Skip to main content

Table 5 Evaluation of the performance of various GAN-based methods

From: Fusion-driven semi-supervised learning-based lung nodules classification with dual-discriminator and dual-generator generative adversarial network

Method

Scenarios

accuracy

precision

recall

f_score

[28],2024 pyramid attention-based GAN

Scenario1

82%

81%

87%

84%

Scenario2

65%

67%

65%

66%

[36], 2024 Reinforcement Learning-based GAN

Scenario1

77%

80%

77%

78%

Scenario2

62%

63%

61%

62%

MD-GAN [26], 2019

Scenario1

76%

74%

82%

78%

Scenario2

60%

59%

58%

59%

DDDG-GAN (proposed)

Scenario1

92.56%

90.12%

95.87%

92.77%

Scenario2 (Luna16)

72.6%

72.3%

73.82%

73.39%

Scenario2 (LUNGx)

71.23%

67.56%

73.52%

70.42%