The application of hierarchical self organizing maps (HSOM) to the segmentation of cell migration images, obtained during high-content screening in molecular medicine, is described. The segmentation is critical to our larger project for developing methods for the automatic annotation of cell migration images. The HSOM appears to perform better than the conventional computer-vision methods of histogram thresholding, edge detection, and the newer techniques involving single-layer SOMs. However, the HSOM techniques have to be complemented by region-based techniques to improve the quality of the segmented images.