Bradbury Laura, Wan Justin W L
Computational Mathematics, University of Waterloo, Ontario, Canada.
Annu Int Conf IEEE Eng Med Biol Soc. 2010;2010:4748-51. doi: 10.1109/IEMBS.2010.5626380.
Automatic segmentation of bright-field cell images is important to cell biologists, but difficult to complete due to the complex nature of the cells in bright-field images (poor contrast, broken halo, missing boundaries). Standard approaches such as level set segmentation and active contours work well for fluorescent images where cells appear as round shape, but become less effective when optical artifacts such as halo exist in bright-field images. In this paper, we present a robust segmentation method which combines the spectral and k-means clustering techniques to locate cells in bright-field images. This approach models an image as a matrix graph and segment different regions of the image by computing the appropriate eigenvectors of the matrix graph and using the k-means algorithm. We illustrate the effectiveness of the method by segmentation results of C2C12 (muscle) cells in bright-field images.
明场细胞图像的自动分割对细胞生物学家来说很重要，但由于明场图像中细胞的复杂特性（对比度差、光晕破碎、边界缺失）而难以完成。诸如水平集分割和活动轮廓等标准方法在荧光图像中效果良好，因为荧光图像中的细胞呈圆形，但当明场图像中存在光晕等光学伪像时，这些方法的效果就会变差。在本文中，我们提出了一种稳健的分割方法，该方法结合了光谱和k均值聚类技术来定位明场图像中的细胞。这种方法将图像建模为矩阵图，并通过计算矩阵图的适当特征向量并使用k均值算法来分割图像的不同区域。我们通过明场图像中C2C12（肌肉）细胞的分割结果来说明该方法的有效性。
