Convolutional Neural Networks Based Level Set Framework for Pancreas Segmentation from CT Images

Pancreas segmentation in computed tomography (CT) is a challenging task because of the high inter-patient anatomical variability in both shape and size between patients. In this work, we proposed a convolutional neural networks based level set framework that can automatically segment a 3D images with the whole pancreas. Convolutional neural networks is applied to obtain an initial level set contour and then level set model is used to produce accurate segmentation results. Our method was compared with the state-of-the-art methods and evaluated on 20 CT images. The experiment results show that our approach achieves the highest dice scores than other methods.