Table 5 Quality coefficient of classification DNN obtained on the manually segmented dataset and on dataset segmented by DeepLabV3Plus
From: Human oocytes image classification method based on deep neural networks
Manually labeled dataset | DNN labeled dataset | |||||
|---|---|---|---|---|---|---|
Validation | Test | All | Validation | Test | All | |
\(\overline{Acc}\) | 1 | 1 | 1 | 0.96471 | 0.95699 | 0.98253 |
\(\overline{TPR}\) | 1 | 1 | 1 | 0.92692 | 0.88291 | 0.91532 |
\(\overline{PPV}\) | 1 | 1 | 1 | 0.91587 | 0.86816 | 0.95112 |
\(\overline{FDR}\) | 0 | 0 | 0 | 0.084126 | 0.13184 | 0.048878 |
\(\overline{f1}\) | 1 | 1 | 1 | 0.91364 | 0.871 | 0.93246 |