Hostname: page-component-8448b6f56d-tj2md Total loading time: 0 Render date: 2024-04-25T05:57:17.369Z Has data issue: false hasContentIssue false
  • English
  • Français

Gray-Level Co-Occurrence Matrix Texture Analysis of Breast Tumor Images in Prognosis of Distant Metastasis Risk

Published online by Cambridge University Press:  10 April 2015

Tijana Vujasinovic ,
Jelena Pribic ,
Ksenija Kanjer ,
Nebojsa T. Milosevic ,
Zorica Tomasevic ,
Zorka Milovanovic ,
Dragica Nikolic-Vukosavljevic  and
Marko Radulovic
Tijana Vujasinovic
Affiliation:
Department of Experimental Oncology, Institute for Oncology and Radiology, 11000 Belgrade, Serbia
Jelena Pribic
Affiliation:
Department of Experimental Oncology, Institute for Oncology and Radiology, 11000 Belgrade, Serbia
Ksenija Kanjer
Affiliation:
Department of Experimental Oncology, Institute for Oncology and Radiology, 11000 Belgrade, Serbia
Nebojsa T. Milosevic
Affiliation:
Department of Biophysics, School of Medicine, University of Belgrade, Višegradska 26/2, 11000 Belgrade, Serbia
Zorica Tomasevic
Affiliation:
Daily Chemotherapy Hospital, Institute for Oncology and Radiology, 11000 Belgrade, Serbia
Zorka Milovanovic
Affiliation:
Department of Pathology and Cytology, Institute for Oncology and Radiology, 11000 Belgrade, Serbia
Dragica Nikolic-Vukosavljevic
Affiliation:
Department of Experimental Oncology, Institute for Oncology and Radiology, 11000 Belgrade, Serbia
Marko Radulovic*
Affiliation:
Department of Experimental Oncology, Institute for Oncology and Radiology, 11000 Belgrade, Serbia
*
*Corresponding author. marko@radulovic.net
Get access

Abstract

Owing to exceptional heterogeneity in the outcome of invasive breast cancer it is essential to develop highly accurate prognostic tools for effective therapeutic management. Based on this pressing need, we aimed to improve breast cancer prognosis by exploring the prognostic value of tumor histology image analysis. Patient group (n=78) selection was based on invasive breast cancer diagnosis without systemic treatment with a median follow-up of 147 months. Gray-level co-occurrence matrix texture analysis was performed retrospectively on primary tumor tissue section digital images stained either nonspecifically with hematoxylin and eosin or specifically with a pan-cytokeratin antibody cocktail for epithelial malignant cells. Univariate analysis revealed stronger association with metastasis risk by texture analysis when compared with clinicopathological parameters. The combination of individual clinicopathological and texture variables into composite scores resulted in further powerful enhancement of prognostic performance, with an accuracy of up to 90%, discrimination efficiency by the area under the curve [95% confidence interval (CI)] of 0.94 (0.87–0.99) and hazard ratio (95% CI) of 20.1 (7.5–109.4). Internal validation was successfully performed by bootstrap and split-sample cross-validation, suggesting that the models are generalizable. Whereas further validation is needed on an external set of patients, this preliminary study indicates the potential use of primary breast tumor histology texture as a highly accurate, simple, and cost-effective prognostic indicator of distant metastasis risk.

Keywords

breast cancertumorgray-level co-occurrence matrixmetastasispan-cytokeratin
Type
Biological Applications
Information
Microscopy and Microanalysis , Volume 21 , Issue 3 , June 2015 , pp. 646 - 654
Copyright
© Microscopy Society of America 2015 

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

Footnotes

a

These authors contributed equally to this work.

References

Adur, J., Carvalho, H.F., Cesar, C.L. & Casco, V.H. (2014). Nonlinear optical microscopy signal processing strategies in cancer. Cancer Inform 13, 67–76.CrossRefGoogle ScholarPubMed
Altman, D.G., Vergouwe, Y., Royston, P. & Moons, K.G. (2009). Prognosis and prognostic research: validating a prognostic model. BMJ 338, b605.CrossRefGoogle ScholarPubMed
Altman, D.G., McShane, L.M., Sauerbrei, W. & Taube, S.E. (2012). Reporting recommendations for tumor marker prognostic studies (REMARK): Explanation and elaboration. PLoS Med 9, e1001216.Google Scholar
Angell, H.K., Gray, N., Womack, C., Pritchard, D.I., Wilkinson, R.W. & Cumberbatch, M. (2013). Digital pattern recognition-based image analysis quantifies immune infiltrates in distinct tissue regions of colorectal cancer and identifies a metastatic phenotype. Br J Cancer 109, 1618–1624.Google Scholar
Brankovic-Magic, M.V., Nikolic-Vukosavljevic, D.B., Neskovic-Konstantinovic, Z.B., Kanjer, K.S. & Spuzic, I.V. (1992). Variations in the content of steroid receptors in breast cancer. Comparison between primary tumors and metastatic lesions. Acta Oncol 31, 629–633.CrossRefGoogle ScholarPubMed
Dunn, J.M., Hveem, T., Pretorius, M., Oukrif, D., Nielsen, B., Albregtsen, F., Lovat, L.B., Novelli, M.R. & Danielsen, H.E. (2011). Comparison of nuclear texture analysis and image cytometric DNA analysis for the assessment of dysplasia in Barrett’s oesophagus. Br J Cancer 105, 1218–1223.CrossRefGoogle ScholarPubMed
Edge, S.B., American Joint Committee on Cancer & American Cancer Society (2010). AJCC Cancer Staging Handbook: From the AJCC Cancer Staging Manual. New York, NY: Springer.Google Scholar
Efron, B. (1979). Bootstrap methods: Another look at the jackknife. Ann Stat 7, 1–26.CrossRefGoogle Scholar
Giordano, A., Gao, H., Anfossi, S., Cohen, E., Mego, M., Lee, B.N., Tin, S., De Laurentiis, M., Parker, C.A., Alvarez, R.H., Valero, V., Ueno, N.T., De Placido, S., Mani, S.A., Esteva, F.J., Cristofanilli, M. & Reuben, J.M. (2012). Epithelial-mesenchymal transition and stem cell markers in patients with HER2-positive metastatic breast cancer. Mol Cancer Ther 11, 2526–2534.Google Scholar
Gomez, W., Pereira, W.C. & Infantosi, A.F. (2012). Analysis of co-occurrence texture statistics as a function of gray-level quantization for classifying breast ultrasound. IEEE Trans Med Imaging 31, 1889–1899.Google Scholar
Guiu, S., Michiels, S., Andre, F., Cortes, J., Denkert, C., Di Leo, A., Hennessy, B.T., Sorlie, T., Sotiriou, C., Turner, N., Van de Vijver, M., Viale, G., Loi, S. & Reis-Filho, J.S. (2012). Molecular subclasses of breast cancer: How do we define them? The IMPAKT 2012 Working Group Statement. Ann Oncol 23, 2997–3006.Google Scholar
Haralick, R., Shanmugam, K. & Dinstein, I.H. (1973). Textural features for image classification. IEEE Trans Syst Man Cybern SMC-3, 610–621.Google Scholar
Holli, K., Laaperi, A.L., Harrison, L., Luukkaala, T., Toivonen, T., Ryymin, P., Dastidar, P., Soimakallio, S. & Eskola, H. (2010). Characterization of breast cancer types by texture analysis of magnetic resonance images. Acad Radiol 17, 135–141.Google Scholar
Justice, A.C., Covinsky, K.E. & Berlin, J.A. (1999). Assessing the generalizability of prognostic information. Ann Intern Med 130, 515–524.Google Scholar
Kok, M., Holm-Wigerup, C., Hauptmann, M., Michalides, R., Stal, O., Linn, S. & Landberg, G. (2009). Estrogen receptor-alpha phosphorylation at serine-118 and tamoxifen response in breast cancer. J Natl Cancer Inst 101, 1725–1729.CrossRefGoogle ScholarPubMed
Laurinavicius, A., Laurinaviciene, A., Dasevicius, D., Elie, N., Plancoulaine, B., Bor, C. & Herlin, P. (2012). Digital image analysis in pathology: Benefits and obligation. Anal Cell Pathol (Amst) 35, 75–78.CrossRefGoogle ScholarPubMed
Laurinavicius, A., Plancoulaine, B., Laurinaviciene, A., Herlin, P., Meskauskas, R., Baltrusaityte, I., Besusparis, J., Dasevicius, D., Elie, N., Iqbal, Y., Bor, C. & Ellis, I.O. (2014). A methodology to ensure and improve accuracy of Ki67 labelling index estimation by automated digital image analysis in breast cancer tissue. Breast Cancer Res 16, R35.CrossRefGoogle ScholarPubMed
Lonning, P.E., Knappskog, S., Staalesen, V., Chrisanthar, R. & Lillehaug, J.R. (2007). Breast cancer prognostication and prediction in the postgenomic era. Ann Oncol 18, 1293–1306.CrossRefGoogle ScholarPubMed
Losa, G.A. & Castelli, C. (2005). Nuclear patterns of human breast cancer cells during apoptosis: Characterisation by fractal dimension and co-occurrence matrix statistics. Cell Tissue Res 322, 257–267.Google Scholar
Loukas, C., Kostopoulos, S., Tanoglidi, A., Glotsos, D., Sfikas, C. & Cavouras, D. (2013). Breast cancer characterization based on image classification of tissue sections visualized under low magnification. Comput Math Methods Med 2013, 829461.Google Scholar
Mirza, A.N., Mirza, N.Q., Vlastos, G. & Singletary, S.E. (2002). Prognostic factors in node-negative breast cancer: A review of studies with sample size more than 200 and follow-up more than 5 years. Ann Surg 235, 10–26.CrossRefGoogle ScholarPubMed
Mohd Khuzi, A., Besar, R., Wan Zaki, W. & Ahmad, N. (2009). Identification of masses in digital mammogram using gray level co-occurrence matrices. Biomed Imaging Interv J 5, e17.CrossRefGoogle ScholarPubMed
Moons, K.G., Royston, P., Vergouwe, Y., Grobbee, D.E. & Altman, D.G. (2009). Prognosis and prognostic research: what, why, and how? BMJ 338, b375.Google Scholar
Neumeister, V., Agarwal, S., Bordeaux, J., Camp, R.L. & Rimm, D.L. (2010). In situ identification of putative cancer stem cells by multiplexing ALDH1, CD44, and cytokeratin identifies breast cancer patients with poor prognosis. Am J Pathol 176, 2131–2138.Google Scholar
Oger, M., Allaoui, M., Elie, N., Marnay, J., Herlin, P., Plancoulaine, B., Chasle, J., Becette, V. & Bor-Angelier, C. (2013). Impact of tumor heterogeneity on disease-free survival in a series of 368 patients treated for a breast cancer. Diagn Pathol 8, S43.Google Scholar
Pantic, I., Basta-Jovanovic, G., Starcevic, V., Paunovic, J., Suzic, S., Kojic, Z. & Pantic, S. (2013). Complexity reduction of chromatin architecture in macula densa cells during mouse postnatal development. Nephrology (Carlton) 18, 117–124.Google Scholar
Pantic, I., Nesic, D., Stevanovic, D., Starcevic, V., Pantic, S. & Trajkovic, V. (2013). Effects of ghrelin on the structural complexity of exocrine pancreas tissue architecture. Microsc Microanal 19, 553–558.Google Scholar
Pantic, I., Pantic, S. & Basta-Jovanovic, G. (2012). Gray level co-occurrence matrix texture analysis of germinal center light zone lymphocyte nuclei: Physiology viewpoint with focus on apoptosis. Microsc Microanal 18, 470–475.Google Scholar
Pantic, I., Pantic, S. & Paunovic, J. (2012). Aging increases nuclear chromatin entropy of erythroid precursor cells in mice spleen hematopoietic tissue. Microsc Microanal 18, 1054–1059.Google Scholar
Perez-Rivas, L.G., Jerez, J.M., Carmona, R., de Luque, V., Vicioso, L., Claros, M.G., Viguera, E., Pajares, B., Sanchez, A., Ribelles, N., Alba, E. & Lozano, J. (2014). A microRNA signature associated with early recurrence in breast cancer. PLoS One 9, e91884.CrossRefGoogle ScholarPubMed
Petushi, S., Garcia, F.U., Haber, M.M., Katsinis, C. & Tozeren, A. (2006). Large-scale computations on histology images reveal grade-differentiating parameters for breast cancer. BMC Med Imaging 6, 14.CrossRefGoogle ScholarPubMed
Rouzier, R., Pronzato, P., Chereau, E., Carlson, J., Hunt, B. & Valentine, W.J. (2013). Multigene assays and molecular markers in breast cancer: Systematic review of health economic analyses. Breast Cancer Res Treat 139, 621–637.CrossRefGoogle ScholarPubMed
Shamir, L., Wolkow, C.A. & Goldberg, I.G. (2009). Quantitative measurement of aging using image texture entropy. Bioinformatics 25, 3060–3063.CrossRefGoogle ScholarPubMed
Tambasco, M., Eliasziw, M. & Magliocco, A.M. (2010). Morphologic complexity of epithelial architecture for predicting invasive breast cancer survival. J Transl Med 8, 140.Google Scholar
Tambasco, M. & Magliocco, A.M. (2008). Relationship between tumor grade and computed architectural complexity in breast cancer specimens. Hum Pathol 39, 740–746.Google Scholar