main| new issue| archive| editorial board| for the authors| publishing house|
Ðóññêèé
Main page
New issue
Archive of articles
Editorial board
For the authors
Publishing house

 

 


ABSTRACTS OF ARTICLES OF THE JOURNAL "INFORMATION TECHNOLOGIES".
No. 4. Vol. 29. 2023

DOI: 10.17587/it.29.204-214

A. R. Teplyakova, Postgraduate Student, Lecturer, Obninsk Institute for Nuclear Power Engineering, Obninsk, Russian Federation,
A. A. Kuznetsov, Master Student, Moscow Institute of Physics and Technology, Dolgoprudnyi, Russian Federation

Development of a Module for COVID-19 Diagnostics Based on Computed Tomography Images of the Chest Based on Computer Vision Methods

The implementation of a module of a medical decision support system for diagnosing COVID-19 using chest CT images is considered. The U-Net architecture is used for segmentation of lung parenchyma and pathological areas in chest CT images, the DSC and IoU values for parenchyma are 0.951 and 0.933, for pathological areas — 0.97 and 0.959, respectively. A method for image pre-processing based on adaptive histogram equalization is described. Methods for segmentation masks post­processing are also proposed. The first of them is necessary to separate masks into masks of the left and right lungs; it is based on the analysis of areas and mutual positions of contours. The second one is needed to eliminate artifacts. In addition to image processing methods, approaches that generate the data necessary for radiologists to make a diagnosis are also implemented (the volumes of both lungs and pathological findings in them are calculated, percentages of parenchymal tissue involvement in the pathological process are determined, the severity of the disease is assessed). The algorithms for generating a processed series of images and a DICOM SR are described. The average time spent by the module on processing one CT study containing about 600 slices, with a video memory limit of 6 GB, is 68 s, and with a limit of 8 GB — 56 s. Considering that the approximate time spent by a radiologist to process a study is about 6 minutes, the developed module can be effectively used in medical practice to reduce the burden on medical personnel.
Keywords: computer vision, COVID-19, computed tomography, medical images, diagnostics, clinical decision support system

DOI: 10.17587/it.29.204-214

References

  1. Lebedeva I. S., Lebedev P. V. Trends in solving staff problems in health care, Vestnik Akademii znanij, 2022, vol. 1, no. 48, pp. 151—159 (in Russian).
  2. Bhargava A., Bansal A. Novel coronavirus (COVID-19) diagnosis using computer vision and artificial intelligence techniques: a review, Multimedia Tools and Applications. 2021. vol. 80, no. 13, pp. 19931—19946.
  3. Ulhaq A. et al. COVID-19 Control by Computer Vision Approaches: A Survey, IEEE Access, 2020, vol. 8, pp. 179437—179456.
  4. Hassan H. et al. Review and classification of AI-enabled COVID-19 CT imaging models based on computer vision tasks, Computers in Biology and Medicine, 2022, vol. 141, pp. 105123.
  5. Makiev V. G., Makiev G. G. Using artificial intelligence to diagnose COVID-19 using computed tomography data, Aktual'nye nauchnye issledovaniya v sovremennom mire, 2020, no. 12-2, pp. 73—81 (in Russian).
  6. Wei Y., Shen G., Li J. A Fully Automatic Method for Lung Parenchyma Segmentation and Repairing, Journal of Digital Imaging, 2013, vol. 26, no. 3, pp. 483—495.
  7. Kumar S. P., Latte M. V. Lung Parenchyma Segmentation: Fully Automated and Accurate Approach for Thoracic CT Scan Images, IETE Journal of Research, 2020, vol. 66, no. 3, pp. 370—383.
  8. Essaf F. et al. An Improved Lung Parenchyma Segmentation Using the Maximum Inter-Class Variance Method (OTSU), Proceedings of the 2020 6th International Conference on Computing and Artificial Intelligence, 2020, pp. 204—212.
  9. He N. et al. Pulmonary parenchyma segmentation in thin CT image sequences with spectral clustering and geodesic active contour model based on similarity, Ninth International Conference on Digital Image Processing (ICDIP 2017), 2017, pp. 104202G.
  10. Xu M. et al. Segmentation of lung parenchyma in CT images using CNN trained with the clustering algorithm generated dataset, BioMedical Engineering OnLine, 2019, vol. 18, no. 1, pp. 2.
  11. Sharafeldeen A. et al. Precise Segmentation of COVID-19 Infected Lung from CT Images Based on Adaptive First-Order Appearance Model with Morphological/Anatomical Constraints, Sensors, 2021, vol. 21, no. 16, pp. 5482.
  12. Tan W. et al. A Segmentation Method of Lung Parenchyma From Chest CT Images Based on Dual U-Net, 2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 2019, pp. 1649—1656.
  13. Chen Y. et al. A Lung Dense Deep Convolution Neural Network for Robust Lung Parenchyma Segmentation, IEEE Access, 2020, vol. 8, pp. 93527—93547.
  14. Omar A. Lung CT Parenchyma Segmentation using VGG-16 based SegNet, International Journal of Computer Applications, 2019, vol. 178, no. 44, pp. 10—13.
  15. Zhao L. 3D Densely Connected Convolution Neural Networks for Pulmonary Parenchyma Segmentation from CT Images, Journal of Physics: Conference Series, 2020, vol. 1631, no. 1, pp. 012049.
  16. Yousef H. A. et al. Automated quantification of COVID-19 pneumonia severity in chest CT using histogram-based multi­level thresholding segmentation. Egyptian Journal of Radiology and Nuclear Medicine, 2021, vol. 52, no. 1, pp. 293.
  17. Alzahrani A., Bhuiyan Md. A.-A., Akhter F. Detecting COVID-19 Pneumonia over Fuzzy Image Enhancement on Computed Tomography Images, Computational and Mathematical Methods in Medicine, 2022, vol. 2022, pp. 1—12.
  18. Barstugan M., Ozkaya U., Ozturk S. Coronavirus (COVID-19) Classification using CT Images by Machine Learning Methods, available at: http://arxiv.org/abs/2003.09424 (date of access: 25.10.2022).
  19. Chen J. et al. Deep learning-based model for detecting 2019 novel coronavirus pneumonia on high-resolution computed tomography, Scientific Reports, 2020, vol. 10, no. 1, pp. 19196.
  20. Song Y. et al. Deep Learning Enables Accurate Diagnosis of Novel Coronavirus (COVID-19) With CT Images, IEEE/ACM Transactions on Computational Biology and Bioinformatics, 2021, vol. 18, no. 6, pp. 2775—2780.
  21. Wang S. et al. A deep learning algorithm using CT images to screen for Corona virus disease (COVID-19), European Radiology, 2021, vol. 31, no. 8, pp. 6096—6104.
  22. Shan F. et al. Lung infection quantification of COVID-19 in CT images with deep learning, available at: http://arxiv.org/ abs/2003.04655 (date of access: 25.10.2022).
  23. Jin C. et al. Development and evaluation of an artificial intelligence system for COVID-19 diagnosis, Nature Communications, 2020, vol. 11, no. 1, pp. 5088.
  24. Suzuki S., Abe K. Topological structural analysis of digi­tized binary images by border following, Computer Vision, Graphics, and Image Processing, 1985, vol. 30, I. 1, pp. 32—46.
  25. Morozov S. P. et al. Radiation diagnostics of coronavirus disease (COVID-19): organization, methodology, interpretation of results: guidelines, Seriya "Luchshie praktiki luchevoj i instrumental'noj diagnostiki", 2020, vol. 65, 78 p.
  26. COVID-19 CT scans, available at: http://kaggle.com/data-sets/andrewmvd/covid19-ct-scans (date of access: 25.10.22).
  27. Finding and Measuring Lungs in CT Data, available at: http://kaggle.com/datasets/kmader/finding-lungs-in-ct-data (date of access: 25.10.22).
  28. Morozov S. P. et al. MosMedData: data set of 1110 chest CT scans performed during the COVID-19 epidemic, Digital Diagnostics, 2020, vol. 1, no. 1, pp. 49—59.
  29. Lungs from chest CT scans, available at: http://lapisco. ifce.edu.br/producao-academica/private-datasets/database-lungs-from-chest-ct-scans/ (date of access: 10.03.22).
  30. Chest CT Segmentation, available at: http://kaggle. com/datasets/polomarco/chest-ct-segmentation (date of access: 25.10.22).

 

To the contents