Adaptive segmentation model for liver CT images based on neural network and level set method

Abstract

Accurate segmentation is difficult for liver computed tomography (CT) images, since the liver CT images do not always have obvious and smooth boundaries. The location of the tumor is not specified and the image intensity is similar to that of the liver. Although manual and automatic segmentation methods, traditional and deep learning models currently exist, none can be specifically and effectively applied to segment liver CT images. In this paper, we propose a new model based on a level set framework for liver CT images in which the energy functional contains three terms including the data fitting term, the length term and the bound term. Then we apply the split Bregman method to minimize the energy functional that leads the energy functional to converge faster. The proposed model is robust to initial contours and can segment liver CT images with intensity inhomogeneity and unclear boundaries. In the bound term, we use the U-Net to get constraint information which has a considerable influence on effective and accurate segmentation. We improve a multi-phase level set of our model to get contours of tumor and liver at the same time. Finally, a parallel algorithm is proposed to improve segmentation efficiency. Results and comparisons of experiments are shown to demonstrate the merits of the proposed model including robustness, accuracy, efficiency and intelligence.