Abstract
Retinal image analysis has opened up a new window for prompt diagnosis and detection of various retinal disorders. Optical Coherence Tomography (OCT) is one of the major diagnostic tools to identify retinal abnormalities related to macular disorders like Age-Related Macular Degeneration (AMD) and Diabetic Macular Edema (DME). The clinical findings include retinal layer analysis to spot the abnormalities on OCT images. Though various models are proposed over the years to diagnose these disorders automatically, an end-to-end system that performs automatic denoising, segmentation, and classification does not exist to the best of our knowledge. This paper proposes a Generative Adversarial Network (GAN) based approach for automated segmentation and classification of OCT-B scans to diagnose AMD and DME. The proposed method incorporates the integration of handcrafted Gabor features to enhance the retina layer segmentation and non-local denoising to remove speckle noise. The classification metrics of GAN are compared with existing methods. The accuracy of up to 92.42% and F1-score of 0.79 indicates that the GANs can perform well for segmentation and classification of OCT images.
Similar content being viewed by others
Notes
The loss function used in a multi-class classification problem when the classes are mutually exclusive and are represented using integers.
f(x) = max(x,0), where x is input
f(x) = \(\frac {2}{1+e^{-2x}}\)
References
Alqudah AM (2020) Aoct-net: A convolutional network automated classification of multiclass retinal diseases using spectral-domain optical coherence tomography images. Med Biol Eng Comput 58:41–53. https://doi.org/10.1007/s11517-019-02066-y
Arjovsky M, Chintala S, Bottou L (2017) Wasserstein GAN. arXiv e-prints arXiv:1701.07875. https://ui.adsabs.harvard.edu/abs/2017arXiv170107875A
Balaji B, Jidesh P (2017) Non-local gradient fidelity model for multiplicative gamma noise removal. In: 2017 Ninth international conference on advances in pattern recognition (ICAPR). https://doi.org/10.1109/ICAPR.2017.8593110, pp 1–6
Bandello F, Lattanzio R, Zucchiatti I, Arrigo A, Battista M, Cicinelli M V (2019) Diabetic macular edema: A step-by-step guide for ophthalmologists. Springer Nature, Switzerland, pp 97–183
Birch DG, Liang FQ (2007) Age-related macular degeneration: A target for nanotechnology derived medicines. Int J Nanomedicine 2(1):65–77. https://doi.org/10.2147/nano.2007.2.1.65
Brownlee J (2019) Generative adversarial networks with python:deep learning generative models for image synthesis and image translation. v1.5 edn. Machine Learning Mastery. https://books.google.co.in/books?id=YBimDwAAQBAJ
Chiu SJ, Li XT, Nicholas P, Toth CA, Izatt JA, Farsiu S (2010) Automatic segmentation of seven retinal layers in sdoct images congruent with expert manual segmentation. Opt Express 18(18):19413–19428. https://doi.org/10.1364/OE.18.019413.
Dai Z, Yang Z, Yang F, Cohen W W, Salakhutdinov R (2017) Good semi-supervised learning that requires a bad GAN. CoRR arXiv:abs/1705.09783
Das V, Dandapat S, Bora PK (2020) A data-efficient approach for automated classification of oct images using generative adversarial network. IEEE Sensors Letters 4(1):1–4. https://doi.org/10.1109/LSENS.2019.2963712
Dodo B I, Li Y, Kaba D, Liu X (2019) Retinal layer segmentation in optical coherence tomography images. IEEE Access 7:152388–152398. https://doi.org/10.1109/ACCESS.2019.2947761
Febin I P, Jidesh P, Bini A A (2018) Noise classification and automatic restoration system using non-local regularization frameworks. Imaging Sci J 66(8):479–491. https://doi.org/10.1080/13682199.2018.1518760
Froment J (2014) Parameter-free fast pixelwise non-local means denoising. Image Process 4:300–326. https://doi.org/10.5201/ipol.2014.120
Fuglede B, Topsoe F (2004) Jensen-shannon divergence and hilbert space embedding. In: International symposium on information theory, 2004. ISIT 2004. Proceedings, p 31
Garcia-Layana, Ciuffo A, Gianfranco, et al. (2017) Optical coherence tomography in age-related macular degeneration. https://amdbook.org/content/optical-coherence-tomography-age-related-macular-degenerationhttps://amdbook.org/content/optical-coherence-tomography-age-related-macular-degeneration. Accessed:20-01-2021
Girish G N, Thakur B, Chowdhury S R, Kothari A R, Rajan J (2019) Segmentation of intra-retinal cysts from optical coherence tomography images using a fully convolutional neural network model. IEEE J Biomed Health Inform 23 (1):296–304. https://doi.org/10.1109/JBHI.2018.2810379
Glen S (2014) P-value in statistical hypothesis tests: What is it?”. https://www.statisticshowto.com/p-value/. Accessed:20-01-2021
Grandini M, Bagli E, Visani G (2020) Metrics for multi-class classification: An overview. arXiv:2008.05756. Accessed: 23-June-2021
Gulrajani I, Ahmed F, Arjovsky M, Dumoulin V, Courville A (2017) Improved training of wasserstein gans. In: Proceedings of the 31st international conference on neural information processing systems, NIPS’17. https://doi.org/10.5555/3295222.3295327. Curran Associates Inc., Red Hook, NY, USA, pp 5769–5779
He K, Zhang X, Ren S, Sun J (2015) Deep residual learning for image recognition. CoRR arXiv:1512.033851512.03385
Huang G, Liu Z, Weinberger K Q (2016) Densely connected convolutional networks. CoRR arXiv:abs/1608.06993
Huang L, He X, Fang L, Rabbani H, Chen X (2019) Automatic classification of retinal optical coherence tomography images with layer guided convolutional neural network. IEEE Signal Process Lett 26(7):1026–1030. https://doi.org/10.1109/LSP.2019.2917779
Jidesh P, Banothu B (2018) Image despeckling with non-local total bounded variation regularization. Comput Electr Eng 70:631–646. https://doi.org/10.1016/j.compeleceng.2017.09.013. http://www.sciencedirect.com/science/article/pii/S0045790617307619
Kermany D, Zhang K, Goldbaum M (2018) Labeled optical coherence tomography (oct) and chest x-ray images for classification. Mendeley Data, v2. https://doi.org/10.17632/rscbjbr9sj.2, https://www.kaggle.com/paultimothymooney/kermany2018
Li J, Jin P, Zhu J, Zou H, Xu X, Tang M, Zhou M, Gan Y, He J, Ling Y, Su Y (2021) Multi-scale gcn-assisted two-stage network for joint segmentation of retinal layers and discs in peripapillary oct images. Biomed Opt Express 12(4):2204–2220. https://doi.org/10.1364/BOE.417212. http://www.osapublishing.org/boe/abstract.cfm?URI=boe-12-4-2204
Li X, Shen L, Shen M, Qiu C S (2019) Integrating handcrafted and deep features for optical coherence tomography based retinal disease classification. IEEE Access 7:33771–33777. https://doi.org/10.1109/ACCESS.2019.2891975
Li QL et al (2020) Deepretina: Layer segmentation of retina in oct images using deep learning. Transl Vision Sci Technol 9(2):61. https://doi.org/10.1167/tvst.9.2.61
Ma Y, Gao Y, Li Z, Li A, Wang Y, Liu J, Yu Y, Shi W, Ma Z (2021) Automated retinal layer segmentation on optical coherence tomography image by combination of structure interpolation and lateral mean filtering. J Innov Opt Health Sci 14(01):2140011. https://doi.org/10.1142/S1793545821400113
Minitab (2020) Goodness of fit for individual distribution identification. https://support.minitab.com/en-us/minitab/19/help-and-how-to/quality-and-process-improvement/quality-tools/how-to/individual-distribution-identification/interpret-the-results/all-statistics-and-graphs/goodness-of-fit/. Accessed:20-01-2021
Mishra Z et al (2020) Automated retinal layer segmentation using graph-based algorithm incorporating deep-learning-derived information. Scientific Reports 10:9541. https://doi.org/10.1038/s41598-020-66355-5
Mittal A, Moorthy A K, Bovik A C (2012) No-reference image quality assessment in the spatial domain. IEEE Trans Image Process 21 (12):4695–4708. https://doi.org/10.1109/TIP.2012.2214050
Moreira Neto C A, Rebhun C (2018) 1 - normal optical coherence tomography. In: Goldman D R, Waheed N K, Duker J S (eds) Atlas of Retinal OCT: Optical Coherence Tomography. http://www.sciencedirect.com/science/article/pii/B9780323461214000017. Elsevier, pp 1–15
Negi A, Chauhan P, Kumar K, Rajput RS (2020) Face mask detection classifier and model pruning with keras-surgeon. In: 2020 5th IEEE international conference on recent advances and innovations in engineering (ICRAIE), pp 1–6
Paul D, Tewari A, Ghosh S, Santosh K C (2020) Octx: Ensembled deep learning model to detect retinal disorders. In: 2020 IEEE 33rd international symposium on computer-based medical systems (CBMS). IEEE, pp 526–531
Popescu DP, Choo-Smith LP et al (2011) Optical coherence tomography: Fundamental principles, instrumental designs and biomedical applications. Biophys Rev 3 (3):155. https://doi.org/10.1007/s12551-011-0054-7
Rasti R, Rabbani H, Mehridehnavi A, Hajizadeh F (2018) Macular oct classification using a multi-scale convolutional neural network ensemble. IEEE Trans Med Imaging 37(4):1024–1034. https://doi.org/10.1109/TMI.2017.2780115
Roy A G, Conjeti S, Karri S P K, Sheet D, Katouzian A, Wachinger C, Navab N (2017) Relaynet: Retinal layer and fluid segmentation of macular optical coherence tomography using fully convolutional networks. Biomed Opt Express 8(8):3627–3642. https://doi.org/10.1364/BOE.8.003627. http://www.osapublishing.org/boe/abstract.cfm?URI=boe-8-8-3627
Salimans T, Goodfellow I, Zaremba W, Cheung V, Radford A, Chen X (2016) Improved techniques for training gans. In: Proceedings of the 30th international conference on neural information processing systems. NIPS’16. https://doi.org/10.5555/3157096.3157346. Curran Associates Inc., Red Hook, NY, USA, pp 2234–2242
Schmitt J M, Xiang SH, Yung KM (1999) Speckle in optical coherence tomography. Journal of Biomedical Optics 4(1):95–105. https://doi.org/10.1117/1.429925
Sedai S, Antony B, Rai R, Jones K, Ishikawa H, Schuman J, Gadi W, Garnavi R (2019) Uncertainty guided semi-supervised segmentation of retinal layers in oct images. In: Shen D, Liu T, Peters T M, Staib L H, Essert C, Zhou S, Yap P-T, Khan A (eds) Medical image computing and computer assisted intervention – MICCAI 2019. Springer International Publishing, Cham, pp 282–290
Serener A, Serte S (2019) Dry and wet age-related macular degeneration classification using oct images and deep learning. In: 2019 scientific meeting on electrical-electronics biomedical engineering and computer science (EBBT), pp 1–4
Sharma S, Shivhare S N, Singh N, Kumar K (2019) Computationally efficient ann model for small-scale problems. In: Tanveer M, Pachori R B (eds) Machine intelligence and signal analysis. Springer Singapore, Singapore, pp 423–435
Sudeep PV, Issac Niwas S, Palanisamy P, Rajan J, Xiaojun Y, Wang X, Luo Y, Liu L (2016) Enhancement and bias removal of optical coherence tomography images: An iterative approach with adaptive bilateral filtering. Comput Biol Med 71:97–107. https://doi.org/10.1016/j.compbiomed.2016.02.003. http://www.sciencedirect.com/science/article/pii/S0010482516300300
Sudeep PV, Palanisamy P, Rajan J, Baradaran H, Saba L, Gupta A, Suri J S (2016) Speckle reduction in medical ultrasound images using an unbiased non-local means method. Biomed Sig Process 28:1–8. https://doi.org/10.1016/j.bspc.2016.03.001. http://www.sciencedirect.com/science/article/pii/S1746809416300222
Sunija AP, Saikat K, Gayathri S, Varun P G, Palanisamy P (2021) Octnet: A lightweight cnn for retinal disease classification from optical coherence tomography images. Comput Methods Prog Biomed 200:105877. https://doi.org/10.1016/j.cmpb.2020.105877. https://www.sciencedirect.com/science/article/pii/S0169260720317107
Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z (2015) Rethinking the inception architecture for computer vision. CoRR arXiv:1512.00567
Teng P-y (2013) Caserel - an open source software for computer-aided segmentation of retinal layers in optical coherence tomography images. Zenodo, Public repository. https://doi.org/10.5281/zenodo.17893
Van Hulle M, Sladojevic S, Arsenovic M, Anderla A, Culibrk D, Stefanovic D (2016) Deep neural networks based recognition of plant diseases by leaf image classification. Computational Intelligence and Neuroscience. https://doi.org/10.1155/2016/3289801
Waheed N K (2018) 15.1 - diabetic macular edema. Elsevier Goldman D R, Waheed N K, Duker J S (eds). http://www.sciencedirect.com/science/article/pii/B9780323461214000376
Wang D, Wang L (2019) On oct image classification via deep learning. IEEE Photon J 11(5):1–14. https://doi.org/10.1109/JPHOT.2019.2934484
Weldon T P, Higgins W E, Dunn D F (1996) Efficient gabor filter design for texture segmentation. Pattern Recogn 29(12):2005–2015. https://doi.org/10.1016/S0031-3203(96)00047-7
Xuehua W, Xiangcong X, Yaguang Z, Dingan H (2021) A new method with seu-net model for automatic segmentation of retinal layers in optical coherence tomography images. In: 2021 IEEE 2nd international conference on big data, artificial intelligence and internet of things engineering (ICBAIE), pp 260–263
Yanagihara R T, Lee C S, Ting D S W, Lee A Y (2020) Methodological challenges of deep learning in optical coherence tomography for retinal diseases: a review. Transl Vision Sci Technol 9(2):11–11. https://doi.org/10.1167/tvst.9.2.11
Acknowledgements
A. Smitha would like to acknowledge Prof. Vasudevan Lakshminarayanan, University of Waterloo, Canada, and Dr. J. Jothi Balaji, Medical Research Foundation, India, for their valuable suggestions regarding the research work. Smitha express her gratitude to the Ministry of Education, Government of India, for providing financial support (as fellowship) for carrying out the research at National Institute of Technology Karnataka, Surathkal. She also acknowledges the contribution of Mr. Abhinaba Hazarika, Master student at NITK, for assisting in the implementation and documentation of the proposed work. Dr. P. Jidesh thanks the Department of Atomic Energy, Govt. of India, for providing financial support under the research grant no. 02011/17/2020NBHM(RP)/R&DII/8073.
Author information
Authors and Affiliations
Corresponding author
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.
Appendix
Appendix
Consider a multi-category classification problem. The classification metrics of such a problem is elaborately explained in [17]. Let ‘C’ denote the number of classes. A classification matrix provides the mapping of expected outcome and the predicted outcome. Accordingly, we define the following terms from a multi-class confusion matrix.
-
TP - True Positive
-
TN - True Negative
-
FP - False Positive
-
NP - False Negative
Ideally, in classification problems related to the medical field, the number of true positives and true negatives have to be maximum, while the number of false positives, and false negatives have to be minimum. This implies that the sensitivity and specificity values must be close to 1 (100%). Sensitivity denotes the proportion of positives that are correctly identified, while specificity corresponds to the proportion of negatives that are correctly identified. Accuracy represents the precision of the classifier, or the ability to identify the positive and negative proportion precisely. A higher accuracy implies a better classifier. The precision, recall, and the F1-scores together signifies the ability of the classifier to accurately identify the true positives. A higher value of these indicates that the classifier performance is better.
Rights and permissions
About this article
Cite this article
Smitha, A., Jidesh, P. Detection of retinal disorders from OCT images using generative adversarial networks. Multimed Tools Appl 81, 29609–29631 (2022). https://doi.org/10.1007/s11042-022-12475-1
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-022-12475-1