针对人体脑部切片图像特点,提出了一种基于数学形态学的脑组织自动分割算法。该算法首先通过形态重构获得粗糙的脑组织区域,然后运用腐蚀和膨胀运算进行边界定位分割出了脑组织,最后对连续断层图像的分割结果进行了三维重建。结果表明该算法分割准确且自动化程度高,适合于大量序列切片图像的快速自动分割。
According to the features of slice images of human brain,an algorithm based on mathematic morphology is proposed for brain tissue segmentation in this study.Initially,the region of brain tissue in each slice image is roughly distinguished through morphological reconstruction.Then its edge is refined by means of dilation and erosion to complete the segmentation.Finally,the segmented sequential slice images are reconstructed in three dimensions to evaluate the performance of the segmentation algorithm.The results indicate that this algorithm exhibits the advantages of accurate segmentation,and highly automatic processing.The proposed algorithm is suitable for rapid and automatic segmentation of massive sequential slice images.