Advertisement

Journal of Digital Imaging

, Volume 31, Issue 6, pp 869–878 | Cite as

Automated Quality Assessment of Colour Fundus Images for Diabetic Retinopathy Screening in Telemedicine

  • Sajib Kumar SahaEmail author
  • Basura Fernando
  • Jorge Cuadros
  • Di Xiao
  • Yogesan Kanagasingam
Article

Abstract

Fundus images obtained in a telemedicine program are acquired at different sites that are captured by people who have varying levels of experience. These result in a relatively high percentage of images which are later marked as unreadable by graders. Unreadable images require a recapture which is time and cost intensive. An automated method that determines the image quality during acquisition is an effective alternative. To determine the image quality during acquisition, we describe here an automated method for the assessment of image quality in the context of diabetic retinopathy. The method explicitly applies machine learning techniques to access the image and to determine ‘accept’ and ‘reject’ categories. ‘Reject’ category image requires a recapture. A deep convolution neural network is trained to grade the images automatically. A large representative set of 7000 colour fundus images was used for the experiment which was obtained from the EyePACS that were made available by the California Healthcare Foundation. Three retinal image analysis experts were employed to categorise these images into ‘accept’ and ‘reject’ classes based on the precise definition of image quality in the context of DR. The network was trained using 3428 images. The method shows an accuracy of 100% to successfully categorise ‘accept’ and ‘reject’ images, which is about 2% higher than the traditional machine learning method. On a clinical trial, the proposed method shows 97% agreement with human grader. The method can be easily incorporated with the fundus image capturing system in the acquisition centre and can guide the photographer whether a recapture is necessary or not.

Keywords

Automated quality assessment Colour fundus image Diabetic retinopathy Telemedicine Deep learning 

References

  1. 1.
    Michelson G Ed: Teleophthalmology in preventive medicine. Berlin Heidelberg: Springer, 2015Google Scholar
  2. 2.
    Patton N, Aslam TM, MacGillivray T, Deary IJ, Dhillon B, Eikelboom RH, Yogesan K, Constable IJ: Retinal image analysis: concepts, applications and potential. Prog Retin Eye Res 25(1):99–127, 2011CrossRefGoogle Scholar
  3. 3.
    Luzio S, Hatcher S, Zahlmann G, Mazik L, Morgan M, Liesenfeld B, Bek T, Schuell H, Schneider S, Owens DR, Kohner E: Feasibility of using the TOSCA telescreening procedures for diabetic retinopathy. Diabet Med. 21(10):1121–1128, 2004CrossRefGoogle Scholar
  4. 4.
    Sim DA, Keane PA, Tufail A, Egan CA, Aiello LP, Silva PS: Automated retinal image analysis for diabetic retinopathy in telemedicine. Current Diabetes Reports 15:14, 2015CrossRefGoogle Scholar
  5. 5.
    Vashist P, Singh S, Gupta N, Saxena R: Role of early screening for diabetic retinopathy in patients with diabetes mellitus: an overview. Indian journal of community medicine: official publication of Indian Association of Preventive & Social Medicine 36(4):247, 2011CrossRefGoogle Scholar
  6. 6.
    ETDRS Research Group: ETDRS report number 9. Early treatment diabetic retinopathy study research group. Ophthalmology 98(5 Suppl):766–785, 1991Google Scholar
  7. 7.
    Niemeijer M, Abramoff MD, van Ginneken B: Image structure clustering for image quality verification of color retina images in diabetic retinopathy screening. Med Image Anal. 10(6):888–898, 2006CrossRefGoogle Scholar
  8. 8.
    Abramoff MD, Suttorp-schulten MSA: Web-based screening for diabetic retinopathy in a primary care population: the EyeCheck project. J Telemed e-Health 11(6):668–675, 2005CrossRefGoogle Scholar
  9. 9.
    LeCun Y, Bengio Y, Hinton G: Deep learning. Nature [Internet] 521(7553):436–444, 2015.  https://doi.org/10.1038/nature14539%5Cn10.1038/nature14539 CrossRefGoogle Scholar
  10. 10.
    Giancardo L, Meriaudeau F, Karnowski TP,Chaum E, Tobin K: New developments in biomedical engineering. Domenico Campolo, Online: IntechOpen, 2010Google Scholar
  11. 11.
    UK National Screening Committee. Essential Elements in Developing a Diabetic Retinopathy Screening Programme. Available at https://bulger.co.uk/dacorumhealth/daccom/PDF%20Documents/Diabetic%20Retinopathy%20Screening%20(Workbook%20R4.1%202Aug07).pdf. Accessed 26 January 2017.
  12. 12.
    Paulus J, Meier J, Bock R, Hornegger J, Michelson G: Automated quality assessment of retinal fundus photos. Int J Comput Assist Radiol Surg. 5(6):557–564, 2010CrossRefGoogle Scholar
  13. 13.
    Imani E, Pourreza H, Banaee T: Retinal image quality assessment using Shearlet transform. In: Constanda C, Kirsch A Eds. Integral Methods in Science and Engineering. Cham: Birkhäuser, 2015, pp 329–339CrossRefGoogle Scholar
  14. 14.
    Lee SC, Wang Y: Automatic retinal image quality assessment and enhancement. Proceedings of SPIE Image Processing, 1999, pp 1581–1591Google Scholar
  15. 15.
    Lalonde M, Gagnon L, Boucher M: Automatic visual quality assessment in optical fundus images. Ottawa Proceedings of Vision Interface, 2001, pp 259–264Google Scholar
  16. 16.
    Davis H, Russell S, Barriga E, Abramoff M, Soliz P: Vision-based, real-time retinal image quality assessment. 22nd IEEE International Symposium on Computer-Based Medical Systems, 2009, pp 1–6Google Scholar
  17. 17.
    Bartling H, Wanger P, Martin L: Automated quality evaluation of digital fundus photographs. Acta Ophthalmol 87(6):643–647, 2009CrossRefGoogle Scholar
  18. 18.
    Dias J, Oliveira CM, Da Silva Cruz LA: Retinal image quality assessment using generic image quality indicators. Inf Fusion 19(1):73–90, 2014CrossRefGoogle Scholar
  19. 19.
    Usher DB, Himaga M, Dumskyj MJ: Automated assessment of digital fundus image quality using detected vessel area. Proceedings of Medical Image Understanding and Analysis, 2003, pp 81–84Google Scholar
  20. 20.
    Fleming AD, Philip S, Goatman KA, Olson JA, Sharp PF: Automated assessment of diabetic retinal image quality based on clarity and field definition. Investig Ophthalmol Vis Sci. 47(3):1120–1125, 2006CrossRefGoogle Scholar
  21. 21.
    Hunter A, Lowell JA, Habib M, Ryder B, Basu A, Steel D: An automated retinal image quality grading algorithm. Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society. EMBS, 2011, pp 5955–5958Google Scholar
  22. 22.
    Lowell J, Hunter A, Habib M, Steel D: Automated quantification of fundus image quality. 3rd European Medical and Biological Engineering Conference: 1618, 2005Google Scholar
  23. 23.
    Giancardo L, Abramoff MD, Chaum E, Karnowski TP, Meriaudeau F, Tobin KW: Elliptical local vessel density: a fast and robust quality metric for retinal images. Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society. EMBS, 2008, pp 3534–3537Google Scholar
  24. 24.
    Bengio Y: Learning deep architectures for AI. Found Trends®. Mach Learn. 2(1):1–127, 2009CrossRefGoogle Scholar
  25. 25.
    Schmidhuber J: Deep learning in neural networks: an overview. Neural Networks 61:85–117, 2015CrossRefGoogle Scholar
  26. 26.
    Krizhevsky A, Sutskever I, Hinton GE: ImageNet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems, 2012, pp 1–9Google Scholar
  27. 27.
    Saha S, Fletcher A, Xiao D, Kanagasingam Y: A novel method for automated correction of non-uniform/poor illumination of retinal images without creating false artifacts. J Vis Commun Image Represent 51:95–103, 2018CrossRefGoogle Scholar
  28. 28.
    Goatman KA, Whitwam AD, Manivannan A, Olson JA, Sharp PF: Colour normalisation of retinal images. Proceedings of medical image understanding and analysis: 49-52, 2003Google Scholar
  29. 29.
    Rosasco L, De Vito E, Caponnetto A, Piana M, Verri A: Are loss functions all the same? Neural Comput [Internet] 16(5):1063–1076, 2004 Available from: http://www.ncbi.nlm.nih.gov/pubmed/15070510 CrossRefGoogle Scholar
  30. 30.
    Tajbakhsh N, Shin JY, Gurudu SR, Hurst RT, Kendall CB, Gotway MB, Liang J: Convolutional neural networks for medical image analysis: full training or fine tuning? IEEE transactions on medical imaging. 35(5):1299–1312, 2016CrossRefGoogle Scholar
  31. 31.
    Saha SK, Xiao D, Fernando B, Tay-Kearney ML, An D, Kanagasingam Y: Deep learning based decision support system for automated diagnosis of age-related macular degeneration (AMD). Investigative Ophthalmology & Visual Science 58(8):25–25, 2017Google Scholar
  32. 32.
    Saha SK, Fernando B, Xiao D, Tay-Kearney ML, Kanagasingam Y: Deep learning for automatic detection and classification of microaneurysms, hard and soft exudates, and hemorrhages for diabetic retinopathy diagnosis. Investigative Ophthalmology & Visual Science 57(12):5962–5962, 2016Google Scholar
  33. 33.
    Jia Y, Shelhamer E, Donahue J, Karayev S, Long J, Girshick R, Guadarrama S, Darrell T: Caffe: convolutional architecture for fast feature embedding. Proceedings of the 22nd ACM International Conference on Multimedia, 2014, pp 675–678Google Scholar
  34. 34.
    Deng J, Dong W, Socher R, Li LJ, Li K, Fei-Fei L: ImageNet: a large-scale hierarchical image database. IEEE Computer Vision and Pattern Recognition, 2009, pp 248–255Google Scholar
  35. 35.
    Vedaldi A, Fulkerson B: An open and portable library of computer vision algorithms. Proceedings of the 18th ACM international conference on Multimedia, 2010, pp 1469–1472Google Scholar

Copyright information

© Society for Imaging Informatics in Medicine 2018

Authors and Affiliations

  • Sajib Kumar Saha
    • 1
    Email author
  • Basura Fernando
    • 2
  • Jorge Cuadros
    • 3
  • Di Xiao
    • 1
  • Yogesan Kanagasingam
    • 1
  1. 1.Australian e-Health Research Centre, CSIROPerthAustralia
  2. 2.ACRVThe Australian National UniversityCanberraAustralia
  3. 3.University of CaliforniaBerkeleyUSA

Personalised recommendations