Automated evaluation of HER-2/neu immunohistochemical expression in breast cancer using digital microscopy

HER-2/neu (HER2) has been shown to be a valuable biomarker for breast cancer. However, inter-observer variability has been reported in the evaluation of HER2 with immunohistochemistry. It has been suggested that automated computer-based evaluation can provide a consistent and objective measure of HER2 expression. In this manuscript, we present an automated method for the quantitative assessment of HER2 using digital microscopy. The method employs imaging algorithms on whole slide images of tissue specimens for the extraction of two features describing HER2 membrane staining, namely membrane staining completeness and membrane staining intensity. A classifier was trained to merge the extracted features into an overall slide assessment score. Preliminary results showed good agreement with the provided truth. The developed automated method has the potential to be used as a computer aid for the immunohistochemical evaluation of HER2 expression with the objective of increasing observer reproducibility.

[1]  J. Ross,et al.  The HER‐2/neu Oncogene in Breast Cancer: Prognostic Factor, Predictive Factor, and Target for Therapy , 1998, Stem cells.

[2]  K. Edmiston,et al.  HER-2 Status in Breast Cancer: Correlation of Gene Amplification by FISH With Immunohistochemistry Expression Using Advanced Cellular Imaging System , 2006, Applied immunohistochemistry & molecular morphology : AIMM.

[3]  W. McGuire,et al.  Human breast cancer: correlation of relapse and survival with amplification of the HER-2/neu oncogene. , 1987, Science.

[4]  Anthony Rhodes,et al.  American Society of Clinical Oncology/College of American Pathologists guideline recommendations for human epidermal growth factor receptor 2 testing in breast cancer. , 2006, Archives of pathology & laboratory medicine.

[5]  H. Tsuda,et al.  Quantitative immunohistochemical evaluation of HER2/neu expression with HercepTestTM in breast carcinoma by image analysis , 2001, Pathology international.

[6]  Hung Chiang,et al.  Interobserver reproducibility of Her-2/neu protein overexpression in invasive breast carcinoma using the DAKO HercepTest. , 2002, American journal of clinical pathology.

[7]  J. Ross,et al.  The HER‐2/neu Oncogene in Breast Cancer: Prognostic Factor, Predictive Factor, and Target for Therapy , 1998, The oncologist.

[8]  Pierre Soille,et al.  Morphological Image Analysis: Principles and Applications , 2003 .

[9]  Ioannis Pitas,et al.  Automated evaluation of her-2/neu status in breast tissue from fluorescent in situ hybridization images , 2005, IEEE Transactions on Image Processing.