Image Segmentation of Nucleus Breast Cancer using Digital Image Processing

Abstract

: One of examination methods of breast cancer cells is using Immunohistochemistry (IHC). IHC is used to determine the status of Estrogen Receptor (ER) and/or Progesterone Receptor (PR). The bonding reaction occurring between the cell and the painting results in the color of the nucleus cell being blue which signifies the negative and brown ER/PR hormone for positive ER/PR. The given hormonal therapy will be effective to breast cancer patients if they have positive ER/PR receptors. Up to now the Anatomy Pathology specialist calculatses the percentage of positive cells that have been marked semiquantitatively. This is time-consuming, costly, subjective and tedious, thereby impacting the length of time required in determining appropriate therapy for breast cancer patients. This study analyze the image of IHC breast cancer to determine the assessment of ER/PR hormone receptor using image processing. The use of kernels of different sizes shows differences in the results of cell segmentation in connective tissue. The use of 3 × 3 and 1 × 1 kernels has indeed succeeded in removing cells in the connective tissue, but not all cells in the connective tissue can be identified. If this step has been completed, then the next process until cell count can be done.