På svenska

Presentation Information     2012-05-14 (14:15)   •  The seminar room at Vi2

Speaker Issac Niwas Swamidoss
Title Classification of immunostaining patterns in breast tissue from the Human Protein Atlas (HPA) using the wavelet transform
Abstract The Human Protein Atlas (HPA) is an effort to map the location of all human proteins (http://www.proteinatlas.org/ ). It contains a large number of histological images of sections from human tissue. The images are captured by a slide scanning microscope, and each image represents a section of a tissue stained with a general blue stain and specific antibodies labeled with a brown/black stain. In this research work, a new method based on undecimated anisotropic complex wavelets textural features is used to investigate antibody staining patterns in breast tissue samples. It is found that the method is useful for classifying different cellular staining patterns, that is nuclear versus cytoplasmic staining. The ultimate goal is to use the methods to evaluate similarities of staining patterns from so-called sibling antibodies, which are antibodies binding to different parts of the same human protein. This project is a collaboration work between the Centre for Image Analysis (CBA) and the Department of Immunology, Genetics and Pathology (IGP) at the Rudbeck Laboratory, Uppsala.