Live cell imaging in 3D platforms is a highly informative approach to visualize cell function and it is becoming more commonly used for understanding cell behavior. Since these experiments typically generate large data sets their analysis manually would be very laborious and error prone. This has led to the necessity of automatic image analysis tools. Cell segmentation is an essential initial step for any detailed automatic quantitative analysis. When the images are captured from the 3D culture containing proliferating and moving cells, cell-cell interactions and collisions cannot be avoided. In these conditions the segmentation of individual cells becomes very challenging. Here we present a method which utilizes the edge probability map and graph cuts to detect and segment individual cells from cell clusters. The main advantage of our method is that it is capable of handling complex cell shapes because it does not make any assumptions about the cell shape.
展开▼