Cascade pattern recognition structure for improving quantitative assessment of estrogen receptor status in breast tissue carcinomas.

OBJECTIVE To develop and validate a computer-based approach for the quantitative assessment of estrogen receptor (ER) status in breast tissue specimens for breast cancer management. STUDY DESIGN Microscopy images of 32 immunohistochemically (IHC) stained specimens of breast cancer biopsies were digitized and were primarily assessed for ER status (percentage of positively stained nuclei) by a histopathologist. A pattern recognition system was designed for automatically assessing the ER status of the IHC-stained specimens. Nuclei were automatically segmented from background by a pixel-based unsupervised clustering algorithm and were characterized as positively stained or unstained by a supervised classification algorithm. This cascade structure boosted the system's classification accuracy. RESULTS System performance in correctly characterizing the nuclei was 95.48%. When specifying each case's ER status, system performance was statistically not significantly different to the physician's assessment (p = 0.13); when ranking each case to a particular 5-scale ER-scoring system (giving the chance of response to endocrine treatment), the system's score and the physician's score were in agreement in 29 of 32 cases. CONCLUSION The need for reliable and operator independent ER-status estimation procedures may be served by the design of efficient pattern recognition systems to be employed as support opinion tools in clinical practice.

[1]  F Breitenecker,et al.  Modified true-color computer-assisted image analysis versus subjective scoring of estrogen receptor expression in breast cancer: a comparison. , 1999, Anticancer research.

[2]  Dimitris Glotsos,et al.  Computer-based malignancy grading of astrocytomas employing a support vector machine classifier, the WHO grading system and the regular hematoxylin-eosin diagnostic staining procedure. , 2004, Analytical and quantitative cytology and histology.

[3]  M. Duffy,et al.  Objective measurement of breast cancer oestrogen receptor status through digital image analysis. , 2003, European journal of surgical oncology : the journal of the European Society of Surgical Oncology and the British Association of Surgical Oncology.

[4]  Donald F. Specht,et al.  Probabilistic neural networks , 1990, Neural Networks.

[5]  Anil K. Jain.  Fundamentals of Digital Image Processing , 2018, Control of Color Imaging Systems.

[6]  F. Schnorrenberg,et al.  Improved detection of breast cancer nuclei using modular neural networks. , 2000, IEEE engineering in medicine and biology magazine : the quarterly magazine of the Engineering in Medicine & Biology Society.

[7]  T. T. Soong,et al.  Fundamentals of Probability and Statistics for Engineers , 2004 .

[8]  Anil K. Jain,et al.  Statistical Pattern Recognition: A Review , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  Maria Petrou,et al.  Histogram ratio features for color texture classification , 2003, Pattern Recognit. Lett..

[10]  Ying Sun,et al.  A hierarchical approach to color image segmentation using homogeneity , 2000, IEEE Trans. Image Process..

[11]  David A. Mankoff,et al.  Application of Photoshop-based Image Analysis to Quantification of Hormone Receptor Expression in Breast Cancer , 1997, The journal of histochemistry and cytochemistry : official journal of the Histochemistry Society.

[12]  N. Sneige,et al.  Estrogen Receptor Analysis for Breast Cancer: Current Issues and Keys to Increasing Testing Accuracy , 2005, Advances in anatomic pathology.

[13]  Geoffrey J McLachlan,et al.  Selection bias in gene extraction on the basis of microarray gene-expression data , 2002, Proceedings of the National Academy of Sciences of the United States of America.

[14]  Kimerly A Powell,et al.  Automated cell nuclear segmentation in color images of hematoxylin and eosin-stained breast biopsy. , 2003, Analytical and quantitative cytology and histology.

[15]  E. Sabo,et al.  The prognostic significance of the semiquantitatively determined estrogen receptor content of breast carcinomas. A clinicopathological study. , 2002, Pathology, research and practice.

[16]  Anthony Rhodes,et al.  Measurement of estrogen receptor status by immunocytochemistry in paraffin wax sections. , 2006, Methods in molecular medicine.

[17]  Panagiota Spyridonos,et al.  Neural network-based segmentation and classification system for automated grading of histologic sections of bladder carcinoma. , 2002, Analytical and quantitative cytology and histology.

[18]  P Karakitsos,et al.  Application of the learning vector quantizer to the classification of breast lesions. , 1997, Analytical and quantitative cytology and histology.

[19]  R M Levenson,et al.  Quantification of immunohistochemistry—issues concerning methods, utility and semiquantitative assessment II , 2006, Histopathology.

[20]  J. Fleiss.  Statistical methods for rates and proportions , 1974 .

[21]  N. Sneige,et al.  Interobserver agreement for estrogen receptor immunohistochemical analysis in breast cancer: a comparison of manual and computer-assisted scoring methods. , 2004, Annals of diagnostic pathology.

[22]  D Barnes,et al.  Immunohistochemical detection of steroid receptors in breast cancer: a working protocol , 2000, Journal of clinical pathology.