Morphological and spectral analysis of histological tissue with the use of deep convolutional networks
Abstract
The results of a study of the application of deep neural convolutional networks to hyperspectral images are presented.
About the Authors
S. V. Trukhan
United institute of informatics problems of National academy of sciences of Belarus
Belarus
Belarus
Trukhan Stanislau Vyacheslavovich - PG student of UIIP NAS of Belarus
220012, Republic of Belarus, Minsk, Surganova st., 6
tel.+375-29-614-37-27
A. M. Nedzved
United institute of informatics problems of National academy of sciences of Belarus
Belarus
Belarus
D.Sci, professor, chief researcher of UIIP NAS of Belarus
A. Kohler
NMBU
Belarus
Belarus
PhD, professor in physics at RealTek
References
1. Marker-free automated histopathological annotation of lung tumour subtypes by FTIR imaging / F. Großerueschkamp [et al.] // Analyst. 2015. Vol. 140, № 7. P. 2114–2120.
2. Robust classification of low-grade cervical cytology following analysis with ATR-FTIR spectroscopy and subsequent application of self-learning classifier eClass / J.G. Kelly [et al.] // Anal. Bioanal. Chem. 2010. Vol. 398, № 5. P. 2191–2201.
3. Distinction of cervical cancer biopsies by use of infrared microspectroscopy and probabilistic neural networks / A. Podshyvalov [et al.] // Appl. Opt. 2005. Vol. 44, № 18. P. 3725.
4. Udelhoven T., Novozhilov M., Schmitt J. The NeuroDeveloper®: a tool for modular neural classification of spectroscopic data // Chemom. Intell. Lab. Syst. 2003. Vol. 66, № 2. P. 219–226.
5. Evaluation and discrimination of simvastatin-induced structural alterations in proteins of different rat tissues by FTIR spectroscopy and neural network analysis / S. Garip [et al.] // Analyst. 2010. Vol. 135. P. 3233–3241.
6. Combining random forest and 2D correlation analysis to identify serum spectral signatures for neuro-oncology / B.R. Smith [et al.] // Analyst. 2016. Vol. 141, № 12. P. 3668–3678.
7. An investigation of the RWPE prostate derived family of cell lines using FTIR spectroscopy / M.J. Baker [et al.] // Analyst. 2010. Vol. 135, № 5. P. 887–894.
8. Vibrational biospectroscopy coupled with multivariate analysis extracts potentially diagnostic features in blood plasma/serum of ovarian cancer patients / G.L. Owens [et al.] // J. Biophotonics. 2014. Vol. 7, № 3–4. P. 200–209.
9. Fourier-transform infrared spectroscopy coupled with a classification machine for the analysis of blood plasma or serum: a novel diagnostic approach for ovarian cancer / K. Gajjar [et al.] // Analyst. 2013. Vol. 138, № 14. P. 3917.
10. Integrating spatial, morphological, and textural information for improved cell type differentiation using Raman microscopy / S.D. Krauß [et al.] // J. Chemom. 2018. Vol. 32, № 1.
11. Krizhevsky A., Sutskever I. , Hinton G.E. ImageNet Classification with Deep Convolutional Neural Networks // NIPS. 2012. P. 1–9.
12. Resonant Mie scattering in infrared spectroscopy of biological materials--understanding the «dispersion artefact» / P. Bassan [et al.] // Analyst. 2009. Vol. 134, № 8. P. 1586–1593.
13. Breiman L. Random Forests // Mach. Learn. 1999. Vol. 45, № 5. P. 1–35.
14. Ronneberger O., Fischer P., Brox T. U-Net: Convolutional Networks for Biomedical Image Segmentation // Miccai. 2015 P. 234–241.
Review
For citations:
Trukhan S.V., Nedzved A.M., Kohler A. Morphological and spectral analysis of histological tissue with the use of deep convolutional networks. Doklady BGUIR. 2019;(4):25-31. (In Russ.)
Views: 1470
Email this article 