Liver vessel segmentation based on extreme learning machine.
Journal:
Physica medica : PM : an international journal devoted to the applications of physics to medicine and biology : official journal of the Italian Association of Biomedical Physics (AIFB)
Published Date:
May 4, 2016
Abstract
Liver-vessel segmentation plays an important role in vessel structure analysis for liver surgical planning. This paper presents a liver-vessel segmentation method based on extreme learning machine (ELM). Firstly, an anisotropic filter is used to remove noise while preserving vessel boundaries from the original computer tomography (CT) images. Then, based on the knowledge of prior shapes and geometrical structures, three classical vessel filters including Sato, Frangi and offset medialness filters together with the strain energy filter are used to extract vessel structure features. Finally, the ELM is applied to segment liver vessels from background voxels. Experimental results show that the proposed method can effectively segment liver vessels from abdominal CT images, and achieves good accuracy, sensitivity and specificity.