Medical Volumes Segmentation Approach Based on Level Set Method

摘要

Volumes segmentation is an important part of computer based medical application for diagnosis and analysis of anatomical data. A segmentation approach based on the level set method is proposed for accurately extracting vasculature from magnetic resonance angiography (MRA) volumes in this paper. The proposed model has a boundary alignment term that is used for segmentation of thin structures. Finally the proposed model is applied to the segmentation of MRA volumes. The result shows that the proposed model by us can complete the segmentation task of vascular structure and cannot complete the same task by the model without boundary alignment term.