We propose a technique for analyzing images of immunohistochemically stained tissue samples for extracting features that correlate with patient disease. We address the problem of quantifying tumor tissue and segmenting and counting nuclei. Our method utilizes a flexible segmentation technique trained from representative image samples. Nuclei counting is based on a nucleus model that takes size, shape and nucleus probability into account. We obtain the probability of a nucleus from our segmentation procedure. Our method is experimentally validated on images stained with nuclear markers for the Estrogen Receptor (ER) and proliferation marker KI-67. In addition we qualitatively validate our method for tumor tissue segmentation and we obtain state of the art results on cell nuclei separation.
|Title of host publication||Proceedings of the MICCAI workshop on Histopathology Image Analysis|
|Publication status||Published - 2011|
|Event||MICCAI workshop on Histopathology Image Analysis : Clinical Challenges and Quantitative Image Analysis Solutions - Toronto, Canada|
Duration: 1 Jan 2011 → …
|Conference||MICCAI workshop on Histopathology Image Analysis : Clinical Challenges and Quantitative Image Analysis Solutions|
|Period||01/01/2011 → …|