HER-2/neu Breast Cancer Diagnosis Procedure Based on Histopathology Image Analysis

The human epidermal growth factor receptor 2 (HER-2/neu) is a biomarker, recognized as a valuable prognostic and predictive factor for breast cancer. In approximately 20% of primary breast cancers, the HER2/neu protein is over-expressed. The effect of this over-expression is an increase in receptor mediated intracellular signalling, directing the cancer cells into fast proliferation, which results in an aggressive form of breast cancer. By recent clinical research, a treatment procedure, with corresponding monoclonal antibodies specifically designed to target the HER2/neu receptor, was confirmed. Therefore, in modern breast cancer diagnostics, accurate recognition of the HER-2/neu positive breast cancer should be provided. This can be done, first by accurate segmentation of HER-2/neu over-expressed cancer cell membranes and then, by providing corresponding membrane connectivity analysis. This paper is a continuation of a previous research, in which the problem of cell membrane segmentation was considered. In the present study, we propose a HER-2/neu cancer cell membrane connectivity analysis, by examining corresponding shape coefficients. We performed statistical analysis, investigating the significance of the proposed coefficients in terms of HER-2/neu cancer cell recognition process. The proposed research gives a basis for the introduction of a complete HER-2/neu breast cancer recognition procedure.