An algorithm for Segmentation of Medical Image Series Based on Active Contour Model
Luo Xi-ping, Tian Jie, Lin Yao · 2014
Abstract: In this paper, an algorithm based on the combination of the live wire algorithm and the active contour model is proposed for the semiautomatic segmentation of medical image series. The traditional live wire algorithm is modified by integrating with the fuzzy region growing method. Then the improved live wire algorithm is applied to obtain accurate segmentation of one or more slices in a medical image series. Next, the computer will segment the nearby slice automatically using the active contour model. To record the local region characters of the desired object in the segmented slice, a gray-scale model is introduced to the boundary points of the active contour model. Based on the similarity measure of regions in the gray-scale model, a new energy function is defined to replace the external energy of the traditional active contour model. Finally, a simple method based on the idea of the live wire algorithm is introduced for the reparation of the automatic segmentation result to guarantee the reliability of the result. Experiment shows that this algorithm can obtain the boundary of the desired object from a series of medical images quickly and reliably with only little user intervention. It has practical value in the medical image analysis. Key words: medical image processing; image segmentation; active contour; live wire algorithm; gray-scale model Image segmentation plays an essential role in medical image processing. Accurate extraction of clinical information from medical images promises reliability for clinical applications and it is the basis of 3-D model reconstruction. Image segmentation is a very difficult problem in practice. Currently, fully automatic techniques for