Abstract
The main objective of this study was to effectively segment the lung tissue area in chest radiograms (called a chest X-ray: CXR). The results of conducted analysis were related to the requirements of effective detection and description of COVID-19 (C-19) symptoms to support the diagnosis of this disease. The proposed method uses the concept of representing the chest radiogram using a dictionary of matched lung shape patterns in reference CXRs. The initial lung shape approximation is then corrected by non-rigid registration based on the tissue texture distribution. The optimization criteria used emphasize tissue features that may have diagnostic significance. We refer to this as the semantic, more reliable lung segmentation required by C-19 diagnostic support. The obtained efficiency is comparable to the best ML reference methods and not far from the average efficiency of DL methods. The relatively high values of the minimum fit indices demonstrate the stability and reliability of the segmentation performed.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Mardian, Y., Kosasih, H., et al.: Review of current COVID-19 diagnostics and opportunities for further development. Front. Med. 8, 615099 (2021)
Laskar, P., Yallapu, M.M., Chauhan, S.C.: “Tomorrow Never Dies’’: Recent advances in diagnosis, treatment, and prevention modalities against coronavirus (COVID-19) amid controversies. Diseases 8, 30 (2020)
Yamac, M., Ahishali, M., et al.: Convolutional sparse support estimator-based COVID-19 recognition from X-ray images. IEEE Tran. Neura Networks Learn. Syst. 32(5), 1810–1820 (2021)
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, 411–24 (2021)
Flor, N., et al.: Diagnostic performance of chest radiography in high COVID-19 prevalence setting: experience from a European reference hospital. Emergency Radiol. 28(5), 877–885 (2021). https://doi.org/10.1007/s10140-021-01946-x
Reamaroon, N., Sjoding, M.W., et al.: Robust segmentation of lung in chest x-ray: applications in analysis of acute respiratory distress syndrome. BMC Med. Imaging 20, 116 (2020)
Liu, X., Li, K.-W., et al.: Review of deep learning based automatic segmentation for lung cancer radiotherapy. Front. Oncol. 11, 717039 (2021)
Candemir, S., Jaeger, S., Palaniappan, K., et al.: Lung segmentation in chest radiographs using anatomical atlases with nonrigid registration. IEEE Tran. Med. Imaging 33(2), 577–590 (2014)
Candemir, S., Antani, S.: A review on lung boundary detection in chest X-rays. Int. J. Comput. Assist. Radiol. Surg. 14(4), 563–576 (2019). https://doi.org/10.1007/s11548-019-01917-1
Teixeira, L.O., Pereira, R.M., Bertolini, D., et al.: Impact of lung segmentation on the diagnosis and explanation of COVID-19 in chest X-ray images. Sensors 21, 7116 (2021)
Calli, E., Sogancioglu, E., et al.: Deep learning for chest X-ray analysis: a survey. Med. Image Anal. 72, 102125 (2021)
Maguolo, G., Nanni, L.: A critic evaluation of methods for COVID-19 automatic detection from X-ray images. Inf. Fusion 76, 1–7 (2021)
Yu, Y., Hu, P., Lin, J., Krishnaswamy, P.: Multimodal multitask deep learning for X-ray image retrieval. In: de Bruijne, M., Cattin, P.C., Cotin, S., Padoy, N., Speidel, S., Zheng, Y., Essert, C. (eds.) MICCAI 2021. LNCS, vol. 12905, pp. 603–613. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-87240-3_58
Stengers, I.: Thinking with Whitehead: A Free and Wild Creation of Concepts. Harvard University Press, Cambridge (2014)
Wang, H., Wang, Q., et al.: Multi-scale location-aware kernel representation for object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1248–57 (2018)
Thompson, J.R.: Empirical Model Building: Data, Models, and Reality. Wiley, Hoboken (2011)
Hassanien, A.E., Mahdy, L.N., et al.: Automatic xray covid-19 lung image classification system based on multi-level thresholding and support vector machine. medRxiv (2020)
Mohammed, S.N., Alkinani, F.S., Hassan, Y.A.: Automatic computer aided diagnostic for COVID-19 based on chest X-ray image and particle swarm intelligence. Int. J. Intell. Eng. Syst. 13, 5 (2020)
Philipsen, R.H.H.M., Maduskar, P., et al.: Localized energy-based normalization of medical images: application to chest radiography. IEEE Trans. Med. Imaging 34(9), 1965–1975 (2015)
Chen, S., Cai, Y.: Enhancement of chest radiograph in emergency intensive care unit by means of reverse anisotropic diffusion-based unsharp masking model. Diagnostics 9, 45 (2019)
Khodaskar, A., Ladhake, S.: Semantic image analysis for intelligent image retrieval. Procedia Comput. Sci. 48, 192–197 (2015)
Chenggang, L.L., Yan, C., et al.: Distributed image understanding with semantic dictionary and semantic expansion. Neurocomputing 174(A), 384–392 (2016)
DeVore, R.A.: Nonlinear approximation. Acta Numerica 7, 51–150 (1998)
Zhong, A., Li, X., et al.: Deep metric learning-based image retrieval system for chest radiograph and its clinical applications in COVID-19. Med. Image Anal. 70, 101993 (2021)
Shiraishi, J., Katsuragawa, S., Ikezoe, J., et al.: Development of a digital image database for chest radiographs with and without a lung nodule: receiver Operating Characteristic analysis of radiologists’ detection of pulmonary nodules. AJR 174, 71–74 (2000)
Jeager, S., Candemir, S., et al.: Two public chest X-ray datasets for computer-aided screening of pulmonary diseases. Quant. Imaging Med. Surg. 4(6), 475–477 (2014)
Pogarell, T., Bayer, N., et al.: Evaluation of a novel content-based image retrieval system for the differentiation of interstitial lung diseases in CT examinations. Diagnostics 11, 2114 (2021)
Nonrigid registration of lung CT images based on tissue features. Comput. Math. Meth. Med. 834192, 1–7 (2013)
Sampat, M.P., Wang, Z., et al.: Complex wavelet structural similarity: a new image similarity index. IEEE Tran. Image Proc. 18(11), 2385–2401 (2009)
Nabizadeh-Shahre-Babak, Z., Karimi, N., et al.: Detection of COVID-19 in X-ray images by classification of bag of visual words using neural networks. Biomed. Signal Process. Control 68, 102750 (2021)
Liu, C., Yuen, J., Torralba, A.: SIFT flow: dense correspondence across different scenes and its applications. IEEE Trans. Pattern Anal. Mach. Intell. 33(5), 978–994 (2011)
Ashour, A.S., Eissa, M.M., et al.: Ensemble-based bag of features for automated classification of normal and COVID-19 CXR images. Biomed. Signal Process. Control 68, 102656 (2021)
Moitra, D., Mandal, R.K.: Automated AJCC (7th edition) staging of non-small cell lung cancer (NSCLC) using deep convolutional neural network (CNN) and recurrent neural network (RNN). Health Inf Sci Syst. 7(1), 14 (2019)
Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 1, 886–893 (2005)
Moskal, A., Jasionowska-Skop, M., Ostrek, G., Przelaskowski, A.: Artifact detection on X-ray images of lung with COVID-19 symptoms. Submitted to IBIB 2022
Nguyen, H.Q., Lam, K., et al.: VinDr-CXR: an open dataset of chest X-rays with radiologist’s annotations. arXiv:2012.15029
YangW, W., Liu, Y., et al.: Lung field segmentation in chest radiographs from boundary maps by a structured edge detector. IEEE J. BiomedHealth Inform. 22(3), 842–851 (2018)
Ginneken, B., Stegmann, M., Loog, M.: Segmentation of anatomical structures in chest radiographs using supervised methods: a comparative study on a public database. Med. Image Anal. 10(1), 19–40 (2006)
Shao, Y., Gao, Y., et al.: Hierarchical lung field segmentation with joint shape and appearance sparse learning. IEEE Trans. Med. Imaging 33(9), 1761–1780 (2014)
Dawoud, A.: Lung segmentation in chest radiographs by fusing shape information in iterative thresholding. IET Comput. Vis. 5(3), 185–190 (2011)
Novikov, A., Major, D., et al.: Fully convolutional architectures for multi-class segmentation in chest radiographs. IEEE Trans. Med. Imaging 37(8), 1865–76 (2018)
Kalinovsky, A., Kovalev, V.: Lung image segmentation using deep learning methods and convolutional neural networks. Pattern recognition and information processing. Publishing Center of BSU, Minsk (2016)
Hwang, S., Park, S.: Accurate lung segmentation via network-wise training of convolutional networks. In: Cardoso, M.J., et al. (eds.) DLMIA/ML-CDS -2017. LNCS, vol. 10553, pp. 92–99. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-67558-9_11
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
Przelaskowski, A., Jasionowska-Skop, M., Ostrek, G. (2022). Semantic Segmentation of Abnormal Lung Areas on Chest X-rays to Detect COVID-19. 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_21
Download citation
DOI: https://doi.org/10.1007/978-3-031-09135-3_21
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)