Automatic Extraction of Positive Cells in Tumor Immunohistochemical Pathology Image Based on YCbCr

摘要

A method is presented to automatically extract and analyze positive cells in tumor immunohistochemical pathology images based on the YCbCr color space. First, according to the distribution rules of positive cells in the YCbCr space, it uses the components of Y, Cb, and Cr as threshold conditions and leverages the maximal entropy principle to build a model to segment and extract positive cells. Then, it extracts the characteristic parameters for positive cell regions. Finally, it quantitatively analyzes the key parameters for positive cells, such as density and intensity. The experimental results showed that the method can be further extended to immunohistochemical standardization.