Comparison of Monofractal, Multifractal and gray level Co-occurrence matrix algorithms in analysis of Breast tumor microscopic images for prognosis of distant metastasis risk
- 179 Downloads
Breast cancer prognosis is a subject undergoing intense study due to its high clinical relevance for effective therapeutic management and a great patient interest in disease progression. Prognostic value of fractal and gray level co-occurrence matrix texture analysis algorithms has been previously established on tumour histology images, but without any direct performance comparison. Therefore, this study was designed to compare the prognostic power of the monofractal, multifractal and co-occurrence algorithms on the same set of images. The investigation was retrospective, with 51 patients selected on account of non-metastatic IBC diagnosis, stage IIIB. Image analysis was performed on digital images of primary tumour tissue sections stained with haematoxylin/eosin. Bootstrap-corrected Cox proportional hazards regression P-values indicated a significant association with metastasis outcome of at least one of the features within each group. AUC values were far better for co-occurrence (0.66–0.77) then for fractal features (0.60–0.64). Correction by the split-sample cross-validation likewise indicated the generalizability only for the co-occurrence features, with their classification accuracies ranging between 67 and 72 %, while accuracies of monofractal and multifractal features were reduced to nearly random 52–55 %. These findings indicate for the first time that the prognostic value of texture analysis of tumour histology is less dependent on the morphological complexity of the image as measured by fractal analysis, but predominantly on the spatial distribution of the gray pixel intensities as calculated by the co-occurrence features.
KeywordsBreast cancer Histology texture Tumor GLCM Prognosis Metastasis Image analysis Fractal Multifractal Histomorphology
Compliance with ethical standards
Conflict of interest
The authors declare that they have no conflict of interest.
This work was supported by the research Grant No. 175068 from the Ministry of Education and Science of the Republic of Serbia.
- D. G. Altman, L. M. McShane, W. Sauerbrei, S. E. Taube, BMC Med 10, 51 (2012)Google Scholar
- A. Basavanhally, M. Feldman, N. Shih, C. Mies, J. Tomaszewski, S. Ganesan, A. Madabhushi, J Pathol Inform 2, S1 (2011)Google Scholar
- A.H. Beck, A.R. Sangoi, S. Leung, R.J. Marinelli, T.O. Nielsen, M.J. van de Vijver, R.B. West, M. van de Rijn, D. Koller, Sci Transl Med 3, 108ra113 (2011).Google Scholar
- D. R. Cox, J. R. Stat. Soc. Ser. B Methodol. 34, 187 (1972)Google Scholar
- R. Haralick, K. Shanmugam, I. H. Dinstein, Systems, Man and Cybernetics. IEEE Transactions on SMC-3, 610 (1973)Google Scholar
- D. Kolarevic, Z. Tomasevic, R. Dzodic, D. Gavrilovic, M. Zegarac, J BUON 17, 21 (2012)Google Scholar
- G. Landini, P. I. Murray, G. P. Misson, Investig. Ophthalmol. Vis. Sci. 36, 2749 (1995)Google Scholar
- M. Oger, M. Allaoui, N. Elie, J. Marnay, P. Herlin, B. Plancoulaine, J. Chasle, V. Becette, C. Bor-Angelier, Diagostic Pathology 8, S43 (2013)Google Scholar
- J. V. Raja, M. Khan, V. K. Ramachandra, O. Al-Kadi, Dento-Maxillo-Facial. Radiology 41, 475 (2012)Google Scholar
- E. R. Weibel, American Journal of Physiology 261, L361 (1991)Google Scholar