2.2. Analysis of Cross-site Heterogeneity
We first evaluated prostate segmentation performance using mean
intersection over union (IoU), in order to ensure that the prostate
regions can be predicted accurately. The IoU indicates the intersection
between the predicted prostate contour and the ground truth mask label,
which was measured on the test split of I2CVB. The mean IoU of prostate
region, central gland, and peripheral zone are 0.843, 0.781, and 0.516,
respectively. These results are comparable with the work of Alkadi,
Taher, El-Baz and Werghi [8] which attained an IoU
of 0.673 and 0.599 for the central gland and peripheral zone,
respectively. It implies that the training set containing MR images from
36 patients is already sufficient for accurate prostate segmentation.
Additionally, the segmentation results are found to be promising on the
image obtained from either 1.5-T or 3.0-T MRI machine, indicating that
the IoU measuring is not sensitive to the scanner types (see details in Supplementary Figure 1 ).
Table 2. Comparisons of AUC using
separate and joint learning
approaches.