Graph-based learning for segmentation of 3D ultrasound images

Abstract

The analysis of 3D medical images becomes necessary since the 3D imaging techniques have been more and more widely applied in medical applications. This paper introduces a novel segmentation method for extracting objects of interest (OOI) in 3D ultrasound images. In the proposed method, a bilateral filtering model is first applied to a 3D ultrasound volume data set for speckle reduction. We then take advantage of graph theory to construct a 3D graph, and merge sub-graphs into larger one during the segmentation process. Therefore, the proposed method can be called a 3D graph-based segmentation algorithm. After the mergence of sub-graphs, a set of minimum spanning trees each of which corresponds to a 3D sub-region is generated. In terms of segmentation accuracy, the experiments using an ultrasound fetus phantom, a resolution phantom and human fingers demonstrate that the proposed method outperforms the 3D Snake and Fuzzy C means clustering methods, indicating improved performance for potential clinical applications.