Background: Fuzzy connectedness method has shown its effectiveness for fuzzy\nobject extraction in recent years. However, two problems may occur when applying it\nto hepatic vessel segmentation task. One is the excessive computational cost, and the\nother is the difficulty of choosing a proper threshold value for final segmentation.\nMethods: In this paper, an accelerated strategy based on a lookup table was presented\nfirst which can reduce the connectivity scene calculation time and achieve a\nspeed-up factor of above 2. When the computing of the fuzzy connectedness relations\nis finished, a threshold is needed to generate the final result. Currently the threshold\nis preset by users. Since different thresholds may produce different outcomes, how to\ndetermine a proper threshold is crucial. According to our analysis of the hepatic vessel\nstructure, a watershed-like method was used to find the optimal threshold. Meanwhile,\nby using Ostu algorithm to calculate the parameters for affinity relations and assigning\nthe seed with the mean value, it is able to reduce the influence on the segmentation\nresult caused by the location of the seed and enhance the robustness of fuzzy connectedness\nmethod.\nResults: Experiments based on four different datasets demonstrate the efficiency of\nthe lookup table strategy. These experiments also show that an adaptive threshold\nfound by watershed-like method can always generate correct segmentation results\nof hepatic vessels. Comparing to a refined region-growing algorithm that has been\nwidely used for hepatic vessel segmentation, fuzzy connectedness method has advantages\nin detecting vascular edge and generating more than one vessel system through\nthe weak connectivity of the vessel ends.\nConclusions: An improved algorithm based on fuzzy connectedness method is proposed.\nThis algorithm has improved the performance of fuzzy connectedness method\nin hepatic vessel segmentation
Loading....