Advertisement

Automatic optic disc detection using low-rank representation based semi-supervised extreme learning machine

  • Wei Zhou
  • Shaojie QiaoEmail author
  • Yugen YiEmail author
  • Nan Han
  • Yuqi Chen
  • Gang Lei
Original Article

Abstract

Optic disc detection plays an important role in developing automatic screening systems for diabetic retinopathy. Several supervised learning-based approaches have been proposed for optic disc detection. However, these approaches demand that the input training examples are completely labelled. Essentially, in medical image analysis, it is difficult to prepare several training samples which were given reliable class labels due to the fact that manually labelling data is very expensive. Moreover, retinal images such as complex vessels structures in the optic disc constituting nonlinear relationships in high-dimensional observation space, which cannot work well by traditional linear classifiers. In this study, a novel approach named low-rank representation based semi-supervised extreme learning machine (LRR-SSELM) is proposed for automated optic disc detection. Our model has the following advantages. First, it detects the optic disc from the viewpoint of semi-supervised learning and overcomes the problem there are small portion of labelled samples. Second, a nonlinear classifier is introduced into our model to fully explore the nonlinear data. Third, the local and global structures of original data can be greatly persevered by low-rank representation (LRR). The performance of the proposed method is validated on three publicly available databases, DIARETDB0, DIARETDB1 and Messidor. The experimental results indicate the advantages and effectiveness of the proposed approach.

Keywords

Retinal fundus images Optic disc Low-rank representation Semi-supervised extreme learning machine 

Notes

Acknowledgements

This study was supported in part by the National Natural Science Foundation of China under Grant Nos. 61602221, 61772091, 61762050, 61802035 and 4166108; the Natural Science Foundation of Jiangxi Province under Grant No. 20171BAB212009; the Sichuan Science and Technology Program under Grant No. 2018JY0448; the National Natural Science Foundation of Guangxi under Grant No. 2018GXNSFDA138005; the Innovative Research Team Construction Plan in Universities of Sichuan Province under Grant No. 18TD0027; the Scientific Research Foundation for Advanced Talents of Chengdu University of Information Technology under Grant Nos. KYTZ201715 and KYTZ201750; the Scientific Research Foundation for Young Academic Leaders of Chengdu University of Information Technology under Grant No. J201701; Guangdong Pre-national project under Grant No. 2014GKXM054.

Compliance with ethical standards

Conflict of interest

All authors declare that this support does not lead to any conflict of interest regarding the publication of this paper.

References

  1. 1.
    Li R, Qin L, Yu J, Mao R (2015) Influential community search in large networks. Proc Vldb Endowment 8(5):509–520Google Scholar
  2. 2.
    Li R, Qin L, Yu J, Mao R (2017) Finding influential communities in massive networks. Vldb J 26(2):1–26Google Scholar
  3. 3.
    Li R, Qin L, Ye F, Yu J, Xiao X, Xiao N, Zhang Z (2018) Skyline community search in multi-valued networks. In: Proceedings of the 2018 international conference on management of data, pp. 457–472Google Scholar
  4. 4.
    Zhou W, Wu C, Gao Y, Yu X (2017) Automatic optic disc boundary extraction based on saliency object detection and modified local intensity clustering model in retinal images. Inst Electron Inf Commun Eng E 100-A(9):2069–2072Google Scholar
  5. 5.
    Zhou W, Wu C, Yu X, Gao Y, Du W (2017) Automatic Fovea Center localization in retinal images using saliency-guided object discovery and feature extraction. J Med Imaging Health Inf 7:1–8Google Scholar
  6. 6.
    Zhou W, Wu C, Du W (2017) Automatic Optic Disc Detection in Retinal Images via Group Sparse Regularization Extreme Learning Machine. Control Conference (CCC), 36th Dalian, ChinaGoogle Scholar
  7. 7.
    Osareh A, Mirmehdi M, Thomas B, Markham R (2002) Classification and localisation of diabetic-related eye disease. In: 7th European conference on computer vision (ECCV). May 2353:502–516Google Scholar
  8. 8.
    Sinthanayothin C, Boyce J, Cook H, Williamson T (1999) Automated localisation of the optic disc, fovea and retinal blood vessels from digital colour fundus images. Br J Ophthalmol 83:902–910Google Scholar
  9. 9.
    Li H, Chutatape O (2004) Automated feature extraction in color retinal images by a model based approach. IEEE Trans Biomed Eng 51:246–254Google Scholar
  10. 10.
    Park M, Jin JS, Luo S (2006) Locating the optic disc in retinal images. In: Proceedings of the international conference on computer graphics, imaging and visualisation, pp 141–145Google Scholar
  11. 11.
    Seo JM, Kim KK, Kim JH, Park KS, Chung H (2004) Measurement of ocular torsion using digital fundus image. In: International conference of the IEEE engineering in medicine and biology society, 3, 1711Google Scholar
  12. 12.
    Liu S, Chen J (2011) Detection of the optic disc on retinal fluorescein angiograms. J Med Biol Eng 31(6):405–412Google Scholar
  13. 13.
    Mithun NC, Das S, Fattah SA (2014) Automated detection of optic disc and blood vessel in retinal image using morphological, edge detection and feature extraction technique. In: Proceedings of the 16th international conference on computer and information technology (ICCIT’14), pp 98–102Google Scholar
  14. 14.
    Lalonde M, Beaulieu M, Gagnon L (2001) Fast and robust optic disc detection using pyramidal decomposition and hausdorff based template matching. IEEE Trans Med Imaging 20(11):1193–1200Google Scholar
  15. 15.
    Youssif AR, Ghalwash AZ, Ghoneim AR (2008) Optic disc detection from normalized digital fundus images by means of a vessels’ direction matched filter. IEEE Trans Med Imaging 27(1):11–18Google Scholar
  16. 16.
    Zhang B, Karray F (2010) Optic disc and fovea detection via multi-scale matched filters and a vessels’ directional matched filter. In: Autonomous and intelligent systems—first international conference, pp 1–5Google Scholar
  17. 17.
    Niemeijer M, Abràmoff MD, Ginneken BV (2009) Fast detection of the optic disc and fovea in color fundus photographs. Med Image Anal 13(6):859–870Google Scholar
  18. 18.
    Tobin KW, Chaum E, Govindasamy VP, Karnowski TP (2007) Detection of anatomic structures in human retinal imagery. IEEE Trans Med Imaging 26(12):1729–1739Google Scholar
  19. 19.
    Perez CA, Schulz DA, Aravena CM, Perez CI, Verdaguer TJ (2013) A new method for online retinal optic-disc detection based on cascade classifiers. In: Proceedings of the 2013 IEEE international conference on systems, pp 4300–4304Google Scholar
  20. 20.
    Zhou W, Wu C, Chen D, Yi Y, Du W (2017) Automatic microaneurysm detection using the sparse principal component analysis-based unsupervised classification method. IEEE Access 5(99):2563–2572Google Scholar
  21. 21.
    Zhou W, Wu C, Yi Y, Du W (2017) Automatic detection of exudates in digital color fundus images using superpixel multi-feature classification. IEEE Access 5:17077–17088Google Scholar
  22. 22.
    Zhou W, Wu H, Wu C, Yu X, Yi Y (2018) Automatic optic disc detection in color retinal images by local feature spectrum analysis. Comput Math Methods Med 2018:1–12Google Scholar
  23. 23.
    Benhur A, Weston J (2010) A user’s guide to support vector machines. Methods Mol Biol 609(2010):223Google Scholar
  24. 24.
    Cao W, Wang X, Ming Z, Gao J (2018) A review on neural networks with random weights. Neurocomputing 275:278–287Google Scholar
  25. 25.
    Wang X, Cao W (2018) Non-iterative approaches in training feed-forward neural networks and their applications. Soft Comput 22(11):3473–3476zbMATHGoogle Scholar
  26. 26.
    Zhai J, Zhang S, Wang C (2017) The classification of imbalanced large data sets based on mapreduce and ensemble of elm classifiers. Int J Mach Learn Cybern 8(3):1009–1017Google Scholar
  27. 27.
    Cao W, Gao J, Ming Z, Cai S, Shan Z (2018) Fuzziness-based online sequential extreme learning machine for classification problems. Soft Comput 22(11):3487–3494Google Scholar
  28. 28.
    Liu M, Liu B, Zhang C, Wang W, Sun W (2017) Semi-supervised low rank kernel learning algorithm via extreme learning machine. Int J Mach Learn Cybern 8(3):1039–1052Google Scholar
  29. 29.
    Ding S, Zhang N, Zhang J, Xu X, Shi Z (2017) Unsupervised extreme learning machine with representational features. Int J Mach Learn Cybern 8(2):587–595Google Scholar
  30. 30.
    Mao W, Wang J, Xue Z (2017) An ELM-based model with sparse-weighting strategy for sequential data imbalance problem. Int J Mach Learn Cybern 8(4):1333–1345Google Scholar
  31. 31.
    Yi Y, Chen Y, Dai J, Gui X, Chen C, Lei G, Wang W (2018) Semi-supervised ridge regression with adaptive graph-based label propagation. Appl Sci 8(12):2631–2636Google Scholar
  32. 32.
    Huang G, Song S, Gupta JN, Wu C (2014) Semi-supervised and unsupervised extreme learning machines. Cybern IEEE Trans 44(12):2405–2417Google Scholar
  33. 33.
    Liu G, Lin Z, Yan S, Sun J, Yu Y, Ma Y (2013) Robust recovery of subspace structures by low-rank representation. IEEE Trans Pattern Anal Mach Intell 35(1):171–184Google Scholar
  34. 34.
    Sánchez CI, Hornero R, López MI (2008) A novel automatic image processing algorithm for detection of hard exudates based on retinal image analysis. Med Eng Phys 30(3):350–357Google Scholar
  35. 35.
    Reza AM (2004) Realization of the contrast limited adaptive histogram equalization (clahe) for real-time image enhancement. J Signal Process Syst 38(1):35–44Google Scholar
  36. 36.
    Bharath R, Nicholas LZJ, Xiang C (2013) Scalable scene understanding using saliency-guided object localization. IEEE Int Conf Control Autom 45(5):1503–1508Google Scholar
  37. 37.
    Matlab r2015 documentation (2015) Morphological reconstruction. https://ww2.mathworks.cn/help/images/ref/imreconstruct.html
  38. 38.
    Huang G, Zhu Q, Siew C (2006) Extreme learning machine: theory and applications. Neurocomputing 70(1–3):489–501Google Scholar
  39. 39.
    Liu T, Huang GB, Lin Z (2018) Extreme learning machine for joint embedding and clustering. Neurocomputing 277:78–88Google Scholar
  40. 40.
    Yao L, Ge Z (2018) Deep learning of semi-supervised process data with hierarchical extreme learning machine and soft sensor application. IEEE Trans Industr Electron 65(2):1490–1498Google Scholar
  41. 41.
    Pang J, Gu Y, Xu J, Yu G (2018) Semi-supervised multi-graph classification using optimal feature selection and extreme learning machine. Neurocomputing 277:89–100Google Scholar
  42. 42.
    Chen Y, Song S, Li S, Lang L, Wu C (2018) Domain space transfer extreme learning machine for domain adaptation. IEEE Trans Cybern PP(99):1–14Google Scholar
  43. 43.
    Yi Y, Qiao S, Zhou W, Zheng C, Liu Q, Wang J (2018) Adaptive multiple graph regularized semi-supervised extreme learning machine. Soft Comput 22(11):3545–3562zbMATHGoogle Scholar
  44. 44.
    Wright J, Yang AY, Ganesh A, Sastry SS, Ma Y (2009) Robust face recognition via sparse representation. IEEE Trans Pattern Anal Mach Intell 31(2):210–227Google Scholar
  45. 45.
    Zhang L, Yang M, Feng X (2011) Sparse representation or collaborative representation: which helps face recognition? In: Proceeding of IEEE international conference on computer vision, pp 471–478Google Scholar
  46. 46.
    DIARETDB0. Standard diabetic retinopathy database. http://www.it.lut.fi/project/imageret/diaretdb0/. Accessed 30 May 2007
  47. 47.
    Kauppi T, Kalesnykiene V, Kamarainen JK, Lensu L, Sorri I, Raninen A et al (2013) DIARETDB1 diabetic retinopathy database and evaluation protocol. In: British machine vision conference 2007, University of Warwick, UK, September. DBLPGoogle Scholar
  48. 48.
    Decencière E, Zhang X, Cazuguel G, Lay B, Cochener B, Trone C, Gain P, Ordonez R, Massin P, Erginay A, Charton B, Klein JC (2014) Feedback on a publicly distributed image database: the Messidor database. Image Anal Stereol 33(3):231–234zbMATHGoogle Scholar
  49. 49.
    Wang J, Zhao R, Wang Y, Zheng C, Kong J, Yi Y (2017) Locality constrained graph optimization for dimensionality reduction. Neurocomputing 245:55–67Google Scholar
  50. 50.
    An S, Liu W, Venkatesh S (2007) Face recognition using kernel ridge regression. Proc IEEE Int Conf Comput Vis 5(6):1–7Google Scholar
  51. 51.
    Xiang S, Nie F, Zhang C (2010) Semi-supervised classification via local spline regression. IEEE Trans Pattern Anal Mach Intell 32(11):2039–2053Google Scholar
  52. 52.
    Yu H, Barriga ES, Agurto C, Echegaray S, Pattichis MS, Bauman W (2012) Fast localization and segmentation of optic disk in retinal images using directional matched filtering and level sets. IEEE Trans Inf Technol Biomed 16(4):644–657Google Scholar
  53. 53.
    Ahmed MI, Amin MA (2015) High speed detection of optical disc in retinal fundus image. Signal Image Video Processing 9(1):77–85Google Scholar
  54. 54.
    Aquino A, Gegundez ME, Marin D (2012) Automated optic disc detection in retinal images of patients with diabetic retinopathy and risk of macular edema. Int J Biol Life Sci 8(2):87–92Google Scholar
  55. 55.
    Dashtbozorg B, Zhang J, Huang F, Haar Romeny ter BM (2016) Automatic optic disc and fovea detection in retinal images using super-elliptical convergence index filters. In: Proceedings of the international conference image analysis and recognition, pp 697–706Google Scholar
  56. 56.
    Qureshi RJ, Kovacs L, Harangi B, Nagy B, Peto T, Hajdu A (2012) Combining algorithms for automatic detection of optic disc and macula in fundus images. Comput Vis Image Underst 116:138–145Google Scholar
  57. 57.
    Pereira C, Gonçalves L, Ferreira M (2013) Optic disc detection in color fundus images using ant colony optimization. Med Biol Eng Comput 51:295–303Google Scholar
  58. 58.
    Rahebi J, Hardalaç F (2016) A new approach to optic disc detection in human retinal images using the firefly algorithm. Med Biol Eng Comput 54(2–3):453–461Google Scholar
  59. 59.
    Qiao S, Han N, Gao Y, Li R-H, Huang J, Guo J, Gutierrez LA, Wu X (2018) A fast parallel community discovery model on complex networks through approximate optimization. IEEE Trans Knowl Data Eng 30(9):1638–1651Google Scholar
  60. 60.
    Qiao S, Han N, Wang J, Li R-H, Gutierrez LA, Wu X (2017) Predicting long-term trajectories of connected vehicles via the prefix-projection technique. IEEE Trans Intell Transp Syst 19(7):2305–2315Google Scholar
  61. 61.
    Qiao S, Han N, Zhu W, Gutierrez LA (2015) Traplan: an effective three-in-one trajectory-prediction model in transportation networks. IEEE Trans Intell Transp Syst 16(3):1188–1198Google Scholar
  62. 62.
    Qiao S, Shen D, Wang X, Han N, Zhu W (2015) A self-adaptive parameter selection trajectory prediction approach via hidden markov models. IEEE Trans Intell Transp Syst 16(1):284–296Google Scholar
  63. 63.
    Yi Y, Zhou W, Bi C, Luo G, Cao Y, Shi Y (2017) Inner product regularized nonnegative self representation for image classification and clustering. IEEE Access 5:14165–14176Google Scholar
  64. 64.
    Yi Y, Zhou W, Liu Q, Luo G, Wang J, Fang Y, Zheng C (2018) Ordinal preserving matrix factorization for unsupervised feature selection. Sig Process Image Commun 67:118–131Google Scholar
  65. 65.
    Yi Y, Zhou W, Shi Y, Dai J (2018) Speedup two-class supervised outlier detection. IEEE Access 6:63923–63933Google Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2019

Authors and Affiliations

  1. 1.College of Computer ScienceShenyang Aerospace UniversityShenyangChina
  2. 2.School of Software EngineeringChengdu University of Information TechnologyChengduChina
  3. 3.School of SoftwareJiangxi Normal UniversityNanchangChina
  4. 4.School of ManagementChengdu University of Information TechnologyChengduChina

Personalised recommendations