Statistical classification of erythrocytes in hereditary spherocytosis based on the spectral features of cell surfaces’ AFM images
Abstract
The method of classification of erythrocytes (red blood cells) based on spectral features of the cell surface images (of physical-mechanical properties maps) obtained with an atomic-force microscope (AFM) is proposed. Each scan line of the original AFM image is considered as a random sequence realization and the discrete Fourier transform is applied to compute its spectral features. The spectral estimates are smoothed on the map and the informative characteristics are computed as the medians of the spectrogram values for each frequency. The classification or two classes of erythrocytes (spherocytes and discocytes) taken from patients with hereditary spherocytosis was carried out by the obtained informative characteristics using the decision trees and boosted decision trees methods. The frequency interval was found with the best classification accuracy – over 82 % for the boosted decision trees method.
About the Authors
I. E. StarodubtsevBelarus
Yu. S. Kharin
Belarus
M. S. Abramovich
Belarus
References
1. Dokukin M., Sokolov I. Nanoscale compositional mapping of cells, tissues, and polymers with ringing mode of atomic force microscopy. Scientific Reports, 2017, vol. 7(1), р. 11828.
2. Suslov A., Chizhik S. Skanirujushhie zondovye mikroskopy (obzor) [Scanning probe microscopes (review)]. Materialy, tehnologii, instrumenty [Materials, Technologies, Tools], 1997, vol. 2, no. 3, рр. 78–89 (in Russian).
3. Starodubtseva M. N., Yegorenkov N. I., Starodubtsev I. E., Petrenyov D. R., Suslov A. A., Chizhik S. A. Temperature- and scale-dependent parameters of lateral force maps of cell surface. XIX Annual Linz Winter Workshop. Advances in Single-Molecule Research for Biology & Nanoscience, 3–6 February 2017, Linz, Austria. Linz, 2017, рр. 6–3.
4. Starodubtseva M. N., Starodubtsev I. E., Starodubtsev E. G. Novel fractal characteristic of atomic force microscopy images. Micron, 2017, vol. 96, рр. 96–102.
5. Kharin Y. Robustness in Statistical Pattern Recognition. Dordrecht, Kluwer, 1996, 302 p.
6. Jacobs T. D., Junge T., Pastewka L. Quantitative characterization of surface topography using spectral analysis. Surface Topography: Metrology and Properties, 2017, vol. 5(1), р. 013001.
7. Starodubtseva M. N., Mitsura E. F., Starodubtsev I. E., Chelnokova I. A., Yegorenkov N. I., Volkova L. I., Kharin Y. S. Nano- and microscale mechanical properties of erythrocytes in hereditary spherocytosis. The Journal of Biomechanics, 2019, vol. 83, рр. 1–8.
8. Anderson T. W. The Statistical Analysis of Time Series. New York, J. Wiley, 1971, 704 р.
9. Harrington P. Machine Learning in Action. New York, Manning, 2012, 382 p.
10. Hastie T., Tibshirani R., Friedman J. H. The Elements of Statistical Learning. New York, Springer Publ., 2009, 764 p.
Review
For citations:
Starodubtsev I.E., Kharin Yu.S., Abramovich M.S. Statistical classification of erythrocytes in hereditary spherocytosis based on the spectral features of cell surfaces’ AFM images. Informatics. 2019;16(3):7-13. (In Russ.)