Fig. 4From: Development of in-house fully residual deep convolutional neural network-based segmentation software for the male pelvic CTBoxplot of the dice similarity coefficients of the testing dataset using different training methods: models trained using a one ROI, b two ROIs, and c three ROIs. P, B, R, and S on the horizontal axis denote the prostate, bladder, rectum, and seminal vesicles, respectivelyBack to article page