LIVER VESSELS SEGMENTATION BASED ON 3D RESIDUAL U-NET

Recently, extraction of blood vessels has aroused widespread interests in medical image analysis. In this work, to accelerate convergence speed and enhance the representation for discriminative features, we introduce the residual block structure in the ResNet into the 3D U-Net, and construct a new 3D Residual U-Net architect to segment the hepatic and portal veins from abdominal CT volumes. In addition, we develop a weighted Dice loss function to cope with the challenges of pixel imbalance, vessel boundary segmentation and small vessels segmentation. Furthermore, based on the prediction results, the post-processing methods of 3D morphological closed operation and volume analysis are employed to smooth the surface of vessels and eliminate noise blocks, respectively. Compared with existing 3D DenseNet, FCN and 3D U-Net, the average Dice coefficients of our method in hepatic veins and portal veins segmentation are 71.7% and 76.5% respectively, which are superior to 55.3% and 53.9% of the 3D DenseNet, 60.2% and 75.6% of the FCN, and 66.4% and 73.9% of the 3D U-Net. Meanwhile, the cross validation results prove that our method is accurate and stable for liver vessel extraction.