基于种子点的粘连巨噬细胞图像的分割方法

粘连细胞的分割是医学细胞图像处理中的关键,随着形态学在图像分割中的应用,分水岭分割成为粘连细胞分割中最有效的方法之一。然而,由于巨噬细胞图像中的噪声和形态的不规则性,传统分水岭算法容易产生过分割。若在经距离变换得到的距离图中提取"种子点",并将其中距离小于某一阈值的两两"种子点"合并得到新的"种子点",在新"种子点"重新分布的距离图基础上使用分水岭分割。实验结果表明:该算法虽然要比传统分水岭算法多花费些时间,但可以有效地分割粘连巨噬细胞并抑制过分割现象。分割后,对细胞进行标记并提取细胞的特征参数,如周长、面积、圆度因子、灰度均值等。

Segmentation Method to Adhesion Macrophage Image Based on Seeding Point

Segmentation to adhesion cells is critical in image segmentation realm,with the morphology being used in image segmentation,watershed becomes one of the most efficient skills in solving adhesion cells. However,the traditional watershed algorithm is apt to cause over-segmentation for the noise and irregular shape of macrophages.If extracting the “seeding points” from the distance map,two “seeding points” is combined into one “seeding point” if the distance between them is under threshold after count the distances between each two “seeding points”. The redistribution distanee map depending on the new seeding points is segmented by watershed. The simulation results show that the algorithm can effectively segment adhesion macrophages as well as restrain the over-segmentation phenomena with a little more time compared with the traditional method.After segmentation,we can mark the numbers to the cells and abstract the characteristic parameters such as circumference, area, roundness factor, mean gray and so on.