informИнформатикаInformatics1816-03012617-6963UIIP NASBinform-351Research ArticleОБРАБОТКА СИГНАЛОВ, ИЗОБРАЖЕНИЙ, РЕЧИ, ТЕКСТА И РАСПОЗНАВАНИЕ ОБРАЗОВSIGNAL, IMAGE, SPEECH, TEXT PROCESSING AND PATTERN RECOGNITIONГЕНЕРАЦИЯ ИСКУССТВЕННЫХ РЕНТГЕНОВСКИХ ИЗОБРАЖЕНИЙ ГРУДНОЙ КЛЕТКИ С ИСПОЛЬЗОВАНИЕМ ГЕНЕРАТИВНО-СОСТЯЗАТЕЛЬНЫХ НЕЙРОННЫХ СЕТЕЙGENERATION OF ARTIFICIAL CHEST RADIOGRAPHS USING GENERATIVE ADVERSARIAL NEURAL NETWORKSКовалевВ. А.KovalevV. A.

кандидат технических наук, заведующий лабораторией анализа биомедицинских изображений

vassili.kovalev@gmail.comКозловскийС. А.KozlovskiS. A.

инженерпрограммист

kozlovski.serge@gmail.comКалиновскийА. А.KalinovskA. A.

научный сотрудник

gakarak@gmail.comОбъединенный институт проблем информатики Национальной академии наук Беларуси, МинскThe United Institute of Informatics Problems of the National Academy of Sciences of Belarus, Minsk201811042018152716Copyright © Ковалев В.А., Козловский С.А., Калиновский А.А., 20182018Ковалев В.А., Козловский С.А., Калиновский А.А.Kovalev V.A., Kozlovski S.A., Kalinovsk A.A.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://inf.grid.by/jour/article/view/351

This paper deals with the problem of generating artificial chest x-ray images which expected to be almost undistinguishable from real ones. Generation was performed using Generative Adversarial Nets (GAN). Similarity of resultant artificial images to the real ones was evaluated both by visual examination and by quantitative assessment using commonly known Local Binary Patterns. It was concluded that GANs can be successfully employed for generating realistically appearing artificial chest radiographs. However, an automatic procedure of selecting “most realistic” results is necessary for excluding the final visual quality control stage and making the whole generation process fully automatic.

нейронные сетигенеративно-состязательные сетиглубокое обучениемедицинские изображениярентгеновские изображения грудной клетиneural networksgenerative adversarial networksdeep learningmedical imaginglungs x-ray imagesРабота была выполнена при финансовой поддержке гранта Президента Республики Беларусь (распоряжение Президента Республики Беларусь № 32рп от 19 января 2018 г.).ReferencesA survey on deep learning in medical image analysis / G. Litjens [et al.] // Medical Image Analysis. – 2017. – Vol. 42. – P. 60–88.A survey on deep learning in medical image analysis / G. Litjens [et al.] // Medical Image Analysis. – 2017. – Vol. 42. – P. 60–88.A comparison of conventional and Deep Learning methods of image classification on a database of chest radiographs / V. А. Kovalev [et al.] // Intern. J. of Computer Assisted Radiology and Surgery. – 2017. – Vol. 12, suppl. 1. – P. S139–S140.A comparison of conventional and Deep Learning methods of image classification on a database of chest radiographs / V. А. Kovalev [et al.] // Intern. J. of Computer Assisted Radiology and Surgery. – 2017. – Vol. 12, suppl. 1. – P. S139–S140.Benchmarking the efficiency of Deep Learning methods on the problem of predicting subjects’ age by chest radiographs / V. А. Kovalev [et al.] // Proc. 3rd Intern. Conf. Big Data and Advanced Analytics. – Minsk : BSUIR, 2017. – P. 75–82.Benchmarking the efficiency of Deep Learning methods on the problem of predicting subjects’ age by chest radiographs / V. А. Kovalev [et al.] // Proc. 3rd Intern. Conf. Big Data and Advanced Analytics. – Minsk : BSUIR, 2017. – P. 75–82.Generative Adversarial Networks / I. J. Goodfellow [et al.] // arXiv.org [Electronic resource]. – 2014. – Mode of access : https://arxiv.org/pdf/1406.2661. – Date of access : 25.09.2017.Generative Adversarial Networks / I. J. Goodfellow [et al.] // arXiv.org [Electronic resource]. – 2014. – Mode of access : https://arxiv.org/pdf/1406.2661. – Date of access : 25.09.2017.Auto-encoding variational bayes / D. P. Kingma [et al.] // arXiv.org [Electronic resource]. – 2014. – Mode of access : https://arxiv.org/pdf/1312.6114. – Date of access : 25.09.2017.Auto-encoding variational bayes / D. P. Kingma [et al.] // arXiv.org [Electronic resource]. – 2014. – Mode of access : https://arxiv.org/pdf/1312.6114. – Date of access : 25.09.2017.LeCun, Y. Gradient-based learning applied to document recognition / Y. LeCun // Proc. of the IEEE. – 1998. – Vol. 86(11). – P. 2278–2324.LeCun, Y. Gradient-based learning applied to document recognition / Y. LeCun // Proc. of the IEEE. – 1998. – Vol. 86(11). – P. 2278–2324.Unsupervised representation learning with deep convolutional generative adversarial networks / A. Radford, L. Metz, S. Chintala // arXiv.org [Electronic resource]. – 2016. – Mode of access : https://arxiv.org/pdf/1511.06434. – Date of access : 25.09.2017.Unsupervised representation learning with deep convolutional generative adversarial networks / A. Radford, L. Metz, S. Chintala // arXiv.org [Electronic resource]. – 2016. – Mode of access : https://arxiv.org/pdf/1511.06434. – Date of access : 25.09.2017.DCGAN in tensorflow [Electronic resource]. – Mode of access : https://github.com/carpedm20/DCGAN-tensorflow. – Date of access : 25.09.2017.DCGAN in tensorflow [Electronic resource]. – Mode of access : https://github.com/carpedm20/DCGAN-tensorflow. – Date of access : 25.09.2017.Medical image synthesis with context-aware generative adversarial networks / D. Nie [et al.] // MICCAI, LNCS. –Springer, Cham, 2017. – Vol. 10435. – P. 417–425.Medical image synthesis with context-aware generative adversarial networks / D. Nie [et al.] // MICCAI, LNCS. –Springer, Cham, 2017. – Vol. 10435. – P. 417–425.Deep MR to CT Synthesis using Unpaired Data / J. M. Wolterink [et al.] // arXiv.org [Electronic resource]. – 2017. – Mode of access : https://arxiv.org/pdf/1708.01155. – Date of access : 22.09.2017.Deep MR to CT Synthesis using Unpaired Data / J. M. Wolterink [et al.] // arXiv.org [Electronic resource]. – 2017. – Mode of access : https://arxiv.org/pdf/1708.01155. – Date of access : 22.09.2017.Synthesis of positron emission tomography (PET) images via multi-channel Generative Adversarial Networks (GANs) / L. Bi [et al.] // Molecular Imaging, Reconstruction and Analysis of Moving Body Organs, and Stroke Imaging and Treatment. – Springer, Cham, 2017. – Vol. 10555. – P. 43–51.Synthesis of positron emission tomography (PET) images via multi-channel Generative Adversarial Networks (GANs) / L. Bi [et al.] // Molecular Imaging, Reconstruction and Analysis of Moving Body Organs, and Stroke Imaging and Treatment. – Springer, Cham, 2017. – Vol. 10555. – P. 43–51.

The authors declare that there are no conflicts of interest present.