The METINUS Plus method for nuclei quantification in tissue microarrays of breast cancer and axillary node tissue section. (February 2017)

• Record Type: Journal Article
• Authors: Korzynska, Anna; Roszkowiak, Lukasz; Zak, Jakub; Lejeune, Marylene; Orero, Guifre; Bosch, Ramon; Lopez, Carlos
• Is Part Of: Biomedical signal processing and control. Volume 32(2017)
• Page Start: 1
• Page End: 9
• Publication Date: 2017-02
• Subjects: Biomedical engineering -- Image processing -- Microscopic images -- Object segmentation -- Pathology -- Immunohistochemistry -- Nuclear quantification; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2016.09.022
• Languages: English
• ISSNs: 1746-8094

Abstract

Abstract : Highlights: A method for localization and quantification of the regulatory T cells' nuclei is proposed. The method relies on the quantity and quality of segmented nuclei. It is possible to differentiate between two types of immunopositive cells' nuclei. Abstract: This paper presents the METINUS Plus (METhod of Immunohistochemical NUclei Segmentation Plus) method that has been developed for localization and quantification of the regulatory T cells' nuclei. The proposed methodology performs color separation followed by the extraction and validation of objects. Objects categorized as clusters, based on the area and shape, are divided with locally applied watershed supported by color deconvolution. Objects are validated based on RGB, Lab color space, and color deconvolution data. The chosen validation criteria allow quantification and differentiation between the subpopulations of regulatory T cells and breast cancer cells, which express FOXP3. The evaluation is based on the quantity and quality of nuclei segmentation in comparison with the results of the manual counting, done by four pathologists on a set of 20 images. The results were analyzed in comparison with human evaluation using Kendall's tau-b correlation coefficient and the Wilcoxon signed-rank test. The main achievement of this study is a possibility to find criteria that allow differentiation between two types of immunopositive cells' nuclei: regulatory T cells with homogeneous stained nuclei and all cells with FOXP3 expression; in both tumor and axillary node biopsies. A major advantage of computer image processing is the reproducibility of achieved results, thus minimizing human intervention, and providing traceable clinical information.