Abstract
In the current COVID-19 pandemic there are growing number of research papers on computer-aided detection of SARS-CoV-2 symptoms in the X-ray of lung. Unfortunately, there are often various types of radiographic artifacts that may interfere with pathology recognition by computer-aided systems. The radiographic artifacts include acquisition artifacts, i.e. necklaces, buttons and bra elements and surgical artifacts, i.e. pacemakers, electrodes, cables. A computational method for detecting, segmenting, and marking foreign bodies using masks that exclude irrelevant areas from further analysis of chest radiograms is presented. After preprocessing, seedpoint detection is performed using Sobel filters with adaptive thresolding based on pixel-oriented K-means. Lung segmentation is performed in parallel to further analyze only those artifacts that hinder disease recognition. We grow seed points by thinning and lightly smoothing edges with hole removal to finally delineate regions based on shape features. The experiments were carried out using both a database of 564 with COVID-19 findings (including 270 cases with artifacts within the lungs) and a database of 573 without findings (including 393 cases with artifacts within the lungs). The resulting sensitivity of artifact detection was 74%, including 73% for normal cases and 76% for separately analyzed COVID-19 confirmed cases.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
World Health Organization: Global research on coronavirus disease (COVID-19). https://www.who.int/emergencies/diseases/novel-coronavirus-2019/global-research-on-novel-coronavirus-2019-ncov
Kanne, J.P., et al.: COVID-19 imaging: what we know now and what remains unknown. Radiology 299(3), 262–279 (2021). https://doi.org/10.1148/radiol.2021204522
Heidari, M., Mirniaharikandehei, S., Zargari, A., et al.: Improving the performance of CNN to predict the likelihood of COVID-19 using chest X-ray with preprocessing algorithms. Int. J. Med. Inform. 144 (2020). 104284, ISSN 1386–5056, https://doi.org/10.1016/j.ijmedinf.2020.104284
Uras, I., Yavuz, O.Y., Kose, K.C., Atalar, H., Uras, N., Karadag, A.: Radiographic artifact mimicking epiphysis of the femoral head in a seven-month-old girl. J. Natl. Med. Assoc. 98(7), 1181–1182 (2006). PMID: 16895292; PMCID: PMC2569463
Mestayer, R.G., Attaway, K.C., Polchow ,T.N., Brogdon, B.G.: Snooping around the adolescent pelvis: good grief, it’s the brief! AJR Am. J. Roentgenol. 186(2):587–588. PMID: 16423982. https://doi.org/10.2214/AJR.05.0816
Hogeweg, L., et al.: Foreign object detection and removal to improve automated analysis of chest radiographs. Med Phys. 40(7), 071901 (2013). PMID: 23822438. https://doi.org/10.1118/1.4805104
Sarkar, A., et al.: Identification of of COVID-19 from chest X-rays using deep learning: comparing COGNEX VisionPro deep learning 1.0 software with open source convolutional neural networks. SN Comput. Sci. 2(3), 130 (2021)
Murphy, A.: Clothing artifact. Case study, Radiopaedia.org. https://doi.org/10.53347/rID-59812. Accessed 18 Jan 2022
Subramaniam, U., Monica Subashini, M., Almakhles, D., Karthick, A., Manoharan, S.: An Expert system for covid-19 infection tracking in lungs using image processing and deep learning techniques. BioMed Res. Int. 2021 (2021). Article ID 1896762, 17 pages. https://doi.org/10.1155/2021/1896762
Heidari, M., et al.: Improving the performance of CNN to predict the likelihood of COVID-19 using chest X-ray with preprocessing algorithms. Int. J. Med. Inform. 144, 104284 (2020). ISSN 1386–5056, https://doi.org/10.1016/j.ijmedinf.2020.104284
Xue, Z., et al.: Foreign object detection in chest X-rays. In: IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 2015, pp. 956–961 (2015). https://doi.org/10.1109/BIBM.2015.7359812
Przelaskowski, A., Jasionowska, M., Ostrek, G.: ’Semantic segmentation of abnormal lung areas on chest X-rays to detect COVID-19’. Submitted to ITIB 2022
Nguyen, H.Q., et al.: VinDr-CXR: An open dataset of chest X-rays with radiologist’s annotations (2020)
Wong, H., Lam, H., Fong, A.T., Leung, S., Chin, T.Y., Lo, C., Lui, M.S., Lee, J., Chiu, K.H., Chung, T.H., Lee, E., Wan, E., Hung, I., Lam, T., Kuo, M., Ng, M.Y.: Frequency and distribution of chest radiographic findings in patients positive for COVID-19. Radiology 296(2), E72–E78 (2020)
Zhang, T.Y., Suen, C.Y.: A fast parallel algorithm for thinning digital patterns. Commun. ACM 27(3), 236–239 (1984)
Lopez-Cabrera, J.D., Orozco-Morales, R., et al.: Current limitations to identify COVID-19 using artifcial intelligence with chest X-ray imaging. Health Technol. 11, 411–424 (2021)
Maguolo, G., Nanni, L.: A critic evaluation of methods for COVID-19 automatic detection from X-ray. Inf. Fus. 76, 1–7 (2021)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Moskal, A., Jasionowska-Skop, M., Ostrek, G., Przelaskowski, A. (2022). Artifact Detection on X-ray of Lung with COVID-19 Symptoms. In: Pietka, E., Badura, P., Kawa, J., Wieclawek, W. (eds) Information Technology in Biomedicine. ITIB 2022. Advances in Intelligent Systems and Computing, vol 1429. Springer, Cham. https://doi.org/10.1007/978-3-031-09135-3_20
Download citation
DOI: https://doi.org/10.1007/978-3-031-09135-3_20
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-09134-6
Online ISBN: 978-3-031-09135-3
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)