Automated segmentation of tissue images for computerized IHC analysis.

This paper presents two automated methods for the segmentation of immunohistochemical tissue images that overcome the limitations of the manual approach as well as of the existing computerized techniques. The first independent method, based on unsupervised color clustering, recognizes automatically the target cancerous areas in the specimen and disregards the stroma; the second method, based on colors separation and morphological processing, exploits automated segmentation of the nuclear membranes of the cancerous cells. Extensive experimental results on real tissue images demonstrate the accuracy of our techniques compared to manual segmentations; additional experiments show that our techniques are more effective in immunohistochemical images than popular approaches based on supervised learning or active contours. The proposed procedure can be exploited for any applications that require tissues and cells exploration and to perform reliable and standardized measures of the activity of specific proteins involved in multi-factorial genetic pathologies.

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.