Skip to main content

Table 5 Results of ‘Visual Turing Test’ on DCGAN-generated liver lesion images presented by Frid-Adar et al. [139]

From: A survey on Image Data Augmentation for Deep Learning

 

Classification accuracy

Is ROI real?

Real (%)

Synthetic (%)

Total score

Total score

Expert 1

78

77.5

235\302 = 77.8%

189\302 = 62.5%

Expert 2

69.2

69.2

209\302 = 69.2%

177\302 = 58.6%