Fatih SARIKOÇ, Adem KALINLI, Hülya AKGÜN, Figen ÖZTÜRK

An automated prognosis system for estrogen hormone status assessment in breast cancer tissue samples

Estrogen receptor (ER) status evaluation is a widely applied method in the prognosis of breast cancer. However, testing for the existence of the ER biomarker in a patient's tumor sample mainly depends on the subjective decisions of the doctors. The aim of this paper is to introduce the usage of a machine learning tool, functional trees (FTs), to attain an ER prognosis of the disease via an objective decision model. For this aim, 27 image files, each of which came from a biopsy sample of an invasive ductal carcinoma patient, were scanned and captured by a light microscope. From these images, 5150 nuclei were segmented with image processing methods. Several attributes, including statistical, wavelet, cooccurrence matrix, and Laws' texture features, were calculated inside the border area of each nucleus. A FT was trained over the feature dataset using a 10-fold cross-validation and then the obtained model was tested on a separate dataset. The assessment results of the model were compared with those of 2 experts. Consequently, the weighted kappa coefficient indicated a very good agreement (k= 0.899 and k= 0.927, P < 0.001) and the Spearman's rank order correlation showed a high level of correlation (r = 0.963 and r= 0.943, P < 0.001) between the results of the FT and those of the observers. The Wilcoxon test revealed that there was no significant difference between the results of the experts and the model (P = 0.051 and P = 0.316). Finally, it was concluded from the results that the FT could be used as a tool to support the decision of doctors by indicating consistent outputs and hence contribute to the objectiveness and reproducibility of the assessment results.

Anahtar Kelimeler:

Image processing, nucleus classification, segmentation, functional trees, estrogen receptor status evaluation, breast cancer prognosis, Allred scoring, machine learning

An automated prognosis system for estrogen hormone status assessment in breast cancer tissue samples

Keywords:

Image processing, nucleus classification, segmentation, functional trees, estrogen receptor status evaluation, breast cancer prognosis, Allred scoring, machine learning,

PDF

___

G. Da˘ glar, Y.N. Y¨ uksek, A.U. G¨ ozalan, T. T¨ ut¨ unc¨ u, Y. G¨ ung¨ or, N.A. Kama, “The prognostic value of histological grade in the outcome of patients with invasive breast cancer”, Turkish Journal of Medical Sciences, Vol. 40, pp. 7–15, 2010.
S. Sommer, S.A. Fuqua, “Estrogen receptor and breast cancer”, Seminars in Cancer Biology, Vol. 11, pp. 339–352, 200 J.M. Harvey, G.M. Clark, C.K. Osborne, D.C. Allred, “Estrogen receptor status by immunohistochemistry is superior to the ligand-binding assay for predicting response to adjuvant endocrine therapy in breast cancer”, Journal of Clinical Oncology, Vol. 17, pp. 1474–1481, 1999.
L.J. Layﬁeld, D. Gupta, E.E. Mooney, “Assessment of tissue estrogen and progesterone receptor levels: a survey of current practice, techniques, and quantitation methods”, Breast Journal, Vol. 6, pp. 189–196, 2000.
R.A. Walker, “Quantiﬁcation of immunohistochemistry – issues concerning methods, utility and semiquantitative assessment I”, Histopathology, Vol. 49, pp. 406–410, 2006.
S. Umemura, J. Itoh, H. Itoh, A. Serizawa, Y. Saito, Y. Suzuki, Y. Tokuda, T. Tajima, R.Y. Osamura, “Immunohistochemical evaluation of hormone receptors in breast cancer: which scoring system is suitable for highly sensitive procedures?” Applied Immunohistochemistry & Molecular Morphology, Vol. 12, pp. 8–13, 2004.
R.A. Walker, “Immunohistochemical markers as predictive tools for breast cancer”, Journal of Clinical Pathology, Vol. 61, pp. 689–696, 2008.
A. Qureshi, S. Pervez, “Allred scoring for ER reporting and its impact in clearly distinguishing ER negative from ER positive breast cancers”, Journal of the Pakistan Medical Association, Vol. 60, pp. 350–353, 2010.
T. Rudiger, H. Hoﬂer, H.H. Kreipe, H. Nizze, U. Pfeifer, H. Stein, F.E. Dallenbach, H.P. Fischer, M. Mengel, R. Wasielewski, H.K. Muller-Hermelink, “Quality assurance in immunohistochemistry: results of an interlaboratory trial involving 172 pathologists”, American Journal of Surgical Pathology, Vol. 26, pp. 873–882, 2002.
L.K. Diaz, N. Sneige, “Estrogen receptor analysis for breast cancer: current issues and keys to increasing testing accuracy”, Advances in Anatomic Pathology, Vol. 12, pp. 10–19, 2005.
C. Charpin, L. Andrac, M.C. Habib, H. Vacheret, L. Xerri, B. Devictor, M.N. Lavaut, M. Toga, “Immunodetection in ﬁne-needle aspirates and multiparametric (SAMBA) image analysis. Receptors (monoclonal antiestrogen and antiprogesterone) and growth fraction (monoclonal Ki67) evaluation in breast carcinomas”, Cancer, Vol. 63, pp. 863–872, 1989.
D.A. Turbin, S. Leung, M.C.U. Cheang, H.A. Kennecke, K.D. Montgomery, S. McKinney, D.O. Treaba, N. Boyd, L.C. Goldstein, S. Badve, A.M. Gown, M. Rijn, T.O. Nielsen, C.B. Gilks, D.G. Huntsman, “Automated quantitative analysis of estrogen receptor expression in breast carcinoma does not diﬀer from expert pathologist scoring: a tissue microarray study of 3,484 cases”, Breast Cancer Research and Treatment, Vol. 110, pp. 417–426, 2008.
H.A. Lehr, D.A. Mankoﬀ, D. Corwin, G. Santeusanio, A.M. Gown, “Application of Photoshop-based image analysis to quantiﬁcation of hormone receptor expression in breast cancer”, Journal of Histochemistry & Cytochemistry, Vol. 45, pp. 1559–1566, 1997.
R. Moﬁdi, R. Walsh, P.F. Ridgway, T. Crotty, E.W. McDermott, T.V. Keaveny, M.J. Duﬀy, A.D. Hill, N. O’Higgins, “Objective measurement of breast cancer oestrogen receptor status through digital image analysis”, European Journal of Surgical Oncology, Vol. 29, pp. 20–24, 2003.
Y. Hatanaka, K. Hashizume, K. Nitta, T. Kato, I. Itoh, Y. Tani, “Cytometrical image analysis for immunohistochemical hormone receptor status in breast carcinomas”, Pathology International, Vol. 53, pp. 693–699, 2003. R.A. McClelland, P. Finlay, K.J. Walker, D. Nicholson, J.F.R. Robertson, R.W. Blamey, R.I. Nicholson, “Automated quantitation of immunocytochemically localized estrogen receptors in human breast cancer”, Cancer Research, Vol. 50, pp. 3545–3550, 1990.
Y. Furukawa, I. Kimijima, R. Abe, “Immunohistochemical image analysis of estrogen and progesterone receptors in breast cancer”, Breast Cancer, Vol. 5, pp. 375–380, 1998.
G.G. Chung, M.P. Zerkowski, S. Ghosh, R.L. Camp, D.L. Rimm, “Quantitative analysis of estrogen receptor heterogeneity in breast cancer”, Laboratory Investigation, Vol. 87, pp. 662–669, 2007.
S. Gokhale, D. Rosen, N. Sneige, L.K. Diaz, E. Resetkova, A. Sahin, J. Liu, C.T. Albarracin, “Assessment of two automated imaging systems in evaluating estrogen receptor status in breast carcinoma”, Applied Immunohistochemistry & Molecular Morphology, Vol. 15, pp. 451–455, 2007.
R.L. Camp, G.G. Chung, D.L. Rimm, “Automated subcellular localization and quantiﬁcation of protein expression in tissue microarrays”, Nature Medicine, Vol. 8, pp. 1323–1328, 2002.
M.C. Lloyd, P.A. Nandyala, C.N. Purohit, N. Burke, D. Coppola, M.M. Bui, “Using image analysis as a tool for assessment of prognostic and predictive biomarkers for breast cancer: how reliable is it?”, Journal of Pathology Informatics, Vol. 1, p. 29, 2010.
K.L. Bolton, M.G. Closas, R.M. Pfeiﬀer, M.A. Duggan, W.J. Howat, S.M. Hewitt, X.R. Yang, R. Cornelison, S.L. Anzick, P. Meltzer, S. Davis, P. Lenz, J.D. Figueroa, P.D.P. Pharoah, M.E. Sherman, “Assessment of automated image analysis of breast cancer tissue microarrays for epidemiologic studies”, Cancer Epidemiology, Biomarkers & Prevention, Vol. 19, pp. 992–999, 2010.
S. Kostopoulos, D. Cavouras, A. Daskalakis, P. Bougioukos, P. Georgiadis, G.C. Kagadis, I. Kalatzis, P. Ravazoula, G. Nikiforidis, “Colour-texture based image analysis method for assessing the hormone receptors status in breast tissue sections”, Conference Proceedings of the IEEE Engineering in Medicine and Biology Society, pp. 4985–4988, 200
F. Schnorrenberg, N. Tsapatsoulis, C.S. Pattichis, C.N. Schizas, S. Kollias, M. Vassiliou, A. Adamou, K. Kyriacou, “Improved detection of breast cancer nuclei using modular neural networks”, IEEE Engineering in Medicine and Biology Magazine, Vol. 19, pp. 48–63, 2000.
S. Kostopoulos, D. Cavouras, A. Daskalakis, P. Ravazoula, G. Nikiforidis, “Image analysis system for assessing the estrogen receptor’s positive status in breast tissue carcinomas”, Proceedings of the International Special Topic Conference on Information Technology in Biomedicine, 2006.
L. Krecs´ ak, T. Micsik, G. Kiszler, T. Kren´ acs, D. Szab´ o, V. J´ on´ as, G. Cs´ asz´ ar, L. Czuni, P. Gurz´ o, L. Ficsor, B. Moln´ ar, “Technical note on the validation of a semi-automated image analysis software application for estrogen and progesterone receptor detection in breast cancer”, Diagnostic Pathology, Vol. 6, p. 6, 2011.
V.J Tuominen, S. Ruotoistenm¨ aki, A. Viitanen, M. Jumppanen, J. Isola, “ImmunoRatio: a publicly available web application for quantitative image analysis of estrogen receptor (ER), progesterone receptor (PR), and Ki-67”, Breast Cancer Research, Vol. 12, R56, 2010.
E. Rexhepaj, D.J. Brennan, P. Holloway, E.W. Kay, A.H. McCann, G. Landberg, M.J. Duﬀy, K. Jirstrom, W.M. Gallagher, “Novel image analysis approach for quantifying expression of nuclear proteins assessed by immunohistochemistry: application to measurement of oestrogen and progesterone receptor levels in breast cancer”, Breast Cancer Research, Vol. 10, R89, 2008.
S. Kostopoulos, D. Cavouras, A. Daskalakis, I. Kalatzis, P. Bougioukos, G. Kagadis, P. Ravazoula, G. Nikiforidis, “Assessing estrogen receptors’ status by texture analysis of breast tissue specimens and pattern recognition methods”, Proceedings of the 12th International Conference on Computer Analysis of Images and Patterns, pp. 221–228, 200 N. Otsu, “A threshold selection method from gray-level histograms”, IEEE Transactions on Systems, Man, and Cybernetics, Vol. 9, pp. 62–66, 1979.
J. Gama, “Functional trees”, Machine Learning, Vol. 55, pp. 219–250, 2004.
M.A. Hall, “Correlation-based feature subset selection for machine learning”, PhD, Department of Computer Science, University of Waikato, 1999.
I.O. Ellis, S.J. Schnitt, X. Sastre-Garau, G. Bussolati, F.A. Tavassoli, V. Eusebi, J.L. Peterse, K. Mukai, L. Tabar, J. Jacquemier, C.J. Cornelisse, A.J. Sasco, R. Kaaks, P. Pisani, D.E. Goldgar, P. Devilee, M.J. Cleton-Jansen, A.L. Borresen-Dale, L. van ’t Veer, A. Sapino, Invasive breast carcinoma, in: I.O. Ellis, S.J. Schnitt, X. Sastre-Garau, eds., World Health Organization Classiﬁcation of Tumors. Pathology and Genetics of Tumours of the Breast and Female Genital Organs, Lyon, France, IARC Press, pp. 40–42, 2003.
C.W. Elston, I.O. Ellis, “Pathological prognostic factors in breast cancer I. The value of histological grade in breast cancer: experience from a large study with long-term follow-up”, Histopathology, Vol. 19, pp. 403–410, 1991.
R.C. Gonzalez, R.E. Woods, Digital Image Processing, New Jersey, Prentice Hall, 2002.
R.M. Haralick, K. Shanmugam, I.H. Dinstein, “Textural features for image classiﬁcation”, IEEE Transactions on Systems, Man, and Cybernetics, Vol. 3, pp. 610–621, 1973.
D.A. Clausi, “An analysis of co-occurrence texture statistics as a function of grey level quantization”, Canadian Journal of Remote Sensing, Vol. 28, pp. 45–62, 2002.
L. Soh, C. Tsatsoulis, “Texture analysis of SAR sea ice imagery using gray level co-occurrence matrices”, IEEE Transactions on Geoscience and Remote Sensing, Vol. 37, pp. 780–795, 1999.
M. Sonka, V. Hlavac, R. Boyle, Image Processing, Analysis and Machine Vision, International Student Edition, Nashville, Thomas Nelson, 2008.
E. Alpaydin, Introduction to Machine Learning, Cambridge, MIT Press, 2004.
A.R. Webb, Statistical Pattern Recognition, 2nd ed., New York, Wiley, 2002.
C.J. Matheus, L. Rendell, “Constructive induction on decision trees”, Proceedings of the 11th International Joint Conference on Artiﬁcial Intelligence, Vol. 1, pp. 645–650, 1989.
J. Gama, “Probabilistic linear tree”, International Conference on Machine Learning, pp. 134–142, 1997.
J. Gama, P. Brazdil, “Cascade generalization”, Machine Learning, Vol. 41, pp. 315–343, 2000.
R. Quinlan, C4.5: Programs for Machine Learning, San Mateo, CA, USA, Morgan Kaufmann Publishers, 1993.
J. Platt, “Fast training of support vector machines using sequential minimal optimization”, in: B. Schoelkopf, C. Burges, A. Smola, eds., Advances in Kernel Methods – Support Vector Learning, Cambridge, MIT Press, 1999.
M. Hall, E. Frank, G. Holmes, B. Pfahringer, P. Reutemann, I.H. Witten, “The WEKA data mining software: an update”, ACM SIGKDD Explorations Newsletter, Vol. 11, 2009.
D.G. Altman, Practical Statistics for Medical Research, London, Chapman and Hall, 1991.
M. Cregger, A.J. Berger, D.L. Rimm, “Immunohistochemistry and quantitative analysis of protein expression”, Archives of Pathology and Laboratory Medicine, Vol. 130, pp. 1026–1030, 2006.
K. Prasad, P.B. Kumar, M. Chakravarthy, G. Prabhu, “Applications of ‘TissueQuant’- a color intensity quantiﬁcation tool for medical research”, Computer Methods and Programs in Biomedicine, Vol. 106, pp. 27–36, 2011.