Abstract
Purpose
Optic disc (OD, hereafter) detection is often the first step to detect other retinal landmarks for analysis of conditions such as glaucoma and diabetic retinopathy. It is often not possible to localize the OD based on colour/pixel information alone, especially for poor-contrast and low-resolution images. Community camp-based images under poor lighting conditions and hand-held ophthalmoscopes also induces imaging artefacts.
Methods
The paper proposes an automatic OD detection method using a U-Net-based regression, with a distance-intensity map. The regression network uses Tukey’s biweight loss function to make it robust to outliers, and improve the overall rate of convergence. The method localizes OD coordinates using a Generalized Laplacian-of-Gaussian (gLoG) operator on the predicted distance-intensity map. The system shows encouraging experimental results on poor resolution images with non-uniform illumination, noise, motion, blurring, and various imaging artefacts.
Results
The experiments with intra- and inter-dataset performance (training and testing on different datasets) are with the following datasets: Messidor, Kaggle, DRIVE, DRIONS, STARE, and Drishti-GS. The method shows excellent qualitative and quantitative results on Messidor and the challenging AIIMS Community Camp dataset, as well. The achieved detection accuracy is of 99.67% and 98.83%, respectively.
Conclusion
The U-Net-based regressor with the novel loss function is geared towards getting good optic disc detection performance across a large number of datasets. The network shows robust detection performance on challenging images with various retinal artifacts (blurring, poor illumination, and clinical pathologies).
Similar content being viewed by others
References
Al-Bander B, Al-Nuaimy W, Williams BM, Zheng Y. Multiscale sequential convolutional neural networks for simultaneous detection of fovea and optic disc. Biomed Signal Process Control. 2018;40:91–101.
Avinash Ramakanth S, Venkatesh Babu R. Approximate nearest neighbour nield based optic disk detection. Comput Med Imaging Graph. 2014;38(1):49–56.
Belagiannis V, Rupprecht C, Carneiro G, Navab N. Robust optimization for deep regression. In: Proc. IEEE International Conference on Computer Vision (ICCV), 2015. p. 2830–2838.
Calimeri F, Marzullo A, Stamile C, Terracina G. Optic disc detection using fine tuned convolutional neural networks. In: Proc. International conference on signal-image technology & internet-based systems, 2016. p. 69–75.
Czarnowski I, Jedrzejowicz P. An approach to data reduction for learning from big datasets: integrating stacking, rotation, and agent population learning techniques. Complexity 2018:1–13.
Dada T, Coote M. Clinical evaluation of optic nerve head. International Society of Glaucoma Surgery. 2010.
Dietter J, Haq W, Ivanov IV, Norrenberg LA, Völker M, Dynowski M, Röck D, Ziemssen F, Leitritz MA, Ueffing M. Optic disc detection in the presence of strong technical artifacts. Biomed Signal Process Control. 2019;53:1–11.
Foracchia M, Grisan E, Ruggeri A. Detection of optic disc in retinal images by means of a geometrical model of vessel structure. IEEE Trans Med Imaging. 2004;23:1189–95.
Fu Y, Chen J, Li J, Pan D, Yue X, Zhu Y. Optic disc segmentation by u-net and probability bubble in abnormal fundus images. Pattern Recognit. 2021;117: 107971.
Huang Y, Zhong Z, Yuan J, Tang X. Efficient and robust optic disc detection and fovea localization using region proposal network and cascaded network. Biomed Signal Process Control. 2020;60:1–10.
Isola P, Zhu JY, Zhou T, Efros AA. Image-to-image translation with conditional adversarial networks. ar**v:1611.07004.
Jana S, Parekh R, Sarkar B. A semi-supervised approach for automatic detection and segmentation of optic disc from retinal fundus image. In: Nayak J, Naik B, Pelusi D, Das AK, editors. Handbook of computational intelligence in biomedical engineering and healthcare. Academic Press; p. 65–91.
Kaggle diabetic retinopathy detection competition. 2015;https://www.kaggle.com/c/diabetic-retinopathy-detection/data, Accessed: 20 July, 2015.
Karras T, Laine S, Aila T. A style-based generator architecture for generative adversarial networks. ar**v:1812.04948.
Kong H, Akakin HC, Sarma SE. A generalized laplacian of gaussian filter for blob detection and its applications. IEEE Trans Cybern. 2013;43(6):1719–33.
Lalonde M, Beaulieu M, Gagnon L. Fast and robust optic disc detection using pyramidal decomposition and Hausdorff-based template matching. IEEE Trans Med Imaging. 2001;20(11):1193–200.
Latif J, Tu S, **ao C, Rehman SU, Imran A, Latif Y. Odgnet: a deep learning model for automated optic disc localization and glaucoma classification using fundus images. SN Appl Sci. 2022;4:98.
Liang M, Zhang Y, Wang H, Li J. Location of optic disk in the fundus image based on visual attention. In: Proc. International Conference on Computer Information and Big Data Applications (CIBDA). p. 446–449.
Lu S. Accurate and efficient optic disc detection and segmentation by a circular transformation. IEEE Trans Med Imaging. 2011;30:2126–33.
Maninis KK, Pont-Tuset J. Retinal databases. http://www.vision.ee.ethz.ch/~cvlsegmentation/driu/downloads.html.
Mendonça AM, Sousa A, Mendonça L, Campilho A. Automatic localization of the optic disc by combining vascular and intensity information. Comput Med Imaging Graph. 2013;37(5–6):409–17.
Messidor Retinal Database. 2016.http://www.adcis.net/en/third-party/messidor/, Accessed: 24 September, 2016.
Meyer MI, Galdran A, Medonça AM, Campilho A. A pixel-wise distance regression approach for joint retinal optical disc and fovea detection. In: Proc. Medical Image Computing and Computer-Assisted Intervention (MICCAI). p. 39–47.
Mitra A, Banerjee PS, Roy S, Roy S, Setua SK. The region of interest localization for glaucoma analysis from retinal fundus image using deep learning. Comput Methods Programs Biomed. 2018;165:25–35.
Nawaz M, Nazir T, Javed A, Tariq U, Yong HS, Khan MA, Cha J. An efficient deep learning approach to automatic glaucoma detection using optic disc and optic cup localization. Sensors. 2022;22(2):434.
Nergiz M, Akin M, Yildiz A, Ömer Takeç. Automated fuzzy optic disc detection algorithm using branching of vessels and color properties in fundus images. Biocybern Biomed Eng. 2018;38(4):850–867.
Niemeijer M, Abràmoff MD, van Ginneken B. Fast detection of the optic disc and fovea in color fundus photographs. Med Image Anal. 2009;13(6):859–70.
Niu D, Xu P, Wan C, Cheng J, Liu J. Automatic localization of optic disc based on deep learning in fundus images. In: Proc. International Conference on Signal and Image Processing. 2017 p. 208–212.
Panda R, Puhan NB, Panda G. Robust and accurate optic disk localization using vessel symmetry line measure in fundus images. Biocybern Biomed Eng. 2017;37(3):466–76.
Pathan S, Kumar P, Pai R, Bhandary S. Automated detection of optic disc contours in fundus images using decision tree classifier. Biocybern Biomed Eng. 2019;40:1–13.
Pathan S, Kumar P, Pai RM, Bhandary SV. Automated segmentation and classifcation of retinal features for glaucoma diagnosis. Biomed Signal Process Control. 2021;63:1–19.
Ronneberger O, Fischer P, Brox T. U-Net: convolutional networks for biomedical image segmentation. In: Proc. Medical Image Computing and Computer-Assisted Intervention (MICCAI), vol 9351. 2015, p. 234–241.
Serte S, Serener A. Graph-based Saliency and ensembles of convolutional neural networks for glaucoma detection. IET Image Process. 2021;15:1–8.
Sharma A, Agrawal M, Lall B. Optic disc detection using vessel characteristics and disc features. In: Proc. National Conference on Communications (NCC). 2017, p. 1–6.
Shukla AK, Pandey RK, Pachori RB. A fractional filter based efficient algorithm for retinal blood vessel segmentation. Biomed Signal Process Control. 2020;59:1–16.
Sivaswamy J, Krishnadas SR, Joshi GD, Jain M, Ujjwal, Syed-Tabish A. Drishti-GS: retinal image dataset for optic nerve head (ONH) segmentation. In: Proc. IEEE International Symposium on Biomedical Imaging (ISBI). 2014
Soares I, Castelo-Branco M, Pinheiro AM. Optic disc localization in retinal images based on cumulative sum fields. IEEE J Biomed Health Inform. 2016;20:574–85.
Subha V, Rayen S. A novel visual saliency thresholding method for accurate ROI segmentation in optic disc from FEIs for glaucoma detection. Int J Comput Digital Syst. 2022;11:477–89.
Trucco E, MacGillivray T, Xu Y. Computational retinal image analysis: tools, applications and perspectives. Mara Conner. 2019.
Tulsani A, Kumar P, Pathan S. Automated segmentation of optic disc and optic cup for glaucoma assessment using improved unet++ architecture. Biocybern Biomed Eng. 2021;41(2):819–32.
Wankhede PR, Khanchandani KB. Optic disc detection using template matching based on color plane histograms. In: Proc. International Conference on Global Trends in Signal Processing, Information Computing and Communication (ICGTSPICC). p. 278–281.
Wei Z, Hao W, Chengdong W, **aosheng Y, Yugen Y. Automatic optic disc detection in color retinal images by local feature spectrum analysis. 2018.
**ong L, Li H. An approach to locate optic disc in retinal images with pathological changes. Comput Med Imaging Graph. 2016;47:40–50.
Yu H, Barriga ES, Agurto C, Echegaray S, Pattichis MS, Bauman W, Soliz P. Fast localization and segmentation of optic disk in retinal images using directional matched filtering and level sets. IEEE Trans Inf Technol Biomed. 2012;16(4):644–57.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare no competing interests.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Sharma, A., Agrawal, M., Dutta Roy, S. et al. A comprehensive study of optic disc detection in artefact retinal images using a deep regression neural network for a fused distance-intensity map. Res. Biomed. Eng. 39, 639–653 (2023). https://doi.org/10.1007/s42600-023-00294-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s42600-023-00294-8