Towards dense volumetric pancreas segmentation in CT using 3D fully convolutional networks
This improves automated segmentation for medical imaging in gastric cancer patients, but is incremental as it builds on existing 3D FCN methods.
The paper tackled pancreas segmentation in CT scans, which is difficult due to shape variations, by developing a 3D fully convolutional network with skip connections, achieving a state-of-the-art average Dice score of 89.7%.
Pancreas segmentation in computed tomography imaging has been historically difficult for automated methods because of the large shape and size variations between patients. In this work, we describe a custom-build 3D fully convolutional network (FCN) that can process a 3D image including the whole pancreas and produce an automatic segmentation. We investigate two variations of the 3D FCN architecture; one with concatenation and one with summation skip connections to the decoder part of the network. We evaluate our methods on a dataset from a clinical trial with gastric cancer patients, including 147 contrast enhanced abdominal CT scans acquired in the portal venous phase. Using the summation architecture, we achieve an average Dice score of 89.7 $\pm$ 3.8 (range [79.8, 94.8]) % in testing, achieving the new state-of-the-art performance in pancreas segmentation on this dataset.