Skip to main content
SpringerLink
Log in

A novel graph-based multi-view spectral clustering: application to X-ray image analysis for COVID-19 recognition

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

Nowadays, machine learning tools and, in particular, classification methods are often used to diagnose COVID-19 cases. However, these methods use a single view of the dataset and assume that the labels of the datasets are known in advance. Due to the extensive use of COVID-19 and the enormous amount of patient data whose labels are unknown, unsupervised learning may be useful in evaluating these photographs. The contribution of this work is twofold. First, we present an improved and generic method for direct multi-view clustering. Second, we apply this method to unsupervised clustering of chest X-ray images. To our knowledge, this is the first attempt to apply unsupervised multi-view clustering to chest X-ray images. We can use an unsupervised learning paradigm and benefit from the wealth of unlabeled data without relying on human experts to label a large number of images. Here, we present an improved version of a recently developed direct method that estimates both nonnegative cluster indices and spectral embeddings. The proposed model includes two types of constraints in addition to the advantages of this method: (i) consistent smoothing of cluster labels across all views and (ii) an orthogonality constraint on the nonnegative embedding matrix (cluster assignment). The COVIDx dataset with three classes is used to demonstrate the advantages of the proposed method. Chest X-ray images were clustered into different classes with promising results. To demonstrate the efficiency of the proposed strategy, other image datasets are used to evaluate the proposed clustering method.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3

Similar content being viewed by others

Data availability statement

The data that support the findings of this study are available from the corresponding author upon reasonable request.

Notes

  1. https://github.com/lindawangg/COVID-Net/blob/master/docs/COVIDx.md.

  2. https://www.researchgate.net/publication/335857675.

  3. http://www.vision.caltech.edu/ImageDatasets/Caltech101/.

  4. http://yann.lecun.com/exdb/mnist/.

References

  1. Chao G, Sun S, Bi J (2021) A survey on multi-view clustering. IEEE Trans Artific Intell

  2. Dai J, Ren Z, Luo Y, Song H, Yang J (2021) Multi-view clustering with latent low-rank proxy graph learning. Cogn Comput 13:1049–1060

    Article  Google Scholar 

  3. Dornaika F, Baradaaji A, El Traboulsi Y (2021) Semi-supervised classification via simultaneous label and discriminant embedding estimation. Inf Sci 546:146–165

    Article  MathSciNet  MATH  Google Scholar 

  4. El Hajjar S, Dornaika F, Abdallah F (2022) One-step multi-view spectral clustering with cluster label correlation graph. Inf Sci

  5. Frid-Adar M, Amer R, Gozes O, Nassar J, Greenspan H (2021) Covid-19 in cxr: from detection and severity scoring to patient disease monitoring. IEEE J Biomed Health Inform 25(6):1892–1903

    Article  Google Scholar 

  6. Greene D, Cunningham P (2009) A matrix factorization approach for integrating multiple data views. In: Joint European conference on machine learning and knowledge discovery in databases, pp 423–438 Springer

  7. Han X, Hu Z, Wang S, Zhang Y (2023) A survey on deep learning in covid-19 diagnosis. J Imag 9(1)

  8. He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR), pp 770–778

  9. Horie M, Kasai H (2021) Consistency-aware and inconsistency-aware graph-based multi-view clustering. In: 2020 28th European signal processing conference, pp 1472–1476

  10. Hu Z, Nie F, Chang W, Hao S, Wang R, Li X (2020) Multi-view spectral clustering via sparse graph learning. Neurocomputing 384:1–10

    Article  Google Scholar 

  11. Hu Z, Nie F, Wang R, Li X (2020) Multi-view spectral clustering via integrating nonnegative embedding and spectral embedding. Inf Fusion 55:251–259

    Article  Google Scholar 

  12. Huang G, Liu Z, Van Der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. In: 2017 IEEE conference on computer vision and pattern recognition (CVPR), pp 2261–2269

  13. Huang S, Kang Z, Tsang IW, Xu Z (2019) Auto-weighted multi-view clustering via kernelized graph learning. Pattern Recogn 88:174–184

    Article  Google Scholar 

  14. Jacobi A, Chung M, Bernheim A, Eber C (2020) Portable chest x-ray in coronavirus disease-19 (covid-19): a pictorial review. Clin Imaging 64:35–42

    Article  Google Scholar 

  15. Kang Z, Peng C, Cheng Q (2017) Kernel-driven similarity learning. Neurocomputing 267:210–219

    Article  Google Scholar 

  16. Kang Z, Shi G, Huang S, Chen W, Pu X, Zhou JT, Xu Z (2020) Multi-graph fusion for multi-view spectral clustering. Knowl-Based Syst 189:105102

    Article  Google Scholar 

  17. Kumar A, Daumé H (2011) A co-training approach for multi-view spectral clustering. In Proceedings of the 28th international conference on international conference on machine learning, ICML’11, Madison, WI, USA, pp 393–400

  18. Kumar A, Rai P, Daumé H (2011) Co-regularized multi-view spectral clustering. In: Proceedings of the 24th international conference on neural information processing systems, NIPS’11. Red Hook, NY, USA, pp 1413–1421

  19. Li J, Wang JZ (2008) Real-time computerized annotation of pictures. IEEE Trans Pattern Anal Mach Intell 30(6):985–1002

    Article  Google Scholar 

  20. Liu X, Zhu X, Li M, Wang L, Tang C, Yin J, Shen D, Wang H, Gao W (2018) Late fusion incomplete multi-view clustering. IEEE Trans Pattern Anal Mach Intell 41(10):2410–2423

    Article  Google Scholar 

  21. Nie F, Cai G, Li J, Li X (2017) Auto-weighted multi-view learning for image clustering and semi-supervised classification. IEEE Trans Image Process 27(3):1501–1511

    Article  MathSciNet  MATH  Google Scholar 

  22. Nie F, Li J, Li X, et al (2016) parameter-free auto-weighted multiple graph learning: a framework for multiview clustering and semi-supervised classification. In: Proceedings of the twenty-fifth international joint conference on artificial intelligence, pp 1881–1887

  23. Nie F, Li J, Li X, et al (2017) Self-weighted multiview clustering with multiple graphs. In IJCAI, pp 2564–2570

  24. Nie F, Tian L, Li X (2018) Multiview clustering via adaptively weighted procrustes. In Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery and data mining, pp 2022–2030

  25. Nie F, Wang X, Jordan MI, Huang H (2016) The constrained laplacian rank algorithm for graph-based clustering. In: AAAI, pp 1969–1976

  26. Ren Z, Lei H, Sun Q, Yang C (2021) Simultaneous learning coefficient matrix and affinity graph for multiple kernel clustering. Inf Sci 547:289–306

    Article  MathSciNet  MATH  Google Scholar 

  27. Ren Z, Li H, Yang C, Sun Q (2020) Multiple kernel subspace clustering with local structural graph and low-rank consensus kernel learning. Knowl-Based Syst 188:105040

    Article  Google Scholar 

  28. Rubin GD, Ryerson CJ, Haramati LB, Sverzellati N, Kanne JP, Raoof S, Schluger NW, Volpi A, Yim J-J, Martin IB et al (2020) The role of chest imaging in patient management during the covid-19 pandemic: a multinational consensus statement from the fleischner society. Radiology 296(1):172–180

    Article  Google Scholar 

  29. Shah FM, Joy SKS, Ahmed F, Hossain T, Humaira M, Ami AS, Paul S, Ji M, Ahmed S (2021) A comprehensive survey of covid-19 detection using medical images. SN Comput Sci 2(6):434

    Article  Google Scholar 

  30. Shi S, Nie F, Wang R, Li X (2020) Auto-weighted multi-view clustering via spectral embedding. Neurocomputing 399:369–379

    Article  Google Scholar 

  31. Tang C, Zhu X, Liu X, Li M, Wang P, Zhang C, Wang L (2018) Learning a joint affinity graph for multiview subspace clustering. IEEE Trans Multimed 21(7):1724–1736

    Article  Google Scholar 

  32. Tartare G, Hamad D, Azahaf M, Puech P, Betrouni N (2014) Spectral clustering applied for dynamic contrast-enhanced mr analysis of time-intensity curves. Comput Med Imaging Graph 38:702–13

    Article  Google Scholar 

  33. Vantaggiato E, Paladini E, Bougourzi F, Distante C, Hadid A, Taleb-Ahmed A (2021) Covid-19 recognition using ensemble-cnns in two new chest x-ray databases. Sensors 21(5)

  34. Varekamp K (2021) Are classes clusters? https://arxiv.org/abs/2104.07840

  35. White M, Zhang X, Schuurmans D, Yu Y.-l (2012) Convex multi-view subspace learning. In: Advances in neural information processing systems, pp 1673–1681

  36. Wong HYF, Lam HYS, Fong AH-T, Leung ST, Chin TW-Y, Lo CSY, Lui MM-S, Lee JCY, Chiu KW-H, Chung TW-H et al (2020) Frequency and distribution of chest radiographic findings in patients positive for covid-19. Radiology 296(2):E72–E78

    Article  Google Scholar 

  37. Xia T, Tao D, Mei T, Zhang Y (2010) Multiview spectral embedding. IEEE Trans Syst Man Cybern 40(6):1438–1446

    Article  Google Scholar 

  38. Xu Y-M, Wang C-D, Lai J-H (2016) Weighted multi-view clustering with feature selection. Pattern Recogn 53:25–35

    Article  Google Scholar 

  39. Yang Y, Wang H (2018) Multi-view clustering: a survey. Big Data Mining Anal 1(2):83–107

    Article  Google Scholar 

  40. Yin Q, Wu S, He R, Wang L (2015) Multi-view clustering via pairwise sparse subspace representation. Neurocomputing 156:12–21

    Article  Google Scholar 

  41. Zhan K, Nie F, Wang J, Yang Y (2019) Multiview consensus graph clustering. IEEE Trans Image Process 28(3):1261–1270

    Article  MathSciNet  Google Scholar 

  42. Zhou T, Zhang C, Peng X, Bhaskar H, Yang J (2020) Dual shared-specific multiview subspace clustering. IEEE Trans Cybern 50:3517–3530

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Ho Chi Minh City Open University, 97 Vo Van Tan, Ward Vo Thi Sau, District 3, Ho Chi Minh City, 70000, Vietnam

    F. Dornaika & V. Truong Hoang

Authors
  1. F. Dornaika
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. V. Truong Hoang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to F. Dornaika.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Dornaika, F., Hoang, V.T. A novel graph-based multi-view spectral clustering: application to X-ray image analysis for COVID-19 recognition. Neural Comput & Applic 35, 22043–22053 (2023). https://doi.org/10.1007/s00521-023-08975-2

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-023-08975-2

Keywords

Search

Navigation