Fig. 3From: Hierarchical combinatorial deep learning architecture for pancreas segmentation of medical computed tomography cancer imagesExample of multistage output. The first column is the original input from our datasets. And from row 1 to row 6 are the six classes of pancreas disease, namely healthy, PNET, PDAC, IPMN, SCA, SPT. From the column 2 to column 6 are the output of stage 1 to 5 from our modelBack to article page