Image Segmentation via Multiple Active Contour Models and Fuzzy Clustering with Biomedical Applications

We address the problem of automatically segmenting cell nuclei or cluster of cell nuclei in image medical microscopy. We present a system of automatic segmentation combining fuzzy clustering and multiple active contour models. An automatic initialization algorithm based on fuzzy clustering is used to robustly identify and classify all possible seed regions in the image. These seeds are propagated outward simultaneously to localize the final contours of all objects. We present examples of quantitative segmentation on biomedical images: segmentation of lobules in color images of histology and segmentation of nuclei in cytological images.