Figure 1
From: Automated pancreas segmentation and volumetry using deep neural network on computed tomography

(a) Raw volume data were cropped and reconstructed for training data generation. (b) All data were divided into datasets that consisted of almost identical numbers of participants for cross validation. (c) A region of the pancreas was enhanced via CLAHE. Valid, validation; TCIA, the Cancer Imaging Archive; WL, window level; WW, window width; CLAHE, contrast-limited adaptive histogram equalization.