作者: Aymen Mouelhi , Mounir Sayadi , Farhat Fnaiech
DOI: 10.1109/ATSIP.2014.6834601
关键词:
摘要: In this paper, we propose a fully automated method able to perform accurate nuclear segmentation in immunohistochemical breast tissue images order provide quantitative assessment of estrogen receptor's status that will help pathologists their diagnosis. The presented approach is based on color deconvolution and an enhanced morphological processing, which used identify positive stained nuclei separate all touching the microscopic image for subsequent cancer evaluation. Experiments several different patients admitted into Tunisian Salah Azaiez Cancer Center, show efficiency proposed when compared manual evaluation experts.