Skip to main content

Table 5 Quantitative comparison of classification accuracy for cephalometric analysis between Ceph-Net and other detection networks

From: Ceph-Net: automatic detection of cephalometric landmarks on scanned lateral cephalograms from children and adolescents using an attention-based stacked regression network

Measurements

U-Net

SegNet

Dense U-Net

Attention U-Net

Ceph-Net

ANB

69.50

63.25

67.25

69.50

71.50

SNB

73.75

68.00

73.50

76.25

77.50

SNA

64.50

58.50

64.50

65.25

65.75

ODI

77.20

64.50

79.50

75.50

77.25

APDI

60.75

53.00

59.75

58.50

63.75

FHI

81.75

72.75

84.00

84.00

83.25

FMA

79.50

75.50

79.00

80.75

78.00

Mean

74.78

67.17

74.57

75.00

76.42