{"id":7022,"date":"2021-06-09T10:37:37","date_gmt":"2021-06-09T07:37:37","guid":{"rendered":"http:\/\/journals.khnu.km.ua\/vestnik\/?p=7022"},"modified":"2021-08-04T13:51:28","modified_gmt":"2021-08-04T10:51:28","slug":"%d1%96%d0%bd%d1%84%d0%be%d1%80%d0%bc%d0%b0%d1%86%d1%96%d0%b9%d0%bd%d0%b0-%d1%82%d0%b5%d1%85%d0%bd%d0%be%d0%bb%d0%be%d0%b3%d1%96%d1%8f-%d0%b2%d1%96%d0%b7%d1%83%d0%b0%d0%bb%d1%8c%d0%bd%d0%be%d0%b3%d0%be","status":"publish","type":"post","link":"https:\/\/journals.khnu.km.ua\/vestnik\/?p=7022","title":{"rendered":"\u0406\u043d\u0444\u043e\u0440\u043c\u0430\u0446\u0456\u0439\u043d\u0430 \u0442\u0435\u0445\u043d\u043e\u043b\u043e\u0433\u0456\u044f \u0432\u0456\u0437\u0443\u0430\u043b\u044c\u043d\u043e\u0433\u043e \u0430\u043d\u0430\u043b\u0456\u0437\u0443 \u0440\u0435\u043d\u0433\u0435\u043d\u0456\u0432\u0441\u044c\u043a\u0438\u0445 \u0437\u043e\u0431\u0440\u0430\u0436\u0435\u043d\u044c \u0434\u043b\u044f \u0456\u043d\u0442\u0435\u0440\u043f\u0440\u0435\u0442\u0430\u0446\u0456\u0457 \u0440\u0435\u0437\u0443\u043b\u044c\u0442\u0430\u0442\u0456\u0432 \u0434\u0456\u0430\u0433\u043d\u043e\u0441\u0442\u0443\u0432\u0430\u043d\u043d\u044f \u043f\u043d\u0435\u0432\u043c\u043e\u043d\u0456\u0457"},"content":{"rendered":"

<\/p>\n

\u0406\u041d\u0424\u041e\u0420\u041c\u0410\u0426\u0406\u0419\u041d\u0410 \u0422\u0415\u0425\u041d\u041e\u041b\u041e\u0413\u0406\u042f \u0412\u0406\u0417\u0423\u0410\u041b\u042c\u041d\u041e\u0413\u041e \u0410\u041d\u0410\u041b\u0406\u0417\u0423 \u0420\u0415\u041d\u0422\u0413\u0415\u041d\u0406\u0412\u0421\u042c\u041a\u0418\u0425 \u0417\u041e\u0411\u0420\u0410\u0416\u0415\u041d\u042c \u0414\u041b\u042f \u0406\u041d\u0422\u0415\u0420\u041f\u0420\u0415\u0422\u0410\u0426\u0406\u0407 \u0420\u0415\u0417\u0423\u041b\u042c\u0422\u0410\u0422\u0406\u0412 \u0414\u0406\u0410\u0413\u041d\u041e\u0421\u0422\u0423\u0412\u0410\u041d\u041d\u042f \u041f\u041d\u0415\u0412\u041c\u041e\u041d\u0406\u0407<\/p>\n

INFORMATION TECHNOLOGY OF VISUAL ANALYSIS OF X-RAY IMAGES FOR INTERPRETATION OF PNEUMONIA DIAGNOSTIC RESULTS<\/p>\n

\u0421\u0442\u043e\u0440\u0456\u043d\u043a\u0438: 52-55. \u041d\u043e\u043c\u0435\u0440: \u21162, 2021 (295)\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0<\/strong> \"\"<\/a>
\n\u0410\u0432\u0442\u043e\u0440\u0438:<\/strong>
\n\u041e.\u0412. \u0411\u0410\u0420\u041c\u0410\u041a, \u041f.\u041c. \u0420\u0410\u0414\u042e\u041a
\n\u0425\u043c\u0435\u043b\u044c\u043d\u0438\u0446\u044c\u043a\u0438\u0439 \u043d\u0430\u0446\u0456\u043e\u043d\u0430\u043b\u044c\u043d\u0438\u0439 \u0443\u043d\u0456\u0432\u0435\u0440\u0441\u0438\u0442\u0435\u0442
\nDOI:<\/strong> https:\/\/www.doi.org\/10.31891\/2307-5732-2021-295-2-52-55<\/a>
\n\u0420\u0435\u0446\u0435\u043d\u0437\u0456\u044f\/Peer review :<\/strong> 03.03.2021 \u0440.
\n\u041d\u0430\u0434\u0440\u0443\u043a\u043e\u0432\u0430\u043d\u0430\/Printed :<\/strong> 02.06.2021 \u0440.<\/p>\n

\u0410\u043d\u043e\u0442\u0430\u0446\u0456\u044f \u043c\u043e\u0432\u043e\u044e \u043e\u0440\u0438\u0433\u0456\u043d\u0430\u043b\u0443<\/strong><\/p>\n

\u041d\u0430 \u0441\u044c\u043e\u0433\u043e\u0434\u043d\u0456 \u043f\u043d\u0435\u0432\u043c\u043e\u043d\u0456\u044f \u0454 \u043e\u0434\u043d\u0438\u043c \u0456\u0437 \u043f\u043e\u0448\u0438\u0440\u0435\u043d\u0456\u0448\u0438\u0445 \u0442\u0430 \u043d\u0430\u0439\u0431\u0456\u043b\u044c\u0448 \u0441\u0435\u0440\u0439\u043e\u0437\u043d\u0438\u0445 \u043b\u0435\u0433\u0435\u043d\u0435\u0432\u0438\u0445 \u0437\u0430\u0445\u0432\u043e\u0440\u044e\u0432\u0430\u043d\u044c \u0443 \u0432\u0441\u044c\u043e\u043c\u0443 \u0441\u0432\u0456\u0442\u0456. \u0420\u0430\u043d\u043d\u0454 \u0434\u0456\u0430\u0433\u043d\u043e\u0441\u0442\u0443\u0432\u0430\u043d\u043d\u044f \u043f\u043d\u0435\u0432\u043c\u043e\u043d\u0456\u0457 \u0454 \u043a\u043b\u044e\u0447\u043e\u0432\u0438\u043c \u0447\u0438\u043d\u043d\u0438\u043a\u043e\u043c \u0457\u0457 \u0443\u0441\u043f\u0456\u0448\u043d\u043e\u0433\u043e \u043b\u0456\u043a\u0443\u0432\u0430\u043d\u043d\u044f. \u0414\u043b\u044f \u0440\u043e\u0437\u0432\u2019\u044f\u0437\u0430\u043d\u043d\u044f \u0430\u043a\u0442\u0443\u0430\u043b\u044c\u043d\u043e\u0433\u043e \u0437\u0430\u0432\u0434\u0430\u043d\u043d\u044f \u0432 \u0433\u0430\u043b\u0443\u0437\u0456 \u0446\u0438\u0444\u0440\u043e\u0432\u043e\u0433\u043e \u0434\u0456\u0430\u0433\u043d\u043e\u0441\u0442\u0443\u0432\u0430\u043d\u043d\u044f \u0432 \u0446\u0456\u0439 \u043f\u0440\u043e\u043f\u043e\u043d\u0443\u0454\u0442\u044c\u0441\u044f \u0456\u043d\u0444\u043e\u0440\u043c\u0430\u0446\u0456\u0439\u043d\u0430 \u0442\u0435\u0445\u043d\u043e\u043b\u043e\u0433\u0456\u044f \u0432\u0456\u0437\u0443\u0430\u043b\u044c\u043d\u043e\u0433\u043e \u0430\u043d\u0430\u043b\u0456\u0437\u0443 \u0440\u0435\u043d\u0442\u0433\u0435\u043d\u0456\u0432\u0441\u044c\u043a\u0438\u0445 \u0437\u043e\u0431\u0440\u0430\u0436\u0435\u043d\u044c \u0434\u043b\u044f \u043f\u043e\u044f\u0441\u043d\u0435\u043d\u043d\u044f \u0440\u0435\u0437\u0443\u043b\u044c\u0442\u0430\u0442\u0456\u0432 \u0434\u0456\u0430\u0433\u043d\u043e\u0441\u0442\u0443\u0432\u0430\u043d\u043d\u044f \u043f\u043d\u0435\u0432\u043c\u043e\u043d\u0456\u0457. \u0412 \u043e\u0441\u043d\u043e\u0432\u0456 \u0442\u0435\u0445\u043d\u043e\u043b\u043e\u0433\u0456\u0457 \u0437\u0430\u043a\u043b\u0430\u0434\u0435\u043d\u043e \u043c\u043e\u0434\u0435\u043b\u044c \u043a\u043b\u0430\u0441\u0438\u0444\u0456\u043a\u0430\u0446\u0456\u0457 \u043d\u0430 \u043e\u0441\u043d\u043e\u0432\u0456 \u0437\u0433\u043e\u0440\u0442\u043a\u043e\u0432\u043e\u0457 \u043d\u0435\u0439\u0440\u043e\u043d\u043d\u043e\u0457 \u043c\u0435\u0440\u0435\u0436\u0456 \u0434\u043b\u044f \u0432\u0438\u043b\u0443\u0447\u0435\u043d\u043d\u044f \u0441\u043b\u0430\u0431\u043e \u0432\u0438\u0440\u0430\u0436\u0435\u043d\u0438\u0445 \u043e\u0437\u043d\u0430\u043a \u0440\u0430\u043d\u043d\u044c\u043e\u0457 \u0432\u0456\u0440\u0443\u0441\u043d\u043e\u0457 \u043f\u043d\u0435\u0432\u043c\u043e\u043d\u0456\u0457 \u0442\u0430 \u043c\u043e\u0434\u0438\u0444\u0456\u043a\u043e\u0432\u0430\u043d\u0438\u0439 \u043c\u0435\u0442\u043e\u0434 \u0432\u0456\u0434\u043c\u0456\u043d\u043d\u043e\u0457 \u043b\u043e\u043a\u0430\u043b\u0456\u0437\u0430\u0446\u0456\u0457 \u0434\u043b\u044f \u0456\u043d\u0442\u0435\u0440\u043f\u0440\u0435\u0442\u0430\u0446\u0456\u0457 \u0440\u0435\u0437\u0443\u043b\u044c\u0442\u0430\u0442\u0456\u0432 \u043a\u043b\u0430\u0441\u0438\u0444\u0456\u043a\u0430\u0446\u0456\u0457. \u041c\u0435\u0442\u043e\u0434 \u0456\u043d\u0442\u0435\u0440\u043f\u0440\u0435\u0442\u0430\u0446\u0456\u0457 \u043f\u043e\u043b\u044f\u0433\u0430\u0454 \u0432 \u0437\u0430\u0441\u0442\u043e\u0441\u0443\u0432\u0430\u043d\u043d\u0456 \u0437\u0432\u0430\u0436\u0435\u043d\u0438\u0445 \u0433\u0440\u0430\u0434\u0456\u0454\u043d\u0442\u0456\u0432 \u0434\u043e \u043c\u0430\u043f \u0430\u043a\u0442\u0438\u0432\u0430\u0446\u0456\u0457 \u043a\u043b\u0430\u0441\u0456\u0432. \u041f\u043e\u0434\u0456\u0431\u043d\u0430 \u043c\u043e\u0434\u0438\u0444\u0456\u043a\u0430\u0446\u0456\u044f \u0437\u0430\u0431\u0435\u0437\u043f\u0435\u0447\u0443\u0454 \u0432\u0456\u0434\u043c\u0456\u043d\u043d\u0443 \u043b\u043e\u043a\u0430\u043b\u0456\u0437\u0430\u0446\u0456\u044e \u0430\u043d\u043e\u043c\u0430\u043b\u044c\u043d\u0438\u0445 \u0437\u043e\u043d \u043d\u0430 \u0440\u0435\u043d\u0442\u0433\u0435\u043d\u043e\u0433\u0440\u0430\u043c\u0430\u0445, \u0449\u043e \u0434\u0430\u0454 \u0437\u043c\u043e\u0433\u0443 \u0432\u0438\u043b\u0443\u0447\u0438\u0442\u0438 \u0446\u0456\u043b\u044c\u043e\u0432\u0456 \u0441\u043b\u0430\u0431\u043a\u043e \u0432\u0438\u0440\u0430\u0436\u0435\u043d\u0456 \u043e\u0437\u043d\u0430\u043a\u0438 \u0440\u0430\u043d\u043d\u044c\u043e\u0457 \u043f\u043d\u0435\u0432\u043c\u043e\u043d\u0456\u0457. \u0412\u0456\u0434\u043f\u043e\u0432\u0456\u0434\u043d\u043e \u0434\u043e \u043e\u0431\u0447\u0438\u0441\u043b\u044e\u0432\u0430\u043b\u044c\u043d\u0438\u0445 \u0435\u043a\u0441\u043f\u0435\u0440\u0438\u043c\u0435\u043d\u0442\u0456\u0432, \u0437\u0430\u043f\u0440\u043e\u043f\u043e\u043d\u043e\u0432\u0430\u043d\u0430 \u0456\u043d\u0444\u043e\u0440\u043c\u0430\u0446\u0456\u0439\u043d\u0430 \u0442\u0435\u0445\u043d\u043e\u043b\u043e\u0433\u0456\u044f \u043c\u043e\u0436\u0435 \u0431\u0443\u0442\u0438 \u0435\u0444\u0435\u043a\u0442\u0438\u0432\u043d\u0438\u043c \u0437\u0430\u0441\u043e\u0431\u043e\u043c \u0434\u043b\u044f \u043c\u0438\u0442\u0442\u0454\u0432\u043e\u0433\u043e \u0434\u0456\u0430\u0433\u043d\u043e\u0441\u0442\u0443\u0432\u0430\u043d\u043d\u044f \u0432 \u0440\u0430\u0437\u0456 \u043f\u0435\u0440\u0448\u0438\u0445 \u043f\u0456\u0434\u043e\u0437\u0440 \u043d\u0430 \u0432\u0438\u044f\u0432\u043b\u0435\u043d\u043d\u044f \u043f\u043d\u0435\u0432\u043c\u043e\u043d\u0456\u0457.
\n\u041a\u043b\u044e\u0447\u043e\u0432\u0456 \u0441\u043b\u043e\u0432\u0430:<\/strong> \u043f\u043d\u0435\u0432\u043c\u043e\u043d\u0456\u044f, \u0437\u0433\u043e\u0440\u0442\u043a\u043e\u0432\u0430 \u043d\u0435\u0439\u0440\u043e\u043d\u043d\u0430 \u043c\u0435\u0440\u0435\u0436\u0430, \u0440\u0435\u043d\u0442\u0433\u0435\u043d\u0456\u0432\u0441\u044c\u043a\u0435 \u0437\u043e\u0431\u0440\u0430\u0436\u0435\u043d\u043d\u044f \u0433\u0440\u0443\u0434\u043d\u043e\u0457 \u043a\u043b\u0456\u0442\u0438\u043d\u0438, \u0432\u0456\u0437\u0443\u0430\u043b\u044c\u043d\u0438\u0439 \u0430\u043d\u0430\u043b\u0456\u0437, \u043c\u0430\u043f\u0438 \u0430\u043a\u0442\u0438\u0432\u0430\u0446\u0456\u0457 \u043a\u043b\u0430\u0441\u0456\u0432.<\/p>\n

\u0420\u043e\u0437\u0448\u0438\u0440\u0435\u043d\u0430 \u0430\u043d\u043e\u0442\u0430\u0446\u0456\u044f \u0430\u043d\u0433\u043b\u0456\u0439\u0441\u044c\u043a\u043e\u044e \u043c\u043e\u0432\u043e\u044e<\/strong><\/p>\n

To date, pneumonia is one of the most common and severe lung diseases in the world. Early diagnosis of pneumonia is a crucial factor in its successful treatment. Over the last decade, automated analysis of chest X-rays has been recognized as an effective tool for diagnosing lung diseases. However, the problem of implementing and configuring methods that explain the results of digital diagnosis remains acute. Convolutional neural networks now show state-of-the-art results in the identification of diseases on X-ray. Therefore, to address the urgent issue in digital diagnosis, we propose information technology for visual analysis of X-ray images to explain the results of diagnosing pneumonia. The technology comprises a classification model based on a convolutional neural network to remove mild features of early viral pneumonia and a modified method of different localization to interpret the classification results. The method of interpretation is to apply weighted gradients to class activation maps. It distinguishes lung masks in the X-ray image and imposes thermal maps with a color gradient from blue to bright red. The red color corresponds to the most probable location of the pneumonia features in the radiograph. Such a modification provides excellent localization of abnormal areas on radiographs, removing the mild target features of early pneumonia. It should be noted that our model based on the convolutional network surpassed other classifiers in precision (98.5%) but slightly conceded in classification accuracy (96.1%) and recall (93.6%). Also, it shows relatively low false positive and false negative rates, with 1.4% and 6.4%, respectively. Overall, according to computational experiments, the proposed information technology can be an effective tool for instant diagnosis in the first suspicion of pneumonia.
\nKeywords:<\/strong> pneumonia, convolutional neural network, chest X-ray, visual analysis, class activation maps.<\/p>\n

References<\/strong><\/p>\n

    \n
  1. Raghu G. COVID-19 interstitial pneumonia: Monitoring the clinical course in survivors \/ G.Raghu, K.C.\u00a0Wilson \/\/ The Lancet Respiratory Medicine. \u2013 2020. \u2013 Volume 8. \u2013 Issue 9. \u2013 P. 839\u2013842.<\/li>\n
  2. Wang X. ChestX-Ray8: Hospital-scale chest X-Ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases \/ X.\u00a0Wang, Y.\u00a0Peng, L.\u00a0Lu, Z.\u00a0Lu, M.\u00a0Bagheri et al. \/\/ Proceedings of the 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR-2017, Honolulu, HI, USA, July 21\u201326, 2017. \u2013 IEEE Inc., 2017. \u2013 P. 3462\u20133471. \u2013 DOI: https:\/\/doi.org\/10.1109\/CVPR.2017.369<\/a><\/li>\n
  3. Simonyan K. Very deep convolutional networks for large-scale image recognition \/ K.\u00a0Simonyan, A.\u00a0Zisserman \/\/ Proceedings of the 3rd International Conference on Learning Representations, ICLR-2015, San Diego, CA, USA, May 7\u20139, 2015. \u2013 ICLR.org., 2015 \u2013 P.\u00a01\u201314.<\/li>\n
  4. Szegedy C. Inception-v4, Inception-ResNet and the impact of residual connections on learning \/ C.\u00a0Szegedy, S.\u00a0Ioffe, V.\u00a0Vanhoucke, A.\u00a0Alemi \/\/ Proceedings of the 31 AAAI Conference on Artificial Intelligence, AAAI-2017, San Francisco, CA, USA, Feb 4\u201310, 2017. \u2013 AAAI Press, 2017. \u2013 P.\u00a04278\u20134284.<\/li>\n
  5. Radiuk P. Applying 3D U-Net architecture to the task of multi-organ segmentation in computed tomography \/ P.\u00a0Radiuk \/\/ Applied Computer Systems. \u2013 2020. \u2013 Volume 25. \u2013 Issue 1. \u2013 P. 43\u201350.<\/li>\n
  6. Mahmud T. CovXNet: A multi-dilation convolutional neural network for automatic COVID-19 and other pneumonia detection from chest X-ray images with transferable multi-receptive feature optimization \/ T.\u00a0Mahmud, M.A.\u00a0Rahman, S.A.\u00a0Fattah \/\/ Computers in Biology and Medicine. \u2013 2020. \u2013 Volume 122. \u2013 P. 103869.<\/li>\n
  7. Sandler M. MobileNetV2: Inverted residuals and linear bottlenecks \/ M.\u00a0Sandler, A.\u00a0Howard, M.\u00a0Zhu, A.\u00a0Zhmoginov, L.\u00a0Chen \/\/ Proceedings of the 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR-2020, Salt Lake City, UT, USA, June 18\u201323, 2018. \u2013 IEEE Inc., 2018. \u2013 P.\u00a04510\u20134520.<\/li>\n
  8. Krak\u00a0Iu. Detection of early pneumonia on individual CT scans with dilated convolutions \/ Iu.\u00a0Krak\u00a0, O.\u00a0Barmak, P.\u00a0Radiuk \/\/ Proceedings of 2nd International Workshop on Intelligent Information Technologies & Systems of Information Security, IntelITSIS-2021, Khmelnytskyi, Ukraine, March 24\u201326, 2021. \u2013 CEUR-WP, 2021 \u2013 Volume 2853. \u2013 P. 214\u2013227.<\/li>\n
  9. Selvaraju R.R. Grad-CAM: Visual explanations from deep networks via gradient-based localization \/ R.R.\u00a0Selvaraju, M.\u00a0Cogswell, A.\u00a0Das, R.\u00a0Vedantam, D.\u00a0Parikh, D.\u00a0Batra \/\/ International Journal of Computer Vision. \u2013 2020. \u2013 Volume 128. \u2013 Issue 2. \u2013 P. 336\u2013359. \u2013 DOI: https:\/\/doi.org\/10.1007\/s11263-019-01228-7<\/a><\/li>\n
  10. Irvin J. CheXpert: A large chest radiograph dataset with uncertainty labels and expert comparison \/ J.\u00a0Irvin, P.\u00a0Rajpurkar, M.\u00a0Ko, Y.\u00a0Yu, S.\u00a0Ciurea-Ilcus et al. \/\/ Proceedings of the 33d AAAI Conference on Artificial Intelligence 2019, Honolulu, HA, USA, Jan 27 \u2013 Feb 1, Feb 2019. \u2013 AAAI.org, 2019. \u2013 P. 590\u2013597.<\/li>\n<\/ol>\n","protected":false},"excerpt":{"rendered":"","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":[],"categories":[46],"tags":[],"_links":{"self":[{"href":"https:\/\/journals.khnu.km.ua\/vestnik\/index.php?rest_route=\/wp\/v2\/posts\/7022"}],"collection":[{"href":"https:\/\/journals.khnu.km.ua\/vestnik\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/journals.khnu.km.ua\/vestnik\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/journals.khnu.km.ua\/vestnik\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/journals.khnu.km.ua\/vestnik\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=7022"}],"version-history":[{"count":3,"href":"https:\/\/journals.khnu.km.ua\/vestnik\/index.php?rest_route=\/wp\/v2\/posts\/7022\/revisions"}],"predecessor-version":[{"id":7302,"href":"https:\/\/journals.khnu.km.ua\/vestnik\/index.php?rest_route=\/wp\/v2\/posts\/7022\/revisions\/7302"}],"wp:attachment":[{"href":"https:\/\/journals.khnu.km.ua\/vestnik\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=7022"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/journals.khnu.km.ua\/vestnik\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=7022"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/journals.khnu.km.ua\/vestnik\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=7022"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}