Skip to main content
Fig. 5 | Insights into Imaging

Fig. 5

From: Label-set impact on deep learning-based prostate segmentation on MRI

Fig. 5

Agreement between generated segmentations and manual segmentations. Boxplots displaying the Dice similarity coefficient (DSC) (a), the 95th percentile of the Hausdorff distance (HD95; log applied to improve visualization) (b), and relative volume difference for whole prostate (RVD (WP)) (c). Panels a and b compare scores that measured agreement between generated masks derived from model 4 and model 5 and scores that measured the agreement between the manual masks in the test subset of the PROSTATEx dataset. Panel c illustrates RVD scores for the same comparisons. ns: p ≥ 0.05, **** p < 0.0001

Back to article page