DLU-Net for Pancreatic Cancer Segmentation
Feng Xian Jiang, Xiaoli Zhi, Xuehai Ding, Weiqin Tong, Yun Bian · 2020
The pancreas is located in the deep abdominal cavity of the human body. It is small in size and variable in shape, which makes the location and diagnosis of pancreatic cancer in abdominal computed tomography (CT) scan images especially difficult. The existing segmentation models of pancreatic cancer have been able to locate the pancreas correctly, but they can't yet segment the edge of the pancreas accurately enough. This paper proposes an extension of the convolutional network U-Net, which is called DLU-Net, for accurately cutting out the irregular shape of pancreatic cancer and improving the segmentation accuracy for pancreatic cancer. In DLU-Net, we use deformable convolution modules to strengthen the ability of the network to model the target edge. To facilitate the transmission of features and reuse the features to reduce the complexity of the network, we add densely connected convolutions. Moreover, Bi-Directional Convolutional Long-Short Term Memory (BConvLSTM) structures are applied to combine the features of different scales by using temporal and spatial correlations. The model was evaluated on the following two datasets: abdominal CT images of pancreatic cancer patients of Medical Segmentation Decathlon (MSD) and abdominal CT images of pancreatic cancer patients of Changhai Hospital. The experimental results show that DLU-Net can more accurately segment the edge of cancer, and has an excellent performance in other segmentation indicators.