Abstract
Glaucoma detection from fundus retinal images is a difficult task which requires years of practice and expertise in the domain. In this paper, we propose a novel method of statistical feature extraction from fundus retinal images and test its feasibility in glaucoma detection with machine learning algorithms. We combine the results of these algorithms by applying ensemble learning to create one optimized predicted output. We also apply transfer learning and compare the results obtained. The random forest model and ensemble learning model performed better than other conventional models. Using the conventional machine learning algorithms, the highest accuracy, sensitivity and AUC of 83.42%, 74.62% and 0.82, respectively, were obtained by ensemble learning, and the highest specificity of 94.74% was observed in the random forest algorithm. Using the transfer learning algorithms, the best performance was obtained with VGG19 model with AUC 0.8919 followed by GoogLeNet with an AUC of 0.8872.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Cook, C., Foster, P.: Epidemiology of glaucoma: what’s new? Can. J. Ophthalmol. 47(3), 223–226 (2012)
Weinreb, R.N., Aung, T., Medeiros, F.A.: The pathophysiology and treatment of glaucoma: a review. JAMA 311(18), 1901–1911 (2014). https://doi.org/10.1001/jama.2014.3192
Ruengkitpinyo, W., Kongprawechnon, W., Kondo, T., Bunnun, P., Kaneko, H.: Glaucoma screening using rim width based on ISNT rule. In: 6th International Conference of Information and Communication Technology for Embedded Systems (IC-ICTES) IEEE, pp. 1–5 (2015). https://doi.org/10.1109/ictemsys.2015.7110827
Dana, K.J.: Computational texture and patterns: from textons to deep learning. Synth. Lect. Comput. Vis. 8(3), 1–113 (2018)
Acharya, U.R., Bhat, S., Koh, J.E., Bhandary, S.V., Adeli, H.: A novel algorithm to detect glaucoma risk using texton and local configuration pattern features extracted from fundus images. Comput. Biol. Med. 88, 72–83 (2017)
Singh, A., Dutta, M.K., ParthaSarathi, M., Uher, V., Burget, R.: Image processing based automatic diagnosis of glaucoma using wavelet features of segmented optic disc from fundus image. Comput. Methods Programs Biomed. 124, 108–120 (2016)
Gupta, G.: Algorithm for image processing using improved median filter and comparison of mean, median and improved median filter. Int. J. Soft Comput. Eng. (IJSCE) 1(5), 304–311 (2011)
Kumar, V., Gupta, P.: Importance of statistical measures in digital image processing. Int. J. Emerg. Technol. Adv. Eng. 2(8), 56–62 (2012)
Fumero, F., Alayón, S., Sanchez, J.L., 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), pp. 1–6. IEEE (2011)
Lee, E.J., Han, J.C., Park, D.Y., & Kee, C.: A neuroglia-based interpretation of glaucomatous neuroretinal rim thinning in the optic nerve head. Prog. Retinal Eye Res. 100840 (2020). https://doi.org/10.1016/j.preteyeres.2020.100840
Wankhede, P.R., Khanchandani, K.B.: Optic disc detection using histogram based template matching. In: International Conference on Signal Processing, Communication, Power and Embedded System (SCOPES) (2016). https://doi.org/10.1109/scopes.2016.7955765
Maheshwari, S., Pachori, R.B., Acharya, U.R.: Automated diagnosis of glaucoma using empirical wavelet transform and correntropy features extracted from fundus images. IEEE J. Biomed. Health Inform. 21(3), 803–813 (2016)
Patil, P.N., Bagkavos, D., Wood, A.T.A.: A measure of asymmetry based on a new necessary and sufficient condition for symmetry. Sankhya A 76(1), 123–145 (2013). https://doi.org/10.1007/s13171-013-0034-z
Elangovan, P., Nath, M.K., Mishra, M.: Statistical parameters for glaucoma detection from color fundus images. Procedia Comput. Sci. 171, 2675–2683 (2020). https://doi.org/10.1016/j.procs.2020.04.290
Senthil Kumar, T., Helen Prabha, K.: Geometric mean filter with grayscale morphological method to enhance the RNFL thickness in the SD-OCT images. Multimedia Tools Appl. 77(8) (2018)
David, D.S., Jayachandran, A.: A new expert system based on hybrid colour and structure descriptor and machine learning algorithms for early glaucoma diagnosis. Multimedia Tools Appl. 79(7), 5213–5224 (2020)
Dey, A., Dey, K.N.: Automated glaucoma detection from fundus images of eye using statistical feature extraction methods and support vector machine classification. Ind. Interact. Innov. Sci. Eng. Technol. 511–521 (2017). https://doi.org/10.1007/978-981-10-3953-9_49
Dey, A., Bandyopadhyay, S.: Automated glaucoma detection using support vector machine classification method. J. Adv. Med. Med. Res. 11(12), 1–12 (2015). https://doi.org/10.9734/BJMMR/2016/19617
Hagiwara, Y., Koh, J.E.W., Tan, J.H., Bhandary, S.V., Laude, A., Ciaccio, E.J., Acharya, U.R.: Computer-aided diagnosis of glaucoma using fundus images: a review. Comput. Methods Progr. Biomed. 165, 1–12 (2018). https://doi.org/10.1016/j.cmpb.2018.07.012
Sagi, O., Rokach, L.: Ensemble learning: A survey. Wiley Interdisc. Rev. Data Mining Knowl. Discov. 8(4), e1249 (2018). https://doi.org/10.1002/widm.1249
Zilly, J., Buhmann, J.M., Mahapatra, D.: Glaucoma detection using entropy sampling and ensemble learning for automatic optic cup and disc segmentation. Comput. Med. Imaging Graph. 55, 28–41 (2017)
Kim, M., Zuallaert, J., De Neve, W.: Few-shot learning using a small-sized dataset of high-resolution FUNDUS images for glaucoma diagnosis. In: Proceedings of the 2nd International Workshop on Multimedia for Personal Health and Health Care. Association for Computing Machinery, New York, MMHealth, pp. 89–92 (2017)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)
Diaz-Pinto, A., Morales, S., Naranjo, V., et al.: CNNs for automatic glaucoma assessment using fundus images: an extensive validation. BioMed. Eng. OnLine 18, 29 (2019). https://doi.org/10.1186/s12938-019-0649-y
Acknowledgements
We sincerely thank N.M.S. Chaitanya, S.R. Shruthi Vidya and S. Chaitanya for their assistance in obtaining the fundus image database, preprocessing of the images.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Ravishyam, D., Samiappan, D. (2021). Comparative Study of Machine Learning with Novel Feature Extraction and Transfer Learning to Perform Detection of Glaucoma in Fundus Retinal Images. In: Sharma, T.K., Ahn, C.W., Verma, O.P., Panigrahi, B.K. (eds) Soft Computing: Theories and Applications. Advances in Intelligent Systems and Computing, vol 1381. Springer, Singapore. https://doi.org/10.1007/978-981-16-1696-9_40
Download citation
DOI: https://doi.org/10.1007/978-981-16-1696-9_40
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-1695-2
Online ISBN: 978-981-16-1696-9
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)