IMAGE ANALYSIS OF HISTOPATHOLOGICAL IMAGES-USING AUTOMATIC SEGMENTATION OF CELL NUCLEI
ABSTRACT :
Automatic segmentation of cell nuclei is an essential step in image cytometry and histometry .The goal of this study is to develop efficient and accurate algorithms for detecting and segmenting cell nuclei in 2-D histological images. This is commonly a first step to counting cells, quantifying molecular markers interest in healthy and pathologic specimens and also for quantifying aspects of normal/diseased tissue architecture. From the image,foreground pixels are separated from the background pixels using a graph-cuts-based binarization. The most critical aspect of nuclear segmentation algorithms is the process of detecting a set of points in the image,usually one per cell nucleus and close to its center, that are variously referred to as “markers” or “seeds.” The accuracy of the segmentation depends critically on the accuracy and reliability of the initial seed points. The initial segmentation is performed and it is refined by using a method of alpha expansions and graph coloring. The present work has built upon integrated, and extended multiple recent advances in the biological image analysis field. The accuracy of the algorithm is investigated for the images with segmentation errors.
No comments:
Post a Comment