SELECTION OF INTENSITY DISTRIBUTION CHARACTERISTICS IN THE COLOR CHANNELS OF FLUORESCENT IMAGES OF CANCER CELLS
Abstract
The different methods (correlation, logistic regression, median and random forest methods) for the selection of informative characteristics of the intensity distribution of fluorescent nuclei on multichannel luminescent images of cancer cells are considered. The input data are the three-channel RGB images. In total, 39 standard characteristics of distributions are studied, including 13 characteristics per each color channel. It is established that the use of 6 features permits to achieve the same classification accuracy as for using 39 features. Moreover, one can use only two features with an insignificant increase in the classification accuracy (by 0.005). It is proposed to use the data of the immunohistochemical analysis of biomarkers in breast cancer cells during the analysis of luminescent images when processing the results in oncocytology.
About the Authors
Y. U. LisitsaBelarus
4 Nezavisimosti Prosp., Minsk, 220030
V. V. Skakun
Belarus
4 Nezavisimosti Prosp., Minsk, 220030
V. V. Apanasovich
Belarus
4 Nezavisimosti Prosp., Minsk, 220030
References
1. B. Stewart, C. P. Wild. World Cancer Report 2014, Geneva, Switzerland, World Health Organization, International Agency for Research on Cancer, WHO Press (2015) 16—81
2. V. Mikkilineni, R. D. Mitra, J. Merritt, J. R. DiTonno, G. M. Church, B. Ogunnaike, J. S. Edwards. Biotechn. Bioengin., 86, N 2 (2004) 117—124
3. O. Ronneberger, D. Baddeley, F. Scheipl, P. J. Verveer, H. Burkhardt, C. Cremer, L. Fahrmeir, T. Cremer, B. Joffe. Chromosome Res., 16, N 3 (2008) 523—562
4. U. Neumann, N. Genze, D. Heider. BioData Mining, 10 (2017) 10:21
5. P.-W. Zhang, L. Chen, T. Huang, N. Zhang, X.-Y. Kong, Y.-D. Cai. PloS One, 10, N 3 (2015) e0123147; doi: 10.1371/journal.pone.0123147
6. J. Sonntag, C. Bender, Z. Soons, S. von der Heyde, R. Konig, S. Wiemann, H.-P. Sinn, A. Schneeweis, T. Beibarth, U. Korf. Translat. Proteom., 2 (2014) 52—59
7. D. K. Chanchala, D. W. May. IEEE J. Biomed. Health Inform., 21, N 1 (2017) 246—253
8. P. Stafford, Z. Cichacz, N. W. Woodbury, S. A. Johnston. Proc. Nat. Acad. Sci., 111, N 30 (2014) E3072—E3080
9. T. Nguyen, S. Nahavandi. IEEE Transact. Fuzzy System., 24, N 2 (2016) 273—287
10. T. Nguyen, A. Khosravi, D. Creighton, S. Nahavandi. PloS One, 10, N 3 (2015) e0120364
11. S. R. Eddy. Current Opinion in Struct. Biol., 6, N 3 (1996) 361—365
12. G. Ritter, H. Woodruff, S. Lowry, T. Isenhour. IEEE Transact. Inform. Theory, 21, N 6 (1975) 665—669
13. M. A. Hearst, S. T. Dumais, E. Osman, J. Platt, B. Scholkopf. IEEE Intell. System. Appl., 13, N 4 (1998) 18—28
14. W. Pang, H. Jiang, S. Li. Biomed. Res. Int. (2017) 1—14
15. H. M. Kluger, R. Halaban, D. L. Rimm. Cancer Res., 64, N 23 (2004) 8767—8772
16. G. G. Chung, M. P. Zerkowski, S. Ghosh, R. L. Camp, D. L. Rimm. Lab. Invest., 87, N 7 (2007) 662—669
17. R. L. Camp, G. G. Chung, D. L. Rimm. Nature Med., 8, N 11 (2002) 1323—1327
18. M. K. Szeszel, C. L. Crisman, L. Crow, S. McMullen, J. M. Major, L. Natarajan, A. Saquib, J. R. Feramisco, L. M. Wasserman. J. Histochem. Cytochem., 53, N 6 (2005) 753—762
19. Е. В. Лисица, Н. Н. Яцков, В. В. Апанасович, Т. В. Апанасович, М. М. Шитик. Журн. прикл. спектр., 81, № 6 (2014) 907—913 [Y. V. Lisitsa, M. M. Yatskou, V. V. Apanasovich, T. V. Apanaso- vich, M. M. Shytsik. J. Appl. Spectr., 81 (2014) 996—1003]
20. T. G. Nick. Methods Mol. Biol., 404 (2007) 33—52
21. F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Biondel, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, E. Duchesnay. J. Mach. Learn. Res., 12 (2011) 2825—2830
Review
For citations:
Lisitsa Y.U., Skakun V.V., Apanasovich V.V. SELECTION OF INTENSITY DISTRIBUTION CHARACTERISTICS IN THE COLOR CHANNELS OF FLUORESCENT IMAGES OF CANCER CELLS. Zhurnal Prikladnoii Spektroskopii. 2019;86(3):394-400. (In Russ.)