Spatial Aggregation of Holistically-Nested Convolutional Neural Networks for Automated Pancreas Localization and Segmentation

Pancreas segmentation in computed tomography (CT) challenges current computer-aided diagnosis (CAD) systems. While automatic segmentation of numerous other organs in CT scans, such as the liver, heart or kidneys, achieves good performance with Dice similarity coefficients (DSCs) of  > 90% (Wang et al., 2014c; Chu et al., 2013; Wolz et al., 2013), the pancreas’ variable shape, size, and location in the abdomen limits segmentation accuracy to  

Source: Medical Image Analysis - February 4, 2018 Category: Radiology Authors: Holger R. Roth, Le Lu, Nathan Lay, Adam P. Harrison, Amal Farag, Andrew Sohn, Ronald M. Summers Source Type: research