Analyzing cellular morphologies on a cell-by-cell basis is vital for drug discovery, cell biology, and many other biological studies. Interactions between cells in their culture environments cause cells to touch each other in acquired microscopy images. Because of this phenomenon, cell segmentation is a challenging task, especially when the cells are of similar brightness and of highly variable shapes. The concept of topological dependence and the maximum common boundary (MCB) algorithm are presented in our previous work (Yu et al., Cytometry Part A 2009;75A:289-297). However, the MCB algorithm suffers a few shortcomings, such as low computational efficiency and difficulties in generalizing to higher dimensions. To overcome these limitations, we present the evolving generalized Voronoi diagram (EGVD) algorithm. Utilizing image intensity and geometric information, EGVD preserves topological dependence easily in both 2D and 3D images, such that touching cells can be segmented satisfactorily. A systematic comparison with other methods demonstrates that EGVD is accurate and much more efficient. ' 2010 International Society for Advancement of Cytometry Key terms image cytometry; cell segmentation; fluorescence microscopy; generalized Voronoi diagram ANALYZING cellular morphology is crucial in drug discovery, cell and developmental biology. Automated high-content image-based approaches are preeminent tools, which enable thousands of images to be acquired. However, acquiring high quality images is only the first step towards biological discoveries. Image processingcomputer-based interrogation is essential to extract useful data from the images acquired. To extract the quantitative information on a cell-by-cell basis, a critical but challenging task is to segment individual cells. Once cells have been segmented successfully, subsequent analysis including cell counting, morphology, and migration becomes possible.In the images acquired by high-content screening experiments, the cells can be classified into three groups; (i) isolated, (ii) touching, and (iii) overlapping. In monolayer cell cultures, as shown in Figure 1, isolated cells are the cells that are well separated from other cells, touching cells are the cells that adhere to other cells and share some common boundaries, and overlapping cells are the cells that lie on top of each other with no clear boundary. Touching cells form the majority of cells in normal culture conditions. Segmentation of the isolated cells is straightforward as simple thresholding can successfully segment them, while segmentation of the touching cells is much more challenging.Among many existing cell segmentation approaches, active contours represented through the level set is a successful way to segment cells of irregular shapes. The Mumford-Shah model (1) is proposed to segment two-phase piecewise constant images. This model is enhanced by Chan-Vese (2) using the level set concept introduced in (3). However, the level set formulation lacks the ability to constrain