural Network deep learning framework: more accurate and more convenient

Burn depths

Model name

R101FA (our method)

IV2RA

R101A

Superficial

89.7*

83.61

77.37

Superficial thickness

85.21*

82.52

84.91

Deep partial thickness

84.54*

84.44

81.96

Full-thickness burn

81.12

74.56

83.5*

  1. *The highest average DC value of this burn depth in different models
  2. R101FA residual network-101 with atrous convolution in feature pyramid network, IV2RA inceptionV2-residual network with atrous convolution, R101A residual network-101 with atrous convolution
Back to article page

Burns & Trauma

ISSN: 2321-3876

Contact us