A Quantitative Evaluation Function For 3d Tree-Like Structure Segmentations In Liver Images

The analysis of vascular structure from volumetric datasets plays a crucial role in many medical applications. Many segmentation algorithms have been designed to extract the vessel features. However, to date, these algorithms have not been efficiently evaluated and a large-scale manual analysis is always impossible. In this paper, we propose a quantitative evaluation function based on connectivity, overlap volume ratio, skeleton coincidence and branches structure error to deal with this evaluation task. The function is applicable to 3D tree-like structure segmentations and does not depend on the segmentation algorithms used. The performances of this evaluation function are tested on real liver datasets. The results show that the values of evaluation function are very close to the human scoring value (standard value), and the average value of relative errors is only 7.3% over all the eight datasets, while other evaluation measurements are 20% or more. So, it provides the greatest correlation with human quality perception when compared with other evaluation measurements. Thus, it is the most suitable measure for the evaluation of 3D tree-like structure segmentations in liver images.