Results of Machine Learning Applications in the Study of COVID-19 Associated Cardiopulmonary Pathology Using Computed Tomography Data
DOI:
https://doi.org/10.20535/ibb.2025.9.4.325335Keywords:
artificial intelligence, COVID-19, diagnosis, computer-assisted, diffuse alveolar damage, disease progression, machine learning, pneumonia, viral, pulmonary fibrosis, tomography, x-ray computedAbstract
Background. The COVID-19 pandemic, caused by SARS-CoV-2, has significantly impacted global health, emphasizing the importance of efficient diagnostic methods. Computed tomography (CT) imaging plays a crucial role in identifying COVID-19-associated lung pathologies, yet manual analysis of extensive imaging data remains burdensome. Machine learning (ML) methods offer promising automated solutions to expedite diagnostics and reduce workload on radiologists.
Objective. To evaluate the effectiveness of machine learning algorithms, specifically convolutional neural networks (CNN) and texture analysis methods, in automated detection and classification of COVID-19-related cardiopulmonary pathology using chest CT imaging.
Methods. This study analyzed chest CT datasets obtained from clinical resources, which included images from patients with COVID-19 exhibiting ground-glass opacities, crazy-paving patterns, and consolidations. Regions of interest (ROIs) were segmented and classified using various machine learning approaches: CNN combined with gray-level co-occurrence matrix (GLCM) texture analysis, logistic self-organizing forest (LSOF), group method of data handling (GMDH), and ensemble methods including random forest, XGBoost, LightGBM, and random forest of optimal complexity trees (RFOCT).
Results. The CNN and texture-based hybrid classifiers achieved high accuracy, with overall classification accuracies ranging from 83% to 99%. Specifically, ground-glass opacity identification reached up to 100% accuracy, while crazy-paving patterns and consolidations showed slightly lower accuracies (71–95%). The ensemble method RFOCT achieved the highest accuracy (89%) in differentiating acute COVID-19 from Long COVID. Additionally, methods incorporating texture analysis significantly enhanced the accuracy and informativeness of CT-based diagnostics.
Conclusions. Machine learning algorithms, particularly CNNs and advanced texture analysis, demonstrate significant potential in automating the diagnosis of COVID-19-associated lung pathology. These approaches not only increase diagnostic efficiency but also facilitate the detection of subtle pathological changes, crucial for clinical decision-making and patient management during epidemiological crises. Future research should address current limitations related to dataset size, computational complexity, and generalizability to further enhance clinical applicability.
Keywords: COVID-19, Computed Tomography, Medical Image Analysis, Machine Learning, Deep Learning, Convolutional Neural Networks, Texture Analysis, Ensemble Methods.
References
World Health Organization. WHO COVID-19 Dashboard [Internet]. Geneva: WHO; 2023 [cited 2024 Oct 27]. Available from: https://covid19.who.int/
World Health Organization. The top 10 causes of death [Internet]. Geneva: WHO; 2024 [cited 2024 Oct 27]. Available from: https://www.who.int/news-room/fact-sheets/detail/the-top-10-causes-of-death
Ai T, Yang Z, Hou H, Xia L, Zha J, Li Y, et al. Correlation of Chest CT and RT-PCR Testing in Coronavirus Disease 2019 (COVID-19) in China: A Report of 1014 Cases. Radiology. 2020;296(2):E32–40. DOI: 10.1148/radiol.2020200642
Mehta V, Jyoti D, Guria RT, Das D, Kumar T, Sharma A, et al. Correlation between chest CT and RT-PCR testing in India’s second COVID-19 wave: a retrospective cohort study. BMJ Evid Based Med. 2022;27:305-312. DOI: 10.1136/bmjebm-2021-111801
Yakovenko O, Soloviov S, Smetiukh M, Khanin O, Khodosh E, Dziublyk Y, et al. Development and Approval of a Multidimensional Model of the Clinical Effectiveness of Treatment Technologies for Patients With a Mild COVID-19 Associated With Comorbidities. Innov Biosyst Bio-eng. 2024;8(1):19–36. DOI: 10.20535/ibb.2024.8.1.299055
Alonaizan F, AlHumaid J, AlJindan R, Bedi S, Dardas H, Abdulfattah D, et al. Sensitivity and Specificity of Rapid SARS-CoV-2 Antigen Detec-tion Using Different Sampling Methods: A Clinical Unicentral Study. Int J Environ Res Public Health. 2022;19(11):6836. DOI: 10.3390/ijerph19116836
Dutta D, Naiyer S, Mansuri S, et al. COVID‑19 diagnosis: a comprehensive review of the RT‑qPCR method for detection of SARS‑CoV‑2. Diag-nostics (Basel). 2022;12(6):1503. DOI:10.3390/diagnostics12061503
Tsang NN, So HC, Ng KY, Cowling BJ, Leung GM, Ip DK. Diagnostic performance of different sampling approaches for SARS-CoV-2 RT-PCR testing: a systematic review and meta-analysis. Lancet Infect Dis. 2021;21(9):1233–45. DOI: 10.1016/S1473-3099(21)00146-8
Toptan T, Eckermann L, Pfeiffer AE, Hoehl S, Ciesek S, Drosten C, et al. Evaluation of a SARS-CoV-2 rapid antigen test: Potential to help re-duce community spread? J Clin Virol. 2021;135:104713. DOI: 10.1016/j.jcv.2020.104713
Sobhani K, Cheng S, Binder RA, Mantis NJ, Crawford JM, Okoye N, et al. Clinical Utility of SARS-CoV-2 Serological Testing and Defining a Cor-relate of Protection. Vaccines. 2023;11(11):1644. DOI: 10.3390/vaccines11111644
Zhong Y, Kang AYH, Tay CJX, Li HE, Elyana N, Tan CW, et al. Correlates of protection against symptomatic SARS‑CoV‑2 in vaccinated chil-dren. Nat Med. 2024;30:1373‑1383. DOI:10.1038/s41591-024-02962-3
Chen X, Meng X, Wu Q, Lim WW, Xin Q, Cowling BJ, et al. Assessment of neutralizing antibody response as a correlate of protection against symptomatic SARS‑CoV‑2 infections after two doses of CoronaVac: phase III randomized controlled trial. J Infect. 2024;89(6):106315. DOI:10.1016/j.jinf.2024.106315
Majeed MN, Iqbal A, Murtaza N, Herrera-Zúñiga LD, Siddique S, Raza M, et al. Designing a Multi-Epitope Vaccine Candidate to MERS-CoV: An in silico Approach. Innov Biosyst Bioeng. 2024;8(3):3–17. DOI: 10.20535/ibb.2024.8.3.296662
Saez de Gordoa E, Portella A, Escudero-Fernández JM, Andreu Soriano J. Usefulness of chest X-rays for detecting COVID 19 pneumonia dur-ing the SARS-CoV-2 pandemic. Radiologia (Engl Ed). 2022;64(4):310–6. DOI: 10.1016/j.rxeng.2021.11.003
Elmokadem AH, Bayoumi D, Abo-Hedibah SA, El-Morsy A. Diagnostic performance of chest CT in differentiating COVID-19 from other causes of ground-glass opacities. Egypt J Radiol Nucl Med. 2021;52(1):12. DOI: 10.1186/s43055-020-00398-6
Sharif PM, Nematizadeh M, Saghazadeh M, Saghazadeh A, Rezaei N. Computed tomography scan in COVID-19: a systematic review and meta-analysis. Pol J Radiol. 2022;87:e1–23. DOI: 10.5114/pjr.2022.112613
Mirahmadizadeh A, Pourmontaseri Z, Afrashteh S, Hosseinzadeh M, Karimi J, Sharafi M. Sensitivity and specificity of chest CT scan based on RT‑PCR in COVID‑19 diagnosis. Pol J Radiol. 2021;86:74‑77. DOI:10.5114/pjr.2021.103858
Adams HJA, Kwee TC, Yakar D, Hope MD, Kwee RM. Systematic review and meta‑analysis on the value of chest CT in the diagnosis of coro-navirus disease (COVID‑19). AJR Am J Roentgenol. 2020;215(6):1342‑50. DOI:10.2214/AJR.20.23391
Gempeler A, Griswold DP, Rosseau G, Johnson WD, Kaseje N, Kolias A, et al. An umbrella review with meta‑analysis of chest computed to-mography for diagnosis of COVID‑19: considerations for trauma patient management. Front Med (Lausanne). 2022;9:900721. DOI:10.3389/fmed.2022.900721
Nam BD, Hong H, Yoon SH. Diagnostic performance of standardized typical CT findings for COVID‑19: a systematic review and me-ta‑analysis. Insights Imaging. 2023;14(1):96. DOI:10.1186/s13244-023-01429-2
Al‑Shaibari KSA, Mousa HA‑L, Alqumber MA, Alqfail KA, Mohammed A, Bzeizi K. The diagnostic performance of various clinical specimens for the detection of COVID‑19: a meta‑analysis of RT‑PCR studies. Diagnostics (Basel). 2023;13(19):3057. DOI:10.3390/diagnostics13193057
Hirabayashi E, Mercado G, Hull B, Soin S, Koshy‑Chenthittayil S, Raman S, et al. Comparison of diagnostic accuracy of rapid antigen tests for COVID‑19 compared to the viral genetic test in adults: a systematic review and meta‑analysis. JBI Evid Synth. 2024;22(10):1939‑2002. DOI:10.11124/JBIES-23-00291
Zheng Z, Yao Z, Wu K, Zheng J. The diagnosis of pandemic coronavirus pneumonia: a review of radiology examination and laboratory test. J Clin Virol. 2020;128:104396. DOI:10.1016/j.jcv.2020.104396
Inui S, Gonoi W, Kurokawa R, et al. The role of chest imaging in the diagnosis, management, and monitoring of coronavirus disease 2019 (COVID-19). Insights Imaging. 2021;12:155. DOI: 10.1186/s13244-021-01096-1
Gavrysyuk VK. CT‑semiotics of pulmonary lesions in coronavirus disease (COVID‑19). Ukrainian Pulmonology Journal. 2020;108(2):13‑18. DOI:10.31215/2306-4927-2020-108-2-13-18
Majrashi NA, Alhulaibi RA, Nammazi IH, Alqasi MH, Alyami AS, Ageeli WA, et al. A systematic review of the relationship between chest CT severity score and laboratory findings and clinical parameters in COVID-19 pneumonia. Diagnostics (Basel). 2023;13(13):2223. DOI: 10.3390/diagnostics13132223
Mishra NK, Singh P, Joshi SD. Automated detection of COVID-19 from CT scan using convolutional neural network. Biocybern Biomed Eng. 2021;41(2):572–88. DOI: 10.1016/j.bbe.2021.04.006
Kalyanpur A, Mathur N. Applications of artificial intelligence in thoracic imaging: a review. Academia Medicine. 2025;2(1). DOI:10.20935/AcadMed7509
Davydko OB, Ladik AO, Maksymenko VB, Lynnyk MI, Pavlov OV, Nastenko YA. Classification of lung lesion during covid-19 by texture fea-tures and convolutional neural network. Biomedychna inzheneriia i tekhnolohiia. 2021;(6):19-28. Ukrainian. DOI:10.20535/2617-8974.2021.6.2318877
Davydko O, Hladkyi Y, Linnik M, Nosovets O, Pavlov V, Nastenko I. Hybrid Classifiers Based on convolutional neural network, LSOF, GMDH in COVID-19 Pneumonic Lesions Types Classification Task. 2021 IEEE 16th International Conference on Computer Sciences and In-formation Technologies (CSIT); 2021 Sep 22-25; Lviv, Ukraine. IEEE; 2021. p. 380-384. DOI:10.1109/CSIT52700.2021.9648752
Davydko O, Hladkyi Y, Linnik M, Nosovets O, Nastenko I, Pavlov V, editors. A Pipeline for the Diagnosis and Classification of Lung Lesions for Patients with COVID-19. 2022 IEEE 17th International Conference on Computer Sciences and Information Technologies (CSIT); 2022 Dec 14-17; Lviv, Ukraine. IEEE; 2022. p. 551-4. DOI: 10.1109/CSIT56902.2022.10000435
Lee JH, Koh J, Jeon YK, Goo JM, Yoon SH. An integrated radiologic-pathologic understanding of COVID-19 pneumonia. Radiology. 2023;306(2):e222600. DOI: 10.1148/radiol.222600
Babar M, Jamil H, Mehta N, Moutwakil A, Duong TQ. Short- and Long-Term Chest-CT Findings after Recovery from COVID-19: A Systematic Review and Meta-Analysis. Diagnostics. 2024;14:621. DOI: 10.3390/diagnostics14060621
Tran S, Ksajikian A, Overbey J, Li P, Li Y. Pathophysiology of pulmonary fibrosis in the context of COVID-19 and implications for treatment: a narrative review. Cells. 2022;11(16):2489. DOI: 10.3390/cells11162489
Yukhymiuk RY, Shkepast MV, Nastenko YA, Lynnyk MI, Davydovych IV, Babenko VO. Utilization of deep neural networks for comparative analyses of normality, pneumonia and COVID-19. Biomedychna inzheneriia i tekhnolohiia. 2023;(12):56-64. Ukrainian. DOI: 10.20535/2617-8974.2023.12.292729
Gupta K, Bajaj V. Deep Learning Models-Based CT-Scan Image Classification for Automated Screening of COVID-19 [preprint]. 2022 [cited 2024 Oct 27]. DOI: 10.2139/ssrn.4031534
Lutchenko VH, Babenko VO, Nastenko YA, Lynnyk MI. Efficiency of machine learning algorithms for classifying lung structural changes in post-COVID-19 and acute stages of COVID-19. Biomedychna inzheneriia i tekhnolohiia. 2024;15(1):27-35. Ukrainian. DOI: 10.20535/.2024.15.306763
Petrunina O, Shevaga D, Babenko V, Pavlov V, Rysin S, Nastenko I. Comparative Analysis of Classification Algorithms in the Analysis of Medical Images From Speckle Tracking Echocardiography Video Data. Innov Biosyst Bioeng. 2021Sep.10;5(3):153-66. DOI:10.20535/ibb.2021.5.3.234990
Babenko V, Nastenko I, Pavlov V, Horodetska O, Dykan I, Tarasiuk B, et al. Classification of pathologies on medical images using the algo-rithm of random forest of optimal‑complexity trees. Cybern Syst Anal. 2023;59:346‑58. DOI:10.1007/s10559-023-00569-z
Godbin AB, Jasmine SG. Screening of COVID-19 Based on GLCM Features from CT Images Using Machine Learning Classifiers. SN COMPUT SCI. 2023;4:133. DOI: 10.1007/s42979-022-01583-2
Garain A, Basu A, Giampaolo F, Velasquez JD, Sarkar R. Detection of COVID-19 from CT scan images: A spiking neural network-based ap-proach. Neural Comput Appl. 2021;33(19):12591–604. DOI: 10.1007/s00521-021-05910-1
Nastenko IA, Honcharuk MO, Babenko VO, Lynnyk MI, Ignatieva VI, Yachnyk VA. Development of Artificial Intelligence-Based Programs for the Diagnosis of Myocarditis in COVID-19 Using Chest Computed Tomography Data. Ukr J Cardiovasc Surg. 2024;32(3):58-65. DOI: 10.30702/ujcvs/24.32(03)/NH052-5865
Afshar P, Heidarian S, Enshaei N, Naderkhani F, Rafiee MJ, Oikonomou A, et al. COVID-CT-MD, COVID-19 computed tomography scan da-taset applicable in machine learning and deep learning. Sci Data. 2021;8(1):121. DOI: 10.1038/s41597-021-00900-3
Li CY, Chang KJ, Yang CF, et al. Towards a holistic framework for multimodal LLM in 3D brain CT radiology report generation. Nat Commun. 2025;16:2258. DOI: 10.1038/s41467-025-57426-0
Blankemeier L, Cohen JP, Kumar A, Van Veen D, Gardezi SJS, Paschali M, et al. Merlin: a vision language foundation model for 3D computed tomography. Research Square. 2024;rs.3.rs-4546309. DOI: 10.21203/rs.3.rs-4546309/v1
Lassau N, Ammari S, Chouzenoux E, et al. Integrating deep learning CT-scan model, biological and clinical variables to predict severity of COVID-19 patients. Nat Commun. 2021;12:634. DOI: 10.1038/s41467-020-20657-4
Chieregato M, Frangiamore F, Morassi M, Baresi C, Nici S, Bassetti C, et al. A hybrid machine learning/deep learning COVID-19 severity pre-dictive model from CT images and clinical data. Sci Rep. 2022;12(1):4329. DOI: 10.1038/s41598-022-07890-1
Yi Z, Xiao T, Albert MV. A survey on multimodal large language models in radiology for report generation and visual question answering. In-formation. 2025;16(2):136. DOI: 10.3390/info16020136
Strotzer QD, Nieberle F, Kupke LS, Napodano G, Muertz AK, Meiler S, et al. Toward foundation models in radiology? quantitative assess-ment of GPT-4V's multimodal and multianatomic region capabilities. Radiology. 2024;313(2):e240955. DOI: 10.1148/radiol.240955
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 The Author(s)
This work is licensed under a Creative Commons Attribution 4.0 International License.
The ownership of copyright remains with the Authors.
Authors may use their own material in other publications provided that the Journal is acknowledged as the original place of publication and National Technical University of Ukraine “Igor Sikorsky Kyiv Polytechnic Institute” as the Publisher.
Authors are reminded that it is their responsibility to comply with copyright laws. It is essential to ensure that no part of the text or illustrations have appeared or are due to appear in other publications, without prior permission from the copyright holder.
IBB articles are published under Creative Commons licence:- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under CC BY 4.0 that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
