Automated segmentation of optic disc and optic cup for glaucoma assessment using improved UNET++ architecture

• Autorzy: Tulsani Akshat , Kumar Preetham , Pathan Sumaiya

Identyfikatory

DOI

10.1016/j.bbe.2021.05.011

• Języki publikacji: EN

Abstrakty

EN

Glaucoma is one of the leading cause of blindness for over 60 million people around the world. Since a cure for glaucoma doesn’t yet exist, early screening and diagnosis become critical for the prevention of the disease. Optic disc and optic cup evaluation are one of the preeminent steps for glaucoma diagnosis. A novel approach is developed in this paper for the identification of glaucoma using a segmentation based approach on the optic disc and optic cup. The Dhristi dataset was used to help improve performance on a small dataset. A custom UNET++ model is built for the segmentation task by tuning the hyperparameters in addition to a custom loss function. The developed loss function helps tackle the class imbalance occurring due to small size of the optic nerve head. The proposed approach achieves 96% accuracy in classifying glaucomatous and non-glaucomatous images based on clinical feature identification. The improvised model is able to achieve state-of-art results for Intersection over Union (IOU) scores, 0.9477 for optic disc and 0.9321 for optic cup, along with providing an enhancement in reducing the training time. The model was tested on publicly available datasets RIM-ONE, DRIONS-DB and ORIGA and is able to achieve an accuracy of 91%, 92% and 90% respectively. The developed approach is validated by training it over RIM-ONE dataset independently, without changing any model parameters. The model provides significant improvement in segmentation of the optic disc and optic cup along with improvement in training time.

Słowa kluczowe

EN

fundus image; glaucoma diagnosis; optic disc; optic cup; automated segmentation; UNET++

PL

obraz dna oka; diagnoza jaskry; dysk optyczny; segmentacja automatyczna; UNET++

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2021
• Tom: Vol. 41, no. 2
• Strony: 819--832
• Opis fizyczny: Bibliogr. 90 poz., rys., tab.

Twórcy

autor

Tulsani Akshat

• Department of Information and Communication Technology, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, Karnataka, India

autor

Kumar Preetham

• Manipal Academy of Higher Education, Department of Information and Communication Technology, Manipal Institute of Technology, Manipal, Karnataka, India

autor

Pathan Sumaiya

• Department of Information and Communication Technology, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, Karnataka, India

Bibliografia

• [1] Weinreb RN, Aung T, Medeiros FA. The pathophysiology and treatment of glaucoma: a review. JAMA 2014;311(18):1901–11.
• [2] Tham Y-C et al. Global prevalence of glaucoma and projections of glaucoma burden through 2040: a systematic review and meta-analysis. Ophthalmology 2014;121 (11):2081–90.
• [3] Wisaeng K, Hiransakolwong N, Pothiruk E. Automatic detection of optic disc in digital retinal images. Int J Comput Appl 2014;90(5):15–20.
• [4] Noronha KP, Acharya UR, Nayak KP, Martis RJ, Bhandary SV. Automated classification of glaucoma stages using higher order cumulant features. Biomed Signal Process Control 2014;10:174–83.
• [5] Acharya UR, Ng EYK, Eugene LWJ, Noronha KP, Min LC, Nayak KP, et al. Decision support system for the glaucoma using Gabor transformation. Biomed Signal Process Control 2015;15:18–26.
• [6] Haleem MS, Han L, Hemert JV, et al. Regional image features model for automatic classification between normal and glaucoma in fundus and scanning laser ophthalmoscopy (SLO) images. J Med Systems 2016;40(132).
• [7] Diaz-Pinto, A., Morales, S., Naranjo, V., Köhler, T., Mossi, J. and Navea, A., CNNs for automatic glaucoma assessment using fundus images: an extensive validation. BioMed Eng OnLine 18, 2019.
• [8] Carneiro, Gustavo, Jacinto Nascimento, Andrew P. Bradley. Unregistered multiview mammogram analysis with pretrained deep learning models, International Conference on Medical Image Computing and Computer-Assisted Intervention, Springer, Cham, pp. 652-660, 2015.
• [9] Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, et al. Going deeper with convolutions. In: IEEE conference on computer vision and pattern recognition (CVPR). p. 1–9.
• [10] Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z. Rethinking the inception architecture for computer vision. In: IEEE conference on computer vision and pattern recognition (CVPR). p. 2818–26.
• [11] He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: IEEE conference on computer vision and pattern recognition (CVPR). p. 770–8.
• [12] Chollet F. Xception: Deep learning with depthwise separable convolutions. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR). p. 1800–7.
• [13] Raghavendra U, Fujita H, Bhandary SV, Gudigar A, Tan JH, Acharya UR. Deep convolution neural network for accurate diagnosis of glaucoma using digital fundus images. Inf Sci 2018;441:41–9.
• [14] Yuki Hagiwara, Joel En Wei Koh, Jen Hong Tan, Sulatha V. Bhandary, Augustinus Laude, Edward J. Ciaccio, Louis Tong, U. Rajendra Acharya, Computer-aided diagnosis of glaucoma using fundus images: A review, Computer Methods Programs Biomed, 165, pp. 1-12, 2018.
• [15] Soltani A, Battikh T, Jabri I, Lakhoua N. A new expert system based on fuzzy logic and image processing algorithms for early glaucoma diagnosis. Biomed Signal Process Control 2018;40:366–77.
• [16] Soorya M, Issac A, Dutta MK. An automated and robust image processing algorithm for glaucoma diagnosis from fundus images using novel blood vessel tracking and bend point detection. Int J Med Inf 2018;110:52–70.
• [17] Nergiz M, Akın M, Yıldız A, Takes Ömer. Automated fuzzy optic disc detection algorithm using branching of vessels and color properties in fundus images. Biocybernetics Biomed Eng 2018;38(4).
• [18] HaleemMS, Han L, Hemert JV, et al. A novel adaptive deformable model for automated optic disc and cup segmentation to aid glaucoma diagnosis. J Med Syst 2018;42(20).
• [19] Kausu TR, Gopi VP, Wahid KA, Doma W, Niwas SI. Combination of clinical and multiresolution features for glaucoma detection and its classification using fundus images. Biocybernetics Biomed Eng 2018;38(2):329–41.
• [20] 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.
• [21] Raghavendra U, Bhandary SV, Gudigar A, Rajendra Acharya U. Novel expert system for glaucoma identification using nonparametric spatial envelope energy spectrum with fundus images. Biocyber Biomed Eng 2018;38(1):170–80.
• [22] Gómez-Valverde JJ, Antón A, Fatti G, Liefers B, Herranz A, Santos A, et al. Automatic glaucoma classification using color fundus images based on convolutional neural networks and transfer learning. Biomed Opt Express 2019;10(2):892–913.
• [23] Guangzhou An, Kazuko Omodaka, Kazuki Hashimoto, Satoru Tsuda, Yukihiro Shiga, Naoko Takada, et al., Glaucoma diagnosis with machine learning based on optical coherence tomography and color fundus images, J Healthcare Eng, vol. 2019, Article ID 4061313, 9 pages, 2019.
• [24] Lee J, Kim YK, Park KH, Jeoung JW. Diagnosing glaucoma with spectral-domain optical coherence tomography using deep learning classifier. J Glaucoma 2020;29(4):287–94.
• [25] Raja H, Hassan T, Akram MU, Werghi N. Clinically verified hybrid deep learning system for retinal ganglion cells aware grading of glaucomatous progression. IEEE Trans Biomed Eng 2020.
• [26] Hina Raja, M. Usman Akram, Sajid Gul Khawaja, Muhammad Arslan, Aneeqa Ramzan, Noman Nazir, Data on OCT and fundus images for the detection of glaucoma, Data in Brief, vol. 29, 2020.
• [27] Asaoka R, Murata H, Hirasawa K, Fujino Y, Matsuura M, Miki A, et al. Using deep learning and transfer learning to accurately diagnose early-onset glaucoma from macular optical coherence tomography images. Am J Ophthalmol 2019;198:136–45.
• [28] Alice C. Verticchio Vercellin, Firas Jassim, Linda Yi-Chieh Poon, Edem Tsikata, Boy Braaf, Sneha Shah, et al., Diagnostic capability of three-dimensional macular parameters for glaucoma using optical coherence tomography volume scans, Invest Ophthalmol Vis Sci., 2018.
• [29] Greg Russell, Silvia N. W. Hertzberg, Natalia Anisimova, Natalia Gavrilova, Beáta É., Petrovski, Goran Petrovski, Digital image analysis of the angle and optic nerve: a simple, fast, and low-cost method for glaucoma assessment, J Ophthalmol, 2020, Article ID 3595610, 8 pages, 2020.
• [30] Muramatsu C., Diagnosis of glaucoma on retinal fundus images using deep learning: detection of nerve fiber layer defect and optic disc analysis, Deep Learning in Medical Image Analysis. Advances in Experimental Medicine and Biology, vol. 1213, Springer, 2020.
• [31] Sevastopolsky A. Optic disc and cup segmentation methods for glaucoma detection with modification of U-Net convolutional neural network. Pattern Recognit Image Anal 2017;27(3):618–24.
• [32] Ronneberger O, Fischer P, Brox T, U-net: Convolutional networks for biomedical image segmentation, Medical Image Computing and Computer-Assisted Intervention (MICCAI), Springer, pp 234–241. Springer, 2015.
• [33] Fu H, Cheng J, Xu Y, Zhang C, Wong DWK, Liu J, et al. Discaware ensemble network for glaucoma screening from fundus image. IEEE Trans Med Imag 2018;37(11):2493–501.
• [34] Bajwa MN, Malik MI, Siddiqui SA, Dengel A, Shafait F, Neumeier W, Ahmed S., Two-stage framework for optic disc localization and glaucoma classification in retinal fundus images using deep learning. BMC Med Inform Decis Mak, 19 (136), 2019.
• [35] Fu H, Cheng J, Xu Y, Wong DWK, Liu J, Cao XC. Joint optic disc and cup segmentation based on multi-label deep network and polar transformation. IEEE Trans Med Imaging 2018;37 (7):1597–605.
• [36] Orlando JI et al. REFUGE challenge: a unified framework for evaluating automated methods for glaucoma assessment from fundus photographs. Med Image Anal 2020;59.
• [37] Li F, Yan L, Wang Y, Shi J, Chen H, Zhang X, et al. Deep learning-based automated Detection of glaucomatous optic neuropathy on color fundus photographs. Graefe’s Arch Clin Exp Ophthalmol 2020;258(4):851–67.
• [38] Al Ghamdi M, Li M, Abdel-Mottaleb M, Shousha MA. Semisupervised transfer learning for convolutional neural networks for glaucoma detection. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). p. 3812–6.
• [39] Pathan S, Kumar P, Pai R, Bhandary SV. Automated detection of optic disc contours in fundus images using decision tree classifier. Biocyber Biomed Eng 2020;40(1):52–64.
• [40] Jiang Y, Tan N, Peng T. Optic disc and cup segmentation based on deep convolutional generative adversarial networks. IEEE Access 2019;7:64483–93.
• [41] Gheisari S, Shariflou S, Phu J. et al., A combined convolutional and recurrent neural network for enhanced glaucoma detection. Scientific Rep, vol. 11, 2021.
• [42] Bisneto TRV, de Carvalho Filho AO, Magalhães DMV. Generative adversarial network and texture features applied to automatic glaucoma detection. Appl Soft Comput 2020;90.
• [43] Tekouabou Koumetio SC, Abdellaoui Alaoui EA, Chabbar I, Cherif W, Silkan H. Using deep features extraction and ensemble classifiers to detect glaucoma from fundus images. Emerging Trends in ICT for Sustainable Development. Advances in Science, Technology & Innovation (IEREK Interdisciplinary Series for Sustainable Development). Springer; 2021.
• [44] Deng J, Dong W, Socher R, Li LJ, Li K, Fei-Fei L. Imagenet: a large-scale hierarchical image database. In: IEEE Conference on Computer Vision and Pattern Recognition. IEEE; 2009. p. 248–55.
• [45] Gour N, Khanna P. Automated glaucoma detection using GIST and pyramid histogram of oriented gradients (PHOG) descriptors. Pattern Recogn Lett 2020;137:3–11.
• [46] Wang S, Yu L, Li K, Yang X, Fu C, Heng P. Boundary and entropy-driven adversarial learning for fundus image segmentation. In: Medical Image Computing and Computer Assisted Intervention – p. 102–10.
• [47] Li L, Xu M, Liu H, Li Y, Wang X, Jiang L, et al. A large-scale database and a CNN model for attention-based glaucoma detection. IEEE Trans Med Imaging 2020;39(2):413–24.
• [48] Shah S, Kasukurthi N, Pande H. Dynamic region proposal networks for semantic segmentation in automated glaucoma screening. In: 16th IEEE International Symposium on Biomedical Imaging. p. 578–82.
• [49] Pruthi J, Khanna K, Arora S. Optic Cup segmentation from retinal fundus images using Glowworm Swarm Optimization for glaucoma detection. Biomed Signal Process Control 2020;60:102004. https://doi.org/10.1016/j.bspc.2020.102004.
• [50] Sumaiya Pathan, Preetham Kumar, Radhika M. Pai, Sulatha V. Bhandary, Automated segmentation and classifcation of retinal features for glaucoma diagnosis, Biomed Signal Process Control, 63, 2021.
• [51] Gao Y, Yu X, Wu C, Zhou W, Wang X, Zhuang Y. Accurate optic disc and cup segmentation from retinal images using a multi-feature based approach for glaucoma assessment, Symmetry., 11(10), 2019.
• [52] Wang L, Gu J, Chen Y, Liang Y, Zhang W, Pu J, et al. Automated segmentation of the optic disc from fundus images using an asymmetric deep learning network. Pattern Recogn 2021;112.
• [53] Jiang Y, Wang F, Gao J, Cao S. Multi-path recurrent U-Net segmentation of retinal fundus image. Appl. Sci.., 10(11), 2020.
• [54] Jin B, Liu P, Wang P, Shi L, Zhao J. Optic disc segmentation using attention-based U-Net and the improved cross-entropy convolutional neural network. Entropy 2020;22(8).
• [55] Decencière E, Zhang X, Cazuguel G, Lay B, Cochener Béatrice, Trone C, et al. Feedback on a publicly distributed image database: The Messidor database. Image Anal Stereol 2014;33 (3):231. https://doi.org/10.5566/ias.1155.
• [56] Singh LK, Pooja, Garg H, Khanna M, Bhadoria RS. An enhanced deep image model for glaucoma diagnosis using feature-based detection in retinal fundus. Med Biol Eng Compu 2021;59(2):333–53.
• [57] Shruti Jadon, A survey of loss functions for semantic Segmentation, IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB), pp. 1-7, 2020.
• [58] Zhou Z, Siddiquee MMR, Tajbakhsh N, Liang J. Unet++: Redesigning skip connections to exploit multiscale features in image segmentation. IEEE Trans Med Imaging 2019;39:1856–67.
• [59] J. Sivaswamy S.R. Krishnadas G. Datt Joshi M. Jain A.U. Syed Tabish Drishti-gs: Retinal image dataset for optic nerve head (onh) segmentation IEEE 11th International Symposium on Biomedical Imaging (ISBI). IEEE 2014 53 56.
• [60] Zhang Z, Yin FS, Liu J, Wong WK, Tan NM, Lee BH, Cheng J, Wong TY., Origa-light: An online retinal fundus image database for glaucoma analysis and research., IEEE Engineering in Medicine and Biology Society. Annual International Conference, pp. 3065–3068, 2010.
• [61] Fumero, Francisco et al, Interactive tool and database for optic disc and cup segmentation of stereo and monocular retinal fundus images, 23rd International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision, IEEE, 2015.
• [62] Carmona EJ, Rincón M, García-Feijó J, Martínez-de-la-Casa José M. Identification of the optic nerve head with genetic algorithms. Artificial Intel Med, Elsevier 2008;43(3):243–59.
• [63] Prenzel BjörnG, Treitz P. Spectral and spatial filtering for enhanced thematic change analysis of remotely sensed data. Int J Remote Sens 2006;27(5):835–54.
• [64] Orhan AE, Pitkow X. Skip connections eliminate singularities. Proceedings of 2018 Machine Learning Research, Stockholm, Sweden, 2018.
• [65] Gao Huang, Zhuang Liu, Laurens van der Maaten, Kilian Q. Weinberger, Densely Connected Convolutional Networks, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2261-2269, 2017.
• [66] Lee C-Y, Xie S, Gallagher P, Zhang Z, Tu Z. Deeply-supervised nets. Artificial Intel Statistics 2015;38:562–70.
• [67] Ma Yi-de, Liu Qing, Qian Zhi-bai, Automated image segmentation using improved PCNN model based on crossentropy, International Symposium on Intelligent Multimedia, Video and Speech Processing, pp. 743–746, IEEE, 2004.
• [68] Gu Z, Cheng J, Fu H, Zhou K, Hao H, Zhao Y, et al. CE-Net: context encoder network for 2D medical image segmentation. IEEE Trans Med Imaging 2019;38(10):2281–92.
• [69] Harizman N, Oliveira C, Chiang A, Tello C, Marmor M, Ritch R, et al. The ISNT rule and differentiation of normal from glaucomatous eyes. Arch Ophthalmol 2006;124(11):1579–883.
• [70] Chaumette F. Image moments: a general and useful set of features for visual servoing. IEEE Trans Rob 2004;20(4):713–23.
• [71] Zilly J.G, Buhmann JM, Mahapatra D, Boosting convolutional filters with entropy sampling for optic cup and disc image segmentation from fundus images., International Workshop on Machine Learning in Medical Imaging, pp. 136–143, Springer, 2015.
• [72] Zilly J, Buhmann JM, Mahapatra D. Glaucoma detection using entropy sampling and ensemble learning for automatic optic cup and disc segmentation. Comput Med Imaging Graph 2017;55:28–41.
• [73] Juneja M, Singh S, Agarwal N, Bali S, Gupta S, Thakur N, et al. Automated detection of glaucoma using deep learning convolution network (G-net). Multimedia Tools Applications 2020;79:15531–53.
• [74] Edupuganti V.G., Chawla A., Kale A., Automatic optic disk and cup segmentation of fundus images using deep learning, IEEE International Conference on Image Processing, IEEE, pp. 2227-2231, 2018.
• [75] Zhou W, Wu C, Gao Y, Yu X, Automatic optic disc boundary extraction based on saliency object detection and modified local intensity clustering model in retinal images, IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences, vol. E100.A, no. 9, pp. 2069–2072, 2017.
• [76] Cheng J, Liu J, Xu Y, Yin F, Wong DWK, Tan N-M, et al. Superpixel classification based optic disc and optic cup segmentation for glaucoma screening. IEEE Trans Med Imaging 2013;32(6):1019–32.
• [77] Mittapalli PS, Kande GB. Segmentation of optic disk and optic cup from digital fundus images for the assessment of glaucoma. Biomed Signal Process Control 2016;24(47):34–46.
• [78] Wei Zhou, Yugen Yi, Yuan Gao, Jiangyan Dai, Optic disc and cup segmentation in retinal images for glaucoma diagnosis by locally statistical active contour model with structure prior, Computational and Mathematical Methods in Medicine, vol. 2019, Article ID 8973287, 16 pages, 2019.
• [79] Shankaranarayana SM, Ram K, Mitra K, Sivaprakasam M. Fully convolutional networks for monocular retinal depth estimation and optic disc-cup segmentation. IEEE J Biomed Health Informatics 2019;23(4):1417–26.
• [80] Maninis, Kevis-Kokitsi, Pont-Tuset, Jordi, Arbelaez, Pablo, Van Gool, Luc, Deep Retinal Image Understanding, Medical Image Computing and Computer-Assisted Intervention – MICCAI, 2016.
• [81] Koh JEW, Acharya UR, Hagiwara Y, Raghavendra U, Tan JH, Sree SV, et al. Diagnosis of retinal health in digital fundus images using continuous wavelet transform (CWT) and entropies. Comput Biol Med 2017;84:89–97.
• [82] Nugroho HA, Oktoeberza KZW, Adji TB, Najamuddin F. Detection of exudates on color fundus images using texturebased feature extraction. Int J Technol 2015;6(2):121–9.
• [83] Guo F, Li W, Tang J, et al. Automated glaucoma screening method based on image segmentation and feature extraction. Med Biol Eng Compu 2020;58(10):2567–86.
• [84] Fatima Bokhari ST, Sharif M, Yasmin M, Fernandes SL. Fundus image segmentation and feature extraction for the detection of glaucoma: A new approach. Curr Med Imaging 2017;14(1):77–87.
• [85] Perdomo O, Andrearczyk V, Meriaudeau F, Muller H, González FA. Glaucoma diagnosis from eye fundus images based on deep morphometric feature estimation. In: Computational Pathology and Ophthalmic Medical Image Analysis. p. 319–27.
• [86] Lotankar M, Noronha K, Koti J, et al. Detection of optic disc and cup from color retinal images for automated diagnosis of glaucoma. In: Proceedings of IEEE UP Section Conference on Electrical Computer and Electronics. p. 1–6.
• [87] Issac A, Sarathi MP, Dutta MK, et al. An adaptive threshold based image processing technique for improved glaucoma detection and classification. Comput Methods Programs Biomed 2015;122(2):229–44.
• [88] Al Ghamdi M, Semi-supervised transfer learning for convolutional neural networks for glaucoma detection IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 3812-3816, 2019.
• [89] Sarkar D, Das S et al, ‘‘Automated glaucoma detection of medical image using biogeography based optimization.” Advances in Optical Science and Engineering. Springer Proceedings in Physics, vol. 194, pp. 381–388, 2017.
• [90] Abbas Q. Glaucoma-deep: detection of glaucoma eye disease on retinal fundus images using deep learning. Int J Adv Comput Sci Appl 2017;8:41–5.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2021).