Generalized region growing operator with optimal scanning: application to segmentation of breast cancer images

Abstract

Segmentation of medical images is a complex problem owing to the large variety of their characteristics. In the automated analysis of breast cancers, two image classes may be distinguished according to whether one considers the quantification of DNA (grey level images of isolated nuclei) or the detection of immunohistochemical staining (colour images of histological sections). The study of these image classes generally involves the use of largely different image processing techniques. We therefore propose a new algorithm derived from the watershed transformation enabling us to solve these two segmentation problems with the same general approach. We then present visual and quantitative results to validate our method.

Identification of Regions of Interest in Digital Mammograms

“…The region growing method of segmentation has been used recently in other studies, e.g. Pohlman et al (1996), Belhomme et al (1996), andPetrick et al (1999). Gradient based methods in the literature have not been used directly for segmentation in most cases, but instead gradient information is used to smooth out images before region growing can be applied.…”

Automated Segmentation of Cytological and Histological Images for the Nuclear Quantification: an Adaptive Approach based on Mathematical Morphology

“…c) A step of localization that corresponds to the segmentation of the objects previously labeled. This step involves region growing processes using one or many criteria such as the watershed transformation [1], or its extension dealing with local and global information [2][3][4].…”

Computer Recognition Systems 4

“…In 1996, Belhomme et al [73] proposed a watershed based algorithm for segmentation of breast cancer cytological and histological images.Their algorithm is a more general version of the method described by Adams and Bischof [74]. In 1996, Belhomme et al [73] proposed a watershed based algorithm for segmentation of breast cancer cytological and histological images.Their algorithm is a more general version of the method described by Adams and Bischof [74].…”