Unsupervised cell nuclei segmentation based on morphology and adaptive active contour modelling

Abstract

This paper proposes an unsupervised segmentation scheme for cell nuclei. This method computes the cell nuclei by using adaptive active contour modelling which is driven by the morphology method. Firstly, morphology is used to enhance the gray level values of cell nuclei. Then binary cell nuclei is acquired by using an image subtraction technique. Secondly, the masks of cell nuclei are utilized to drive an adaptive region-based active contour modelling to segment the cell nuclei. In addition, an artificial interactive segmentation method is used to generate the ground truth of cell nuclei. This method can have an interest in several applications covering different kinds of cell nuclei. Experiments show that the proposed method can generate accurate segmentation results compared with alternative approaches. © 2013 Springer-Verlag.