Achieving the way for automated segmentation of nuclei in cancer tissue images through morphology-based approach: a quantitative evaluation.

In this paper we address the problem of nuclear segmentation in cancer tissue images, that is critical for specific protein activity quantification and for cancer diagnosis and therapy. We present a fully automated morphology-based technique able to perform accurate nuclear segmentations in images with heterogeneous staining and multiple tissue layers and we compare it with an alternate semi-automated method based on a well established segmentation approach, namely active contours. We discuss active contours' limitations in the segmentation of immunohistochemical images and we demonstrate and motivate through extensive experiments the better accuracy of our fully automated approach compared to various active contours implementations.