Towards Accurate Segmentation of Retinal Vessels and the Optic Disc in Fundoscopic Images with Generative Adversarial Networks

  • Jaemin Son
  • Sang Jun Park
  • Kyu-Hwan JungEmail author


Automatic segmentation of the retinal vasculature and the optic disc is a crucial task for accurate geometric analysis and reliable automated diagnosis. In recent years, Convolutional Neural Networks (CNN) have shown outstanding performance compared to the conventional approaches in the segmentation tasks. In this paper, we experimentally measure the performance gain for Generative Adversarial Networks (GAN) framework when applied to the segmentation tasks. We show that GAN achieves statistically significant improvement in area under the receiver operating characteristic (AU-ROC) and area under the precision and recall curve (AU-PR) on two public datasets (DRIVE, STARE) by segmenting fine vessels. Also, we found a model that surpassed the current state-of-the-art method by 0.2 − 1.0% in AU-ROC and 0.8 − 1.2% in AU-PR and 0.5 − 0.7% in dice coefficient. In contrast, significant improvements were not observed in the optic disc segmentation task on DRIONS-DB, RIM-ONE (r3) and Drishti-GS datasets in AU-ROC and AU-PR.


Retinal vessel segmentation Optic disc segmentation Convolutional neural network Generative adversarial networks 


Convolutional Neural Networks (CNN)

Generative Adversarial Networks (GAN)


Funding Information

This study was supported by the Research Grant for Intelligence Information Service Expansion Project, which is funded by National IT Industry Promotion Agency (NIPA-C0202-17-1045) and the Small Grant for Exploratory Research of the National Research Foundation of Korea (NRF), which is funded by the Ministry of Science, ICT, and Future Planning (NRF- 2015R1D1A1A02062194). The sponsors or funding organizations had no role in the design or conduct of this research.


  1. 1.
    Sarah BW, Mitchell P, Liew G, Wong TY, Phan K, Thiagalingam A, Joachim N, Burlutsky G, Gopinath B: A spectrum of retinal vasculature measures and coronary artery disease. Atherosclerosis, 2017Google Scholar
  2. 2.
    Liew G, Benitez-Aguirre P, Craig ME, Jenkins AJ, Hodgson LAB, Kifley A, Mitchell P, Wong TY, Donaghue K: Progressive retinal vasodilation in patients with type 1 diabetes: A longitudinal study of retinal vascular geometryretinal vascular geometry in type 1 diabetes. Invest Ophthalmol Vis Sci 58 (5): 2503–2509, 2017Google Scholar
  3. 3.
    Taylor AM, MacGillivray TJ, Henderson RD, Ilzina L, Dhillon B, Starr JM, Deary IJ: Retinal vascular fractal dimension, childhood iq, and cognitive ability in old age: the lothian birth cohort study 1936. Plos one 10 (3): e0121119, 2015Google Scholar
  4. 4.
    McGrory S, Taylor AM, Kirin M, Corley J, Pattie A, Cox SR, Dhillon B, Wardlaw JM, Doubal FN, Starr JM, et al: Retinal microvascular network geometry and cognitive abilities in community-dwelling older people: The lothian birth cohort 1936 study. Br J Ophthalmol, pp bjophthalmol–2016, 2016Google Scholar
  5. 5.
    McGrory S, Cameron JR, Pellegrini E, Warren C, Doubal FN, Deary IJ, Dhillon B, Wardlaw JM, Trucco E, MacGillivray TJ: The application of retinal fundus camera imaging in dementia: A systematic review. Alzheimer’s & Dementia: Diagnosis, Assessment & Disease Monitoring 6: 91–107, 2017Google Scholar
  6. 6.
    Sumukadas D, McMurdo M, Pieretti I, Ballerini L, Price R, Wilson P, Doney A, Leese G, Trucco E: Association between retinal vasculature and muscle mass in older people. Arch Gerontol Geriatr 61 (3): 425–428, 2015Google Scholar
  7. 7.
    Seidelmann SB, Claggett B, Bravo PE, Gupta A, Farhad H, Klein BE, Klein R, Di Carli MF, Solomon SD: Retinal vessel calibers in predicting long-term cardiovascular outcomes: the atherosclerosis risk in communities study. Circulation, pp CIRCULATIONAHA–116, 2016Google Scholar
  8. 8.
    McGeechan K, Liew G, Macaskill P, Irwig L, Klein R, Sharrett AR, Klein BEK, Wang JJ, Chambless LE, Wong TY: Risk prediction of coronary heart disease based on retinal vascular caliber (from the atherosclerosis risk in communities [aric] study). Am J Cardiol 102 (1): 58–63, 2008Google Scholar
  9. 9.
    Perez-Rovira A, MacGillivray T, Trucco E, Chin KS, Zutis K, Lupascu C, Tegolo D, Giachetti A, Wilson PJ, Doney A, et al: Vampire: vessel assessment and measurement platform for images of the retina.. In: Engineering in medicine and biology society, EMBC, 2011 annual international conference of the IEEE. IEEE, 2011, pp 3391–3394Google Scholar
  10. 10.
    Nguyen UTV, Bhuiyan A, Park LAF, Ramamohanarao K: An effective retinal blood vessel segmentation method using multi-scale line detection. Pattern Recog 46 (3): 703–715, 2013Google Scholar
  11. 11.
    Jiang X, Mojon D: Adaptive local thresholding by verification-based multithreshold probing with application to vessel detection in retinal images. IEEE Transactions on Pattern Analysis and Machine Intelligence 25 (1): 131–137, 2003Google Scholar
  12. 12.
    Vlachos M, Dermatas E: Multi-scale retinal vessel segmentation using line tracking. Comput Med Imaging Graph 34 (3): 213–227, 2010Google Scholar
  13. 13.
    Martinez-Perez ME, Hughes AD, Thom SA, Bharath AA, Parker KH: Segmentation of blood vessels from red-free and fluorescein retinal images. Med Image Anal 11 (1): 47–61, 2007Google Scholar
  14. 14.
    Staal J, Abràmoff MD, Niemeijer M, Viergever MA, Ginneken BV: Ridge-based vessel segmentation in color images of the retina. IEEE Trans Med Imaging 23 (4): 501–509, 2004Google Scholar
  15. 15.
    Mendonca AM, Campilho A: Segmentation of retinal blood vessels by combining the detection of centerlines and morphological reconstruction. IEEE Trans Med Imaging 25 (9): 1200–1213, 2006Google Scholar
  16. 16.
    Niemeijer M, Abràmoff MD, Ginneken BV: Fast detection of the optic disc and fovea in color fundus photographs. Med Image Anal 13 (6): 859–870, 2009Google Scholar
  17. 17.
    Sinthanayothin C, Boyce JF, Cook HL, Williamson TH: Automated localisation of the optic disc, fovea, and retinal blood vessels from digital colour fundus images. Br J Ophthalmol 83 (8): 902–910, 1999Google Scholar
  18. 18.
    Marín D, Aquino A, Gegúndez-Arias ME, Bravo JM: A new supervised method for blood vessel segmentation in retinal images by using gray-level and moment invariants-based features. IEEE Trans Med Imaging 30 (1): 146–158, 2011Google Scholar
  19. 19.
    Soares JVB, Leandro JJG, Cesar RM, Jelinek HF, Cree MJ: Retinal vessel segmentation using the 2-d gabor wavelet and supervised classification. IEEE Trans Med Imaging 25(9): 1214–1222, 2006Google Scholar
  20. 20.
    Fraz MM, Remagnino P, Hoppe A, Uyyanonvara B, Rudnicka AR, Owen CG, Barman SA: An ensemble classification-based approach applied to retinal blood vessel segmentation. IEEE Trans Biomed Eng 59(9): 2538–2548, 2012Google Scholar
  21. 21.
    Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A: Going deeper with convolutions.. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015, pp 1–9Google Scholar
  22. 22.
    He K, Zhang X, Ren S, Sun J: Deep residual learning for image recognition.. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp 770–778Google Scholar
  23. 23.
    Simonyan K, Zisserman A: Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556, 2014
  24. 24.
    Girshick R: Fast r-cnn.. In: Proceedings of the IEEE International Conference on Computer Vision, 2015, pp 1440–1448Google Scholar
  25. 25.
    Ren S, He K, Girshick R, Sun J: Faster r-cnn: Towards real-time object detection with region proposal networks.. In: Advances in neural information processing systems, 2015, pp 91–99Google Scholar
  26. 26.
    Noh H, Hong S, Han B: Learning deconvolution network for semantic segmentation.. In: Proceedings of the IEEE International Conference on Computer Vision, 2015, pp 1520–1528Google Scholar
  27. 27.
    Ronneberger O, Fischer P, Brox T: U-net: Convolutional networks for biomedical image segmentation.. In: International conference on medical image computing and computer-assisted intervention. Springer, 2015, pp 234–241Google Scholar
  28. 28.
    Long J, Shelhamer E, Darrell T: Fully convolutional networks for semantic segmentation.. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015, pp 3431– 3440Google Scholar
  29. 29.
    Maninis K-K, Pont-Tuset J, Arbeláez P, Gool LV: Deep retinal image understanding.. In: International conference on medical image computing and computer-assisted intervention. Springer, 2016, pp 140–148Google Scholar
  30. 30.
    Fu H, Xu Y, Lin S, Wong DWKW, Liu J: Deepvessel: Retinal vessel segmentation via deep learning and conditional random field.. In: International conference on medical image computing and computer-assisted intervention. Springer, 2016, pp 132– 139Google Scholar
  31. 31.
    Xie S, Tu Z: Holistically-nested edge detection.. In: Proceedings of the IEEE International Conference on Computer Vision, 2015, pp 1395–1403Google Scholar
  32. 32.
    Melinščak M, Prentašić P, Lončarić S: Retinal vessel segmentation using deep neural networks.. In: VISAPP 2015 (10Th international conference on computer vision theory and applications), 2015Google Scholar
  33. 33.
    Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A, Bengio Y: Generative adversarial nets.. In: Advances in neural information processing systems, 2014, pp 2672–2680Google Scholar
  34. 34.
    Mirza M, Osindero S: Conditional generative adversarial nets. arXiv:1411.1784, 2014
  35. 35.
    Hoover AD, Kouznetsova V, Goldbaum M: Locating blood vessels in retinal images by piecewise threshold probing of a matched filter response. IEEE Trans Med Imaging 19 (3): 203–210, 2000Google Scholar
  36. 36.
    Carmona EJ, Rincón M, García-feijoó J, Martínez-de-la Casa JM: Identification of the optic nerve head with genetic algorithms. Artif Intell Med 43 (3): 243–259, 2008Google Scholar
  37. 37.
    Fumero F, Alayón S, Sanchez JL, Sigut J, Gonzalez-Hernandez M: Rim-one: An open retinal image database for optic nerve evaluation.. In: 2011 24th international symposium on Computer-based medical systems (CBMS). IEEE, 2011, pp 1–6Google Scholar
  38. 38.
    Sivaswamy J, Krishnadas S, Joshi G, Jain M, Tabish AUS: Drishti-gs: Retinal image dataset for optic nerve head(onh) segmentation, 04 2014Google Scholar
  39. 39.
    Radford A, Metz L, Chintala S: Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv:1511.06434, 2015
  40. 40.
    Ganin Y, Victor L: N 4-fields: Neural network nearest neighbor fields for image transforms.. In: Asian conference on computer vision. Springer, 2014, pp 536–551Google Scholar
  41. 41.
    Becker C, Rigamonti R, Lepetit V, Fua P: Supervised feature learning for curvilinear structure segmentation.. In: International conference on medical image computing and computer-assisted intervention. Springer, 2013, pp 526–533Google Scholar
  42. 42.
    Orlando JI, Blaschko M: Learning fully-connected crfs for blood vessel segmentation in retinal images.. In: International conference on medical image computing and computer-assisted intervention. Springer, 2014, pp 634–641Google Scholar
  43. 43.
    Otsu N: A threshold selection method from gray-level histograms. IEEE Trans Syst Man Cybern 9 (1): 62–66, 1979Google Scholar
  44. 44.
    Orlando JI, Prokofyeva E, Blaschko MB: A discriminatively trained fully connected conditional random field model for blood vessel segmentation in fundus images. IEEE Trans Biomed Eng 64 (1): 16–27, 2017.
  45. 45.
    Sakata K, Funatsu H, Harino S, Noma H, Hori S: Relationship of macular microcirculation and retinal thickness with visual acuity in diabetic macular edema. Ophthalmology 114 (11): 2061–2069, 2007Google Scholar
  46. 46.
    Prentašić P, Heisler M, Mammo Z, Lee S, Merkur A, Navajas E, Beg MF, Šarunić M, Lončarić S: Segmentation of the foveal microvasculature using deep learning networks. J Biomed Op 21 (7): 075008–075008, 2016Google Scholar
  47. 47.
    Zhang Z, Liu J, Cherian NS, Sun Y, Lim JH, Wong WK, Tan NM, Lu S, Li H, Wong TY: Convex hull based neuro-retinal optic cup ellipse optimization in glaucoma diagnosis.. In: Annual international conference of the IEEE Engineering in medicine and biology society, 2009. EMBC 2009. IEEE, 2009, pp 1441– 1444Google Scholar
  48. 48.
    Nair V, Hinton GE: Rectified linear units improve restricted boltzmann machines.. In: Proceedings of the 27th international conference on machine learning (ICML-10), 2010, pp 807– 814Google Scholar
  49. 49.
    Ioffe S, Szegedy C: Batch Accelerating deep network training by reducing internal covariate shift.. In: 32nd international conference on international conference on machine learning, volume 37 of ICML’15, 2015, pp 448–456. JMLR.orgGoogle Scholar
  50. 50.
    Isola P, Zhu J-Y, Zhou T, Efros AA: Image-to-image translation with conditional adversarial networks.. In: The IEEE conference on computer vision and pattern recognition (CVPR), 2017Google Scholar
  51. 51.
    Kingma D, Ba J: Adam: A method for stochastic optimization.. In: Proceedings of the International Conference on Learning Representations (ICLR), 2015Google Scholar

Copyright information

© Society for Imaging Informatics in Medicine 2018

Authors and Affiliations

  1. 1.VUNO Inc.SeoulRepublic of Korea
  2. 2.Department of Ophthalmology, Seoul National University College of MedicineSeoul National University Bundang HospitalSeongnamRepublic of Korea

Personalised recommendations