Methods of Preprocessing Chest X-Ray Images for Classification Tasks

V. I. SUCHKOV, Postgraduate Student

DOI: https://doi.org/10.35668/2520-6524-2026-1-11

PDF (Ukrainian)

Keywords: convolutional neural network, data preprocessing, dataset, pattern recognition, artificial intelligence.

ABSTRACT

The article examines the application of chest X-ray image preprocessing methods in the task of automated classification of medical images. Preprocessing is an important stage of data preparation, since the characteristics of input images can significantly affect the efficiency of training artificial intelligence models and the quality of medical image analysis. The study analyzes various approaches to image preprocessing in the task of classifying X-ray images into the following classes: COVID-19, pneumonia, and no disease. In particular, the application of the Gaussian filter, median filter, and contrast limited adaptive histogram equalization (CLAHE) method is considered. These methods are used, respectively, for noise smoothing, contour preservation, and enhancement of local image contrast. The results of the study confirm that the application of preprocessing methods improves the effectiveness of chest X-ray image classification. The contrast limited adaptive histogram equalization method demonstrated the best classification results in the experiments conducted.

Received by the Editorial Office on 04.03.2026
Accepted for publication on 16.03.2026

REFERENCES

  1. Suchkov, V. I., & Pashko, A. O. (2025). Zghortkova neironna merezha dlia klasyfikatsii renthen-znimkiv hrudnoi klityny [Convolutional neural network for classification of chest X-ray images]. Zhurnal obchysliuvalnoi ta prykladnoi matematyky [Journal of Computational and Applied Mathematics], 2, 77-86. DOI: 10.17721/2706-9699.2025.2.06. [in Ukr.].
  2. Khan, A. I., Shah, J. L., & Bhat, M. M. (2020). CoroNet: A deep neural network for detection and diagnosis of COVID-19 from chest x-ray images. Comput Methods Programs Biomed, 196, 105581. PMCID: PMC7274128. DOI: 10.1016/j.cmpb.2020.105581
  3. Cohen, J. Р., Morrison, P., Dao, L., Roth, K., Duong, T., & Ghassem, M. (2020). COVID‑19 image data collection: Prospective predictions are the future. Journal of Machine Learning for Biomedical Imaging, 1, 1-38. DOI: 10.59275/j.melba.2020-48g7
  4. Mooney, P. (2018). Chest X-ray images (pneumonia). Retrieved from: https://kaggle.com/datasets/paultimothymooney/chest-xray-pneumonia.
  5. Zolya, M.-A., Baltag, C., Bratu, D.-V., Coman, S., & Moraru, S.-A. (2024). COVID-19 Detection and Diagnosis Model on CT Scans Based on AI Techniques. Bioengineering, 11(1), 79. DOI: https://doi.org/10.3390/bioengineering11010079.
  6. Goyal, S., & Singh, R. (2023). Detection and classification of lung diseases for pneumonia and COVID-19 using machine and deep learning techniques. Journal of Ambient Intelligence and Humanized Computing. 14, 3239-3259. DOI: https://doi.org/10.1007/s12652-021-03464-7.
  7. El Houby E. M. F. (2024). COVID-19 detection from chest X-ray images using transfer learning. Scientific reports, 14(1), 11639. DOI: https://doi.org/10.1038/s41598-024-61693-0.
  8. Davydko, O. B., Ladik, A. O., Maksymenko, V. B., Lynnyk, M. I., Pavlov, O. V., & Nastenko, Ye. A. (2021). Klasyfikatsiia urazhen lehen pry COVID-19 na osnovi teksturnykh oznak ta zghortkovoi neironnoi merezhi [Classification of lung lesion during COVID-19 by texture features and convolutional neural network]. Biomedychna inzheneriia i tekhnolohiia [Biomedical engineering and technology], 6, 19-28. [in Ukr.].
  9. Loey, M., Smarandache, F., & M. Khalifa, N. E. (2020). Within the Lack of Chest COVID-19 X-ray Dataset: A Novel Detection Model Based on GAN and Deep Transfer Learning. Symmetry. 12 (4). 651. DOI: 10.3390/sym12040651.
  10. Amuda, K., Wakili, A., Amoo, T., Agbetu, L., Wang, Q., & Feng, J. (2025). Detecting SARS-CoV-2 in CT Scans Using Vision Transformer and Graph Neural Network. Algorithms, 18(7), 413. DOI:3390/a18070413.
  11. Amuda, K., Wakili, A., Amoo, T., Agbetu, L., Wang, Q., & Feng, J. (2025). Diagnostic accuracy of X-ray versus CT in COVID-19: a propensity-matched database study. BMJ Open, 6;10 (11). DOI: 10.1136/bmjopen-2020-042946.

License
Copyright (c) 2026 Science, Technologies, Innovations Journal

All materials published in the current issue of the journal are distributed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (CC BY-NC 4.0): https://creativecommons.org/licenses/by-nc/4.0/deed.uk
The license permits free non-commercial use, distribution, reproduction, and adaptation of the materials in any format, provided that proper attribution is given to the author(s) and the source of publication is cited. Commercial use of the materials is permitted only with the publisher’s written consent.