Fluorescence in situ hybridization is a widely used diagnostic procedure in pathology. This method can reveal the genetic background of malignant lesions. The aim of our study was to develop and optimize an image segmentation algorithm specifically for FISH quantification in breast cancer tissue. Moreover, we aimed to validate the results of our algorithm and to compare them with a semi-automated assessment (i.e. scoring on a computer screen) and the results of the conventional (i.e. manual microscopic) IHC quantification.