Figure 4
From: Sperm motility assessed by deep convolutional neural networks into WHO categories
Comparison of manually and DCNN-predicted rapid progressive sperm motility. Correlation graph (A) and difference plot (B) between rapid progressive motility assessed manually by reference laboratories and motility values predicted for four categories by deep convolutional neural network (DCNN). In the correlation graph, solid line represents the trendlines while dashed lines the 95% confidence interval. Pearson’s correlation coefficient (r) and p-value (p) between results are also depicted. In the difference plot the bias estimated as the median of the differences between predicted and manually assessed motility is shown as a solid line, while the 95% limits of agreement (LoA) are represented in the figure and shown in dashed lines to display outliers. For the results between all the four categories, manually and DCNN-predicted, see Supplementary Fig. S1.
