Fig. 2From: Pelvic U-Net: multi-label semantic segmentation of pelvic organs at risk for radiation therapy anal cancer patients using a deeply supervised shuffle attention convolutional neural network2-stage observational evaluation process of segmentation predictions derived for n = 15 test patients. Uncorrected segmentations were rated on a scale between 1–4 by three radiation oncologists (a). Once rated, all structures were manually corrected (b) and rated a second time (c)Back to article page