Skip to main content
SpringerLink
Log in

Two-stage framework for optic disc segmentation and estimation of cup-to-disc ratio using deep learning technique

  • Original Research
  • Published:
Journal of Ambient Intelligence and Humanized Computing Aims and scope Submit manuscript

Abstract

The accurate segmentation of retinal anatomies and pathology is a crucial task to diagnose and evaluate various metabolic and ophthalmic disorders such as diabetes, hypertension, glaucoma and other common diseases. The optic disc (OD) segmentation in fundus photography is the preliminary and essential activity for diagnosing retinal disorders. The conventional supervised methods follow multiple stages which consume more time and also the accuracy found to be deprived in majority of the cases. The potentiality of deep learning techniques, especially the fully convolutional neural architecture is adopted in this paper to perform OD segmentation in the initial stage and at a later stage image processing algorithms are used to estimate the cup-to-disc ratio. Using an optimal set of image processing operations the ground truth images were generated from the hand-labeled fundus images. The proposed U-Net architecture consisting of encoder and decoder blocks to capture the spatial information and to precise localization of OD respectively. The model performance was estimated in terms of Accuracy and Intersection over Union (IoU) indices. The proposed method attained an accuracy level of 99.7% and IoU of 87.9% which is superior when compared to the contemporary methods in literature.

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
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14

Similar content being viewed by others

Availability of data and materials

The datasets were collected from six different sources: BinRushed and Magrabia: https://deepblue.lib.umich.edu/data/concern/data_sets/3b591905z. MESSIDOR: http://www.adcis.net/en/third-party/messidor/. DRIONS-DB: http://www.ia.uned.es/~ejcarmona/DRIONS-DB/BD/DRIONS-DB.rar. RIM-ONE: http://medimrg.webs.ull.es/research/downloads/. IDRiD: https://ieee-dataport.org/open-access/indian-diabetic-retinopathy-image-dataset-idrid.

References

  • Ahmed A, Sami A, Essameldin O, Eslam R, Mohammed H, Mohammed D, Muhannad A, Kaamran R, Vasudevan L (2018) Retinal fundus images for glaucoma analysis: the RIGA dataset. In: Proceedings of SPIE 10579, medical imaging 2018: imaging informatics for healthcare, research, and applications, 105790B. https://doi.org/10.1117/12.2293584

  • Araújo T, Aresta G, Galdran A, Costa P, Mendonça AM, Campilho A (2018) UOLO—automatic object detection and segmentation in biomedical images. arXiv:abs/1810.05729.

  • Bourne RRA, Flaxman SR, Braithwaite T, Cicinelli MV, Das A, Jonas JB et al (2017) Vision Loss Expert Group. Magnitude, temporal trends, and projections of the global prevalence of blindness and distance and near vision impairment: a systematic review and meta-analysis. Lancet Glob Health 5(9):e888–e897. https://doi.org/10.1016/S2214-109X(17)30293-0 (ISSN 2214-109X)

  • Calimeri F, Marzullo A, Stamile C, Terracina G (2016) Optic disc detection using fine tuned convolutional neural networks. In: 12th international conference on signal-image technology & internet-based systems (SITIS), Naples, pp 69–75. https://doi.org/10.1109/SITIS.2016.20

  • Carmona EJ, Rincón M, García-Feijoó J, Martínez-de-la-Casa JM (2008) Identification of the optic nerve head with genetic algorithms. Artif Intell Med 43(3):243–259. https://doi.org/10.1016/j.artmed.2008.04.005 (Epub 2008 Jun 4 PMID: 18534830)

    Article  Google Scholar 

  • Decencière E, Zhang X, Cazuguel G, Lay B, Trone C, Gain P, Ordonez R, Massin P, Erginay A, Charton B, Klein J-C (2014) Feedback on a publicly distributed image database: the Messidor database. Image Anal Stereol. https://doi.org/10.5566/ias.1155

    Article  MATH  Google Scholar 

  • Fumero F, Alayon S, Sanchez JL, Sigut J, Gonzalez-Hernandez M (2011) RIM-ONE: an open retinal image database for optic nerve evaluation. In: 24th international symposium on computer-based medical systems (CBMS), Bristol, 2011, pp 1–6.https://doi.org/10.1109/CBMS.2011.5999143

  • Gu Z, Jiang S, Lee J, Xie J, Cheng J, Liu J (2018) Automatic localization of optic disc using modified U-Net. In: Proceedings of the 2018 international conference on control and computer vision (ICCCV '18). Association for Computing Machinery, New York, NY, USA, 79–83. https://doi.org/10.1145/3232651.3232671

  • He K, Zhang X, Ren S, Sun J (2015) Delving deep into rectifiers: surpassing human-level performance on ImageNet classification. In: IEEE international conference on computer vision (ICCV 2015). p 1502. https://doi.org/10.1109/ICCV.2015.123

  • International Symposium on BIOMEDICAL IMAGING: From Nano to Macro (2015). https://biomedicalimaging.org/2015/program/isbi-challenges/. Accessed 10 May 2018

  • Li A, Niu Z, Cheng J, Yin F, Wong DW, Yan S, Liu J (2018) Learning supervised descent directions for optic disc segmentation. Neurocomputing 275:350–357. https://doi.org/10.1016/j.neucom.2017.08.033

    Article  Google Scholar 

  • Mitra A, Priya Shankar B, Sudipta R, Somasis R, Sanjit Kumar S (2018) The region of interest localization for glaucoma analysis from retinal fundus image using deep learning. Comput Methods Progr Biomed 165:25–35. https://doi.org/10.1016/j.cmpb.2018.08.003 (ISSN 0169-2607)

    Article  Google Scholar 

  • Mohan D, Kumar JR, Seelamantula CS (2018) High-performance optic disc segmentation using convolutional neural networks. In: 2018 25th IEEE international conference on image processing (ICIP), pp 4038–4042

  • Mohan D, Harish Kumar JR, Sekhar Seelamantula C (2019) Optic disc segmentation using cascaded multiresolution convolutional neural networks. In: IEEE international conference on image processing (ICIP), Taipei, Taiwan, 2019, pp 834–838. https://doi.org/10.1109/ICIP.2019.8804267

  • Niu D, Xu P, Wan C, Cheng J, Liu J (2017) Automatic localization of optic disc based on deep learning in fundus images. In: IEEE 2nd international conference on signal and image processing (ICSIP), Singapore, 2017, pp 208–212. https://doi.org/10.1109/SIPROCESS.2017.8124534

  • Prasanna P, Samiksha P, Ravi K, Manesh K, Girish D, Vivek S, Fabrice M (2018) Indian diabetic retinopathy image dataset (IDRiD). IEEE Dataport. https://doi.org/10.21227/H25W98

  • Ronneberger O, Fischer P, Brox T (2015) U-Net: convolutional networks for biomedical image segmentation. arXiv:abs/1505.04597

  • Sadhukhan S, Ghorai GK, Maiti S, Sarkar G, Dhara AK (2018) Optic disc localization in retinal fundus images using faster R-CNN. In: 2018 fifth international conference on emerging applications of information technology (EAIT), Kolkata, pp 1–4. https://doi.org/10.1109/EAIT.2018.8470435

  • Saha O, Sathish R, Sheet D (2019) Learning with multitask adversaries using weakly labelled data for semantic segmentation in retinal images. MIDL

  • Singh VK, Rashwan HA, Akram F, Pandey N, Sarker MM, Saleh A, Abdulwahab S, Maaroof N, Torrents-Barrena J, Romani S, Puig D (2018) Retinal optic disc segmentation using conditional generative adversarial network. CCIA

  • Son J, Park SJ, Jung K-H (2018) Towards accurate segmentation of retinal vessels and the optic disc in fundoscopic images with generative adversarial networks. J Digit Imaging. https://doi.org/10.1007/s10278-018-0126-3

    Article  Google Scholar 

  • Sudheer Kumar E, Shoba Bindu C (2019) Medical image analysis using deep learning: a systematic literature review. In: Emerging technologies in computer engineering: microservices in big data analytics. Communications in computer and information science, vol 985. Springer, pp 81–97. https://doi.org/10.1007/978-981-13-8300-7_8

  • Sun X, Xu Y, Zhao W, You T, Liu J (2018) Optic disc segmentation from retinal fundus images via deep object detection networks. In: 40th annual international conference of the IEEE engineering in medicine and biology society (EMBC), Honolulu, HI, pp 5954–5957. https://doi.org/10.1109/EMBC.2018.8513592

  • Wang L, Liu H, Lu Y, Chen H, Zhang J, Pu J (2019) A coarse-to-fine deep learning framework for optic disc segmentation in fundus images. Biomed Signal Process Control 51:82–89. https://doi.org/10.1016/J.BSPC.2019.01.022

    Article  Google Scholar 

Download references

Funding

Not applicable.

Author information

Authors and Affiliations

  1. Department of CSE, JNTUA, Ananthapuramu, Andhra Pradesh, 515002, India

    E. Sudheer Kumar & C. Shoba Bindu

Authors
  1. E. Sudheer Kumar
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. C. Shoba Bindu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to E. Sudheer Kumar.

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

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Kumar, E.S., Bindu, C.S. Two-stage framework for optic disc segmentation and estimation of cup-to-disc ratio using deep learning technique. J Ambient Intell Human Comput (2021). https://doi.org/10.1007/s12652-021-02977-5

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s12652-021-02977-5

Keywords

Search

Navigation