The use of machine learning methods for computed tomography image classification in the COVID-19 pandemic: a review
DOI:
https://doi.org/10.17058/reci.v15i1.19227Keywords:
COVID-19, computed tomography, machine learning, deep learning, convolutional neural networksAbstract
Background and Objectives: COVID-19 has been declared a pandemic by the World Health Organization, representing a major challenge worldwide. An early diagnosis method for COVID-19 is based on CT scans, which can be analyzed using artificial intelligence to save medical, logistical, and human resources. Therefore, this study aimed to present the current state of the art in the application of machine learning to classify computed tomography images in the COVID-19 pandemic. Content: The review briefly describes the types of machine learning methods for COVID-19 detection, the stages of deep learning model construction (segmentation, augmentation), and selected aspects of explainable artificial intelligence. Finally, the application results are discussed and the most common performance indicators for individual models are given. Conclusion: Models and algorithms developed during the peak of the COVID-19 pandemic can be reused in the event of future outbreaks of this or similar infectious diseases.
Downloads
References
Abdel-Basset M, Chang V, Hawash H, et al. FSS-2019-nCov: A deep learning architecture for semi-supervised few-shot segmentation of COVID-19 infection. Knowl-Based Syst. 2021;212:106647. https://doi.org/10.1016/j.knosys.2020.106647.
Mondal MRH, Bharati S, Podder P. Diagnosis of COVID-19 using machine learning and deep learning: A review. Curr Med Imaging. 2021;17(12):1403–18. https://doi.org/10.2174/1573405617666210713113439.
Sedik A, Iliyasu AM, Abd El-Rahiem B, et al. Deploying machine and deep learning models for efficient data-augmented detection of COVID-19 infections. Viruses. 2020;12(7):769. https://doi.org/10.3390/v12070769.
Aboul-Fotouh S, Mahmoud AN, Elnahas EM, et al. What are the current anti-COVID-19 drugs? From traditional to smart molecular mechanisms. Virol J. 2023;20(1):241. https://doi.org/10.1186/s12985-023-02210-z.
Aslan MF, Sabanci K, Durdu A, et al. COVID-19 diagnosis using state-of-the-art CNN architecture features and Bayesian Optimization. Comput Biol Med. 2022;142:105244. https://doi.org/10.1016/j.compbiomed.2022.105244.
Aggarwal P, Mishra NK, Fatimah B, et al. COVID-19 image classification using deep learning: Advances, challenges and opportunities. Comput Biol Med. 2022;144:105350. https://doi.org/10.1016/j.compbiomed.2022.105350.
Jia G, Lam H-K, Xu Y. Classification of COVID-19 chest X-Ray and CT images using a type of dynamic CNN modification method. Comput Biol Med. 2021;134:104425. https://doi.org/10.1016/j.compbiomed.2021.104425.
Fallahpoor M, Chakraborty S, Heshejin MT, et al. Generalizability assessment of COVID-19 3D CT data for deep learning-based disease detection. Comput Biol Med. 2022;145:105464. https://doi.org/10.1016/j.compbiomed.2022.105464.
Wu Y, Qi Q, Qi S, et al. Classification of COVID-19 from community-acquired pneumonia: Boosting the performance with capsule network and maximum intensity projection image of CT scans. Comput Biol Med. 2023;154:106567. https://doi.org/10.1016/j.compbiomed.2023.106567.
Awassa L, Jdey I, Dhahri H, et al. Study of different deep learning methods for coronavirus (COVID-19) pandemic: taxonomy, survey and insights. Sensors (Basel). 2022;22(5):1890. https://doi.org/10.3390/s22051890.
Fang L, Wang X. COVID-19 deep classification network based on convolution and deconvolution local enhancement. Comput Biol Med. 2021;135:104588. https://doi.org/10.1016/j.compbiomed.2021.104588.
Qi Q, Qi S, Wu Y, et al. Fully automatic pipeline of convolutional neural networks and capsule networks to distinguish COVID-19 from community-acquired pneumonia via CT images. Comput Biol Med. 2022;141:105182. https://doi.org/10.1016/j.compbiomed.2021.105182.
Shi F, Xia L, Shan F, et al. Large-scale screening to distinguish between COVID-19 and community-acquired pneumonia using infection size-aware classification. Phys Med Biol. 2021;66(6):065031. https://doi.org/10.1088/1361-6560/abe838.
Xu X, Jiang X, Ma C, et al. A deep learning system to screen novel coronavirus disease 2019 pneumonia. Engineering. 2020;6(10):1122–9. https://doi.org/10.1016/j.eng.2020.04.010.
Kuo K-M, Talley PC, Chang C-S. The accuracy of machine learning approaches using non-image data for the prediction of COVID-19: A meta-analysis. Int J Med Inf. 2022;164:104791. https://doi.org/10.1016/j.ijmedinf.2022.104791.
Baghdadi NA, Malki A, Abdelaliem SF, et al. An automated diagnosis and classification of COVID-19 from chest CT images using a transfer learning-based convolutional neural network. Comput Biol Med. 2022;144:105383. https://doi.org/10.1016/j.compbiomed.2022.105383.
Dey A, Chattopadhyay S, Singh PK, et al. MRFGRO: a hybrid meta-heuristic feature selection method for screening COVID-19 using deep features. Sci Rep. 2021;11(1):24065. https://doi.org/10.1038/s41598-021-02731-z.
Zhang X, Jiang R, Huang P, et al. Dynamic feature learning for COVID-19 segmentation and classification. Comput Biol Med. 2022;150:106136. https://doi.org/10.1016/j.compbiomed.2022.106136.
Carmo D, Campiotti I, Rodrigues L, et al. Rapidly deploying a COVID-19 decision support system in one of the largest Brazilian hospitals. Health Informatics J. 2021;27(3):14604582211033017. https://doi.org/10.1177/14604582211033017.
Shiri I, Sorouri M, Geramifar P, et al. Machine learning-based prognostic modeling using clinical data and quantitative radiomic features from chest CT images in COVID-19 patients. Comput Biol Med. 2021;132:104304. https://doi.org/10.1016/j.compbiomed.2021.104304.
Champendal M, Müller H, Prior JO, et al. A scoping review of interpretability and explainability concerning artificial intelligence methods in medical imaging. Eur J Radiol. 2023;169:111159. https://doi.org/10.1016/j.ejrad.2023.111159.
Javaheri T, Homayounfar M, Amoozgar Z, et al. CovidCTNet: an open-source deep learning approach to diagnose covid-19 using small cohort of CT images. NPJ Digit Med. 2021;4(1):29. https://doi.org/10.1038/s41746-021-00399-3.
Li L, Qin L, Xu Z, et al. Using artificial intelligence to detect COVID-19 and community-acquired pneumonia based on pulmonary CT: Evaluation of the diagnostic accuracy. Radiology. 2020;296(2):E65–71. https://doi.org/10.1148/radiol.2020200905.
Fan D-P, Zhou T, Ji G-P, et al. Inf-Net: Automatic COVID-19 lung infection segmentation from CT images. IEEE Trans Med Imaging. 2020;39(8):2626–37. https://doi.org/10.1109/TMI.2020.2996645.
Zhang K, Liu X, Shen J, et al. Clinically applicable AI system for accurate diagnosis, quantitative measurements, and prognosis of COVID-19 pneumonia using computed tomography. Cell. 2020;181(6):1423–33. https://doi.org/10.1016/j.cell.2020.04.045.
Wang X, Deng X, Fu Q, et al. A weakly-supervised framework for COVID-19 classification and lesion localization from chest CT. IEEE Trans Med Imaging. 2020;39(8):2615–25. https://doi.org/10.1109/TMI.2020.2995965.
Bao G, Chen H, Liu T, et al. COVID-MTL: Multitask learning with Shift3D and random-weighted loss for COVID-19 diagnosis and severity assessment. Pattern Recognit. 2022;124:108499. https://doi.org/10.1016/j.patcog.2021.108499.
Shiri I, Mostafaei S, Haddadi Avval A, et al. High-dimensional multinomial multiclass severity scoring of COVID-19 pneumonia using CT radiomics features and machine learning algorithms. Sci Rep. 2022;12(1):14817. https://doi.org/10.1038/s41598-022-18994-z.
Guhan B, Almutairi L, Sowmiya S, et al. Automated system for classification of COVID-19 infection from lung CT images based on machine learning and deep learning techniques. Sci Rep. 2022;12(1):17417. https://doi.org/10.1038/s41598-022-20804-5.
Li T, Wei W, Cheng L, et al. Computer-aided diagnosis of COVID-19 CT scans based on spatiotemporal information fusion. J Healthc Eng. 2021;2021:6649591. https://doi.org/10.1155/2021/6649591.
Tello-Mijares S, Woo L. Computed tomography image processing analysis in COVID-19 patient follow-up assessment. J Healthc Eng. 2021;2021:8869372. https://doi.org/10.1155/2021/8869372.
Topff L, Sánchez-García J, López-González R, et al. A deep learning-based application for COVID-19 diagnosis on CT: The Imaging COVID-19 AI initiative. PLoS One. 2023;18(5):e0285121. https://doi.org/10.1371/journal.pone.0285121.
Yang Z, Zhao L, Wu S, et al. Lung lesion localization of COVID-19 from chest CT image: A novel weakly supervised learning method. IEEE J Biomed Health Inform. 2021;25(6):1864–72. https://doi.org/10.1109/JBHI.2021.3067465.
Ortiz A, Trivedi A, Desbiens J, et al. Effective deep learning approaches for predicting COVID-19 outcomes from chest computed tomography volumes. Sci Rep. 2022;12(1):1716. https://doi.org/10.1038/s41598-022-05532-0.
Nguyen D, Kay F, Tan J, et al. Deep learning–based COVID-19 pneumonia classification using chest CT images: model generalizability. Front Artif Intell. 2021;4:694875. https://doi.org/10.3389/frai.2021.694875.
Goel T, Murugan R, Mirjalili S, et al. Automatic screening of COVID-19 using an optimized generative adversarial network. Cogn Comput. 2021. https://doi.org/10.1007/s12559-020-09785-7.
Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks. Adv Neural Inf Process Syst. 2012;25. https://doi.org/10.1145/3065386
Kang D, Park S, Paik J. SdBAN: Salient object detection using bilateral attention network with dice coefficient loss. IEEE Access. 2020;8:104357–70. https://doi.org/10.1109/ACCESS.2020.2999627.
Rezatofighi H, Tsoi N, Gwak J, et al. Generalized intersection over union: A metric and a loss for bounding box regression. Proc. IEEECVF Conf. Comput. Vis. Pattern Recognit. 2019. p. 658–66. https://doi.org/10.48550/arXiv.1902.09630.
Zaborski D, Proskura WS, Grzesiak W, et al. The comparison between random forest and boosted trees for dystocia detection in dairy cows. Comput Electron Agric. 2019;163:104856. https://doi.org/10.1016/j.compag.2019.104856.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Jacek Sieredzinski, Daniel
This work is licensed under a Creative Commons Attribution 4.0 International License.
The author must state that the paper is original (has not been published previously), not infringing any copyright or other ownership right involving third parties. Once the paper is submitted, the Journal reserves the right to make normative changes, such as spelling and grammar, in order to maintain the language standard, but respecting the author’s style. The published papers become ownership of RECI, considering that all the opinions expressed by the authors are their responsibility. Because we are an open access journal, we allow free use of articles in educational and scientific applications provided the source is cited under the Creative Commons CC-BY license.
