Identification of postacute COVID-19 patterns in tomography using artificial intelligence
DOI:
https://doi.org/10.59681/2175-4411.v16.iEspecial.2024.1331Keywords:
Multidetector Computed Tomography, Artificial Intelligence, Postacute COVID-19 SyndromeAbstract
Objective: Develop AI models capable of recognizing post-COVID lung patterns in computed tomography scans. Method: Radiologists analyzed 87 CT scans to establish tomographic patterns for training and testing deep learning models. The best model was then selected to read eight full scans. Results: The chosen model showed an average accuracy of 92.21% in detecting post-COVID patterns.
Conclusion: Although the sample size was limited, testing with image sets and full scans showed promising results. The sample used in the study reflects the epidemiological profile found in the literature.
References
Cau R, Faa G, Nardi V, Balestrieri A, Puig J, Suri JS, SanFilippo R, Saba L. Long-COVID diagnosis: from diagnostic to advanced AI-driven models. Eur J Radiol. 2022. 148:110164.
Luqmani Y.A., El Hashim A. The COVID-19 pandemic: a health crisis managed or a panic response with disastrous future consequences? Med Princ Pract.2022. 31:1-10.
British Thoracic Society (2020) British thoracic society guidance on respiratory follow up of patients with a clinico-radiological diagnosis of COVID-19 pneumonia. 2020.
Nalbandian A, Sehgal K, Gupta A et al. Post-acute COVID-19 syndrome. Nat Med. 2021. 27:601-615.
Caruso D, Guido G, Zerunian M et al. Post-acute sequelae of COVID-19 pneumonia: six-month chest CT follow-up. Radiology. 2021. 301:E396-E405.
Desai AD, Lavelle M, Boursiquot BC, Wan EY. Long-term complications of COVID-19. 2022, 322:C1-C11.
Lee KS, Wi YM. Residual lung lesions at 1-year CT after COVID-19. 2022. Radiology 302:720-721.
Alhasan M, Hasaneen M. Digital imaging, technologies and artificial intelligence applications during COVID-19 pandemic. Comput Med Imaging Graph. 2021. 91:101933.
Noce J, Chantong G, Jauregui G, Mogami R, Monteiro A, Figueiredo K, Vellasco M. Applied enhanced Q-NAS for COVID-19 detection in CT images. In: Mahmud CIM, Kaiser MS, Mammone N, Morabito FC (eds) Applied intelligence and informatics. Springer, Berlin, Germany 2023. p 419.
Leão PPS, Freire NS, Pinto RA, Maciel K, Pinto B, Giusti R, Santos EM, Detecção de Covid-19 em Imagens de Raio-x Utilizando Redes Convolucionais, J. Health Inform. 2020 Número Especial SBIS - Dezembro: 393-8
Simonyan, K. and Zisserman, A. Very deep convolutional networks for large-scale image recognition, NASA/ADS. 2014.
Sandler M, Howard A, Zhu M, Zhmoginov A, Chen LC. MobileNetV2: Inverted Residuals and Linear Bottlenecks, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA. 2018. pp. 4510-4520.
Friedman B, Nissenbaum H. Bias in computer systems. ACM Trans Inf Syst. 1996. 14:330-347.
Mehrabi N, Morstatter F, Saxena N, Lerman K, Galstyan A. A survey on bias and fairness in machine learning. ACM Comput Surv.2021. 54:1-35.
Chlap P, Min H, Vandenberg N, Dowling J, Holloway L, Haworth A. A review of medical image data augmentation techniques for deep learning applications. J Med Imaging Radiat Oncol. 2021. 65:545-563.
Goodfellow I, Yoshua B, Courville A. Deep learning. The Mit Press. 2016., Cambridge, US
Mogami R, Lopes AJ, Filho RCA, De Almeida FCS, Messeder A, Koifman ACB, Guimarães AB, Monteiro A. Chest computed tomography in COVID-19 pneumonia: a retrospective study of 155 patients at a university hospital in Rio de Janeiro, Brazil. Radiol Bras.2021. 54:1-8.
Mogami R, Filho R.C.A., Chantong C.G.C. et al. The importance of radiological patterns and small airway disease in long-term follow-up of postacute COVID-19: a preliminary study. Radiol Res Pract.2022. 2022:7919033.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Submission of a paper to Journal of Health Informatics is understood to imply that it is not being considered for publication elsewhere and that the author(s) permission to publish his/her (their) article(s) in this Journal implies the exclusive authorization of the publishers to deal with all issues concerning the copyright therein. Upon the submission of an article, authors will be asked to sign a Copyright Notice. Acceptance of the agreement will ensure the widest possible dissemination of information. An e-mail will be sent to the corresponding author confirming receipt of the manuscript and acceptance of the agreement.
