Abstract
The novel coronavirus illness (COVID-19) is a highly contagious virus that has swept around the world and has presented a serious threat to every country’s economy and public health. It has been demonstrated that COVID-19 can be accurately diagnosed with computed tomography (CT) scans that automatically partition infected areas. However, accurate segmentation continues to be a difficult task, due to the lack of pixel-level annotated medical images. For the automatic segmentation of distinct COVID-19 infection zones, a Convolutional Block Attention U-Net with additional dilated blocks is proposed in this study. The suggested architecture for the automatic segmentation of COVID-19 chest CT images with a dual attention mechanism and dilated block performs remarkably well in experiments, reaching an IoU score of 89.0% and a dice score of 90.2%. The proposal provides a novel, promising approach for quantitative COVID-19 detection utilizing CT scans of lung infection by overcoming the aforementioned issues.
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
Coronavirus Update. https://www.worldometers.info/coronavirus/. Accessed 18 May 2022
Simpson, S., et al.: Radiological society of North America expert consensus statement on Proceedings of SPIE, vol. 11597 115972X-5. https://www.spiedigitallibrary.org/conference-proceedings-of-spie on 10 Apr 2022 Terms of Use: https://www.spiedigitallibrary.org/terms-of-use reporting chest CT findings related to COVID-19. Endorsed by the society of thoracic radiology, the American college of radiology, and RSNA. Radiology: Cardiothoracic Imaging 2(2) (2020)
Ai, T., et al.: Correlation of chest CT and RT-PCR testing for coronavirus disease 2019 (Covid-19) in China: a report of 1014 cases. Radiology 296(2) (2020)
Salehi, S., Abedi, A., Balakrishnan, S., Gholamrezanezhad, A.: Coronavirus disease 2019 (COVID-19): a systematic review of imaging findings in 919 patients. Am. J. Roentgenol. 1–7 (2020)
Shan, F., et al.: Lung infection quantification of Covid-19 in CT images with deep learning. arXiv preprint arXiv:2003.04655 (2020)
Shi, F., et al.: Review of artificial intelligence techniques in imaging data acquisition, segmentation and diagnosis for Covid-19. arXiv preprint arXiv:2004.02731 (2020)
Shen, D., Wu, G., Suk, H.-I.: Deep learning in medical image analysis. Annu. Rev. Biomed. Eng. 19, 221–248 (2017)
Alom, M.Z., Hasan, M., Yakopcic, C., Taha, T.M., Asari, V.K.: Recurrent residual convolutional neural network based on U-Net (R2U-Net) for medical image segmentation. arXiv preprint arXiv:1802.06955 (2018)
Chen, X., Lina, Y., Yu, Z.: Residual attention U-Net for automated multi-class segmentation of Covid-19 chest CT images. arXiv preprint arXiv:2004.05645 (2020)
Zhao, X., et al.: D2A U-Net: automatic segmentation of Covid-19 lesions from CT slices with dilated convolution and dual attention mechanism. arXiv preprint arXiv:2102.05210 (2021)
Wang, Y., et al.: Does non-COVID-19 lung lesion help? Investigating transferability in COVID-19 CT image segmentation. Comput. Methods Programs Biomed. 202, 106004 (2021)
Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431–3440 (2015)
Woo, S., Park, J., Lee, J.-Y., Kweon, I.S.: CBAM: convolutional block attention module. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 3–19. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01234-2_1
Pei, H.-Y., Yang, D., Liu, G.-R., Lu, T.: MPS-Net: multi-point supervised network for CT image segmentation of COVID-19. IEEE Access 9, 47144–47153 (2021)
Yan, Q., et al.: COVID-19 chest CT image segmentation–a deep convolutional neural network solution. arXiv preprint arXiv:2004.10987 (2020)
Prakash, N.B., Murugappan, M., Hemalakshmi, G.R., Jayalakshmi, M., Mahmud, M.: Deep transfer learning for COVID-19 detection and infection localization with superpixel based segmentation. Sustain. Cities Soc. 75, 103252 (2021)
Yan, Q., et al.: COVID-19 chest CT image segmentation network by multi-scale fusion and enhancement operations. IEEE Trans. Big Data 7(1), 13–24 (2021)
https://www.kaggle.com/code/haksorus/covid19-lungs-inf-segmentation-baseline
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering
About this paper
Cite this paper
Ovi, T.B., Chowdhury, M.JU.K., Oyshee, S.S., Rizu, M.I. (2023). Infection Segmentation from COVID-19 Chest CT Scans with Dilated CBAM U-Net. In: Satu, M.S., Moni, M.A., Kaiser, M.S., Arefin, M.S. (eds) Machine Intelligence and Emerging Technologies. MIET 2022. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, vol 490. Springer, Cham. https://doi.org/10.1007/978-3-031-34619-4_12
Download citation
DOI: https://doi.org/10.1007/978-3-031-34619-4_12
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-34618-7
Online ISBN: 978-3-031-34619-4
eBook Packages: Computer ScienceComputer Science (R0)