Advertisement

Early Detection of Proliferative Diabetic Retinopathy in Neovascularization at the Disc by Observing Retinal Vascular Structure

  • Nilanjana Dutta RoyEmail author
  • Arindam Biswas
Conference paper
Part of the Lecture Notes in Computational Vision and Biomechanics book series (LNCVB, volume 30)

Abstract

Proliferative Diabetic Retinopathy (PDR) is the advanced stage of Diabetic Retinopathy (DR) with high risk of severe visual impairment. Neovascularization is a common scenario at this stage where abnormal vessels proliferate. This paper describes a semi-automated method for early detection of PDR around few diameters of Optic Disc (OD) in retinal images. Center of OD detection from segmented images is essentially important here because the approach focuses on Neovascularization at the Disc (NVD). Around OD center on few pixel distance window boundary, the width of major vessels are measured and counted. Finally, the major vessels are identified by distinct colors. The sensitivity and specificity results on STARE dataset of 25 images are 0.86 and 0.87, respectively. The approach shows the average accuracy as 0.88.

Keywords

Proliferative diabetic retinopathy Neovascularization Early detection Center of optic disc Width Major vessels 

References

  1. 1.
    Akram MU, Khalid S, Tariq A, Javed MY (2013) Detection of neovascularization in retinal images using multivariate m-mediods based classifier. Comput Med Imaging Graph 37(5):346–357CrossRefGoogle Scholar
  2. 2.
    Oloumi F, Rangayyan RM, Ells AL (2012) Computer-aided diagnosis of proliferative diabetic retinopathy. International conference of the IEEE engineering in medicine and biology society (EMBC) 2012:1438–1441Google Scholar
  3. 3.
    Hassan SSA, Bong DB, Premsenthil M (2012) Detection of neovascularization in diabetic retinopathy. J Digit Imaging 25(3):437–444CrossRefGoogle Scholar
  4. 4.
    Srivastava R, Wong DW, Duan L, Liu J, Wong TY (2015) Red lesion detection in retinal fundus images using frangi-based filters. In: IEEE engineering in medicine and biology society (EMBC), pp 5663–5666Google Scholar
  5. 5.
    The DRIVE database, Image sciences institute, university medical center Utrecht, The Netherlands. http://www.isi.uu.nl/Research/Databases/DRIVE/. Last accessed on 7th July 2007
  6. 6.
    Gonzalez RC, Eugene Woods R Digital image processing book, 3rd edn. Paperback PublishersGoogle Scholar
  7. 7.
    Dutta Roy N, Someswar M, Dalmia H, Biswas A (2014) Identification of distinct nerves in retinal fundus images. compImage’14, P.A. Pittsburgh, USAGoogle Scholar
  8. 8.
    Boyd J (1996) STARE software documentation: diskOptic disk locator. Vis Comput Lab Dept Elect Comput Eng Univ CaliforniaGoogle Scholar
  9. 9.
    Agurto C, Honggang Y, Murray V, Pattichis MS, Barriga S, Bauman W et al (2012) Detection of neovascularization in the optic disc using an AMFM representation, granulometry, and vessel segmentation. In: Annual international conference of the IEEE, engineering in medicine and biology society (EMBC), 2012, pp 4946–4949Google Scholar
  10. 10.
    Goatman KA, Fleming AD, Philip S, Williams GJ, Olson JA, Sharp PF (2011) Detection of new vessels on the optic discusing retinal photographs. IEEE Trans Med Imaging 30:972CrossRefGoogle Scholar
  11. 11.
    Jelinek HF, Cree MJ, Leandro JJ, Soares JV, Cesar RM Jr, Luckie A (2007) Automated segmentation of retinal blood vessels and identification of proliferative diabetic retinopathy. J Opt Soc Am Opt Image Sci Vis 24:1448–1456CrossRefGoogle Scholar
  12. 12.
    Welikala R, Dehmeshki J et al (2014) Automated detection of proliferative diabetic retinopathy using a modified line operator and dual classification. Comput Methods Programs Biomed 114(3):247261CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Department of Computer Science and EngineeringInstitute of Engineering and ManagementKolkataIndia
  2. 2.Department of Information TechnologyIndian Institute of Engineering Science and TechnologyShibpur, HowrahIndia

Personalised recommendations