Abstract
An auxiliary neural network is developed to solve the problem of preliminarily processing X-ray images to distinguish areas with lung and spine, and to mask unnecessary areas. Images processed with the neural network are used to study the main neural network for detecting pathology in lungs. A comparative analysis is performed of the quality of studying the main neural network on the basis of preliminarily processed images and initial ones.
Similar content being viewed by others
REFERENCES
Minyazev, R.Sh., Rumyantsev, A.A., Dyganova, S.A., and Baev, A.A., Bull. Russ. Acad. Sci.: Phys., 2018, vol. 82, no. 12, p. 1529.
Dyudin, M.V., Tomakova, R.A., and Tomakov, M.V., Biomed. Radioelektron., 2014, no. 9, p. 12.
Hoo-Chang, Sh., Kirk, R., Le, L., et al., Proc. IEEE Conf. on Computer Vision and Pattern Recognition, Las Vegas, 2016, p. 2497.
Richert, W. and Coelho, L.P., Building Machine Learning Systems with Python, Packt, 2013.
Szegedy, C., Liu, W., Jia, Y., et al., Proc. IEEE Conf. on Computer Vision and Pattern Recognition, Boston, 2015, p. 2559.
He, K., Zhang, X., Ren, S., et al., Proc. IEEE Conf. on Computer Vision and Pattern Recognition, Las Vegas, 2016, p. 770.
Thein, H.T.T., Adv. Comput. Sci. Int. J., 2014, vol. 3, no. 1, p. 67.
Gibadullin, R.F., Vershinin, I.S., and Minyazev, R.Sh., Proc. IEEE Int. Conf. on Industrial Engineering, Applications and Manufacturing, St. Petersburg, 2017. https://doi.org/10.1109/ICIEAM.2017.8076380
Saifullin, E.R., Ziganshin, Sh.G., Vankov, Y.V., et al., J. Fundam. Appl. Sci., 2017, vol. 9, no. 2, p. 1139.
Funding
This work was supported by the RF Ministry of Education and Science, state task under project no. 8.8017.2017/BCh.
Author information
Authors and Affiliations
Corresponding author
Additional information
Translated by Yu. Zikeeva
About this article
Cite this article
Minyazev, R.S., Rumyantsev, A.A., Baev, A.A. et al. Using a Neural Network to Separate Lungs in X-Ray Images. Bull. Russ. Acad. Sci. Phys. 83, 1494–1497 (2019). https://doi.org/10.3103/S1062873819120153
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.3103/S1062873819120153