Abstract
Glaucoma damages the optical nerve, which sends visual pictures to the brain, and results in irreversible vision loss. This chronic infection is the second leading cause of permanent blindness across the world and worsens the purpose of life if not cured at an early stage. Traditional ways of diagnosing glaucoma, however, rely on heavy equipment and highly trained personnel, making it impossible to assess huge populations of individuals. This results in high costs and lengthy wait times. As a result, new methods for diagnosing glaucoma that do not exacerbate these problems need to be investigated. Previously, to detect glaucoma through artificial intelligence, features were extracted manually, which not only consumes a lot of time but is also a tedious task to perform and there is a chance of intra-observer variability. Now, deep learning (DL) techniques can be used to extract features automatically, which was not possible in the traditional methods. In view of the multiple associated problems like limited labeled data, difficulty and cost incurred in building glaucoma fundus photographic datasets, and special hardware requirements, this study assessed the performance of a DL model (s) which are trained in detecting glaucoma from fundus pictures and methods. The objective is to present a versatile DL model which should generate auspicious performance across multiple datasets to meet real-life scenarios instead of generating specific dataset performance and, along with it, take care of these coupled problems. Diverse deep learning techniques are investigated in this empirical study to categorise the fundus images into two classes: normal and glaucomatous. On all these models, fine-tuning with transfer learning is also performed. Three different publicly available benchmark datasets (ACRIMA, ORIGA, and HRF) were used for training and validation. The models were tested not only on DRISHTI-GS (a public dataset) and a private dataset but also on twelve combinations of these five datasets. Extensive experiments are conducted to manifest the effectiveness of the proposed approach, and on the basis of Area under Curve values and computed accuracy values, it is concluded that Inception-ResNet-v2 and Xception models outperform other competitive models. The findings show the potential of this technology in the early identification of glaucoma. This automated diagnosis system has great potential to ultimately reduce the human efforts and precious time of ophthalmologists.
Similar content being viewed by others
References
Abbas Q (2017) Glaucoma-deep: detection of glaucoma eye disease on retinal fundus images using deep learning. Int J Adv Comput Sci Appl 8(6):41–45
Ahn JM, Kim S, Ahn KS, Cho SH, Lee KB, Kim US (2018) A deep learning model for the detection of both advanced and early glaucoma using fundus photography. PLoS ONE 13(11):e0207982
Al-Bander B, Al-Nuaimy W, Al-Taee MA, Zheng Y (2017) Automated glaucoma diagnosis using a deep learning approach. In: 2017 14th international multi-conference on systems, signals & devices (SSD) (pp 207–210), IEEE
Alghamdi HS, Tang HL, Waheeb SA, Peto T (2016) Automatic optic disc abnormality detection in fundus images: a deep learning approach. OMIA 2016:11–16
An G, Omodaka K, Hashimoto K, Tsuda S, Shiga Y, Takada N, Nakazawa T (2019) Glaucoma diagnosis with machine learning based on optical coherence tomography and color fundus images. J Healthcare Eng 2019:1
Angelov PP, Gu X (2018) Deep rule-based classifier with human-level performance and characteristics. Inf Sci 463:196–213
Angelov PP, Gu X (2019) Empirical approach to machine learning. Springer, Cham
Angelov P, Gu X, Kangin D (2017) Empirical data analytics. Int J Intell Syst 32(12):1261–1284
Bajwa MN, Malik MI, Siddiqui SA, Dengel A, Shafait F, Neumeier W, Ahmed S (2019) Two-stage framework for optic disc localization and glaucoma classification in retinal fundus images using deep learning. BMC Med Inform Decis Mak 19(1):1–16
Bhatkalkar B, Joshi A, Prabhu S, Bhandary S (2020) Automated fundus image quality assessment and segmentation of optic disc using convolutional neural networks. Int J Electr Comput Eng 2088–8708:10
Bhuiyan A, Govindaiah A, Smith RT (2021) An artificial-intelligence-and telemedicine-based screening tool to identify glaucoma suspects from color fundus imaging. J Ophthalmol 2021:5
Chakravarty A, Sivaswamy J (2016) Glaucoma classification with a fusion of segmentation and image-based features. In: 2016 IEEE 13th international symposium on biomedical imaging (ISBI) (pp 689–692), IEEE
Chen X, Xu Y, Wong DWK, Wong TY, Liu J (2015) Glaucoma detection based on deep convolutional neural network. In: 2015 37th annual international conference of the IEEE engineering in medicine and biology society (EMBC) (pp 715–718), IEEE
Chollet F (2017) Xception: Deep learning with depthwise separable convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition (pp 1251–1258)
Choudhary P, Hazra A (2021) Chest disease radiography in twofold: using convolutional neural networks and transfer learning. Evol Syst 12(2):567–579
Christopher M, Belghith A, Bowd C, Proudfoot JA, Goldbaum MH, Weinreb RN, Zangwill LM et al (2018) Performance of deep learning architectures and transfer learning for detecting glaucomatous optic neuropathy in fundus photographs. Sci Rep 8(1):16685
Claro M, Veras R, Santana A, Araújo F, Silva R, Almeida J, Leite D (2019) An hybrid feature space from texture information and transfer learning for glaucoma classification. J vis Commun Image Represent 64:102597
Devecioglu OC, Malik J, Ince T, Kiranyaz S, Atalay E, Gabbouj M (2021) Real-time glaucoma detection from digital fundus images using Self-ONNs. IEEE Access 2021:5
Diaz-Pinto A, Morales S, Naranjo V, Köhler T, Mossi JM, Navea A (2019) CNNs for automatic glaucoma assessment using fundus images: an extensive validation. Biomed Eng Online 18(1):29
dos Santos Ferreira MV, de CarvalhoFilho AO, de Sousa AD, Silva AC, Gattass M (2018) Convolutional neural network and texture descriptor-based automatic detection and diagnosis of glaucoma. Expert Syst Appl 110:250–263
Elangovan P, Nath MK (2021) Glaucoma assessment from color fundus images using convolutional neural network. Int J Imaging Syst Technol 31(2):955–971
Fu H, Cheng J, Xu Y, Zhang C, Wong DWK, Liu J, Cao X (2018) Disc-aware ensemble network for glaucoma screening from fundus image. IEEE Trans Med Imaging 37(11):2493–2501
Fu H, Cheng J, Xu Y, Liu J (2019) Glaucoma detection based on deep learning network in fundus image. In: Deep learning and convolutional neural networks for medical imaging and clinical informatics (pp 119–137). Springer, Cham
Gao Y, Yu X, Wu C, Zhou W, Lei X, Zhuang Y (2019) Automatic optic disc segmentation based on modified local image fitting model with shape prior information. J Healthcare Eng 2019:5
Geetha Ramani R, Balasubramanian L (2016) Retinal blood vessel segmentation employing image processing and data mining techniques for computerized retinal image analysis. Biocybern Biomed Eng 36(1):102–118
Gherghout Y, Tlili Y, Souici L (2021) Classification of breast mass in mammography using anisotropic diffusion filter by selecting and aggregating morphological and textural features. Evol Syst 12(2):273–302
Gómez-Valverde JJ, Antón A, Fatti G, Liefers B, Herranz A, Santos A, Ledesma-Carbayo MJ et al (2019) Automatic glaucoma classification using color fundus images based on convolutional neural networks and transfer learning. Biomed Opt Express 10(2):892–913
Guo F, Mai Y, Zhao X, Duan X, Fan Z, Zou B, Xie B (2018) Yanbao: a mobile app using the measurement of clinical parameters for glaucoma screening. IEEE Access 6:77414–77428
Guo F, Li W, Tang J, Zou B, Fan Z (2020) Automated glaucoma screening method based on image segmentation and feature extraction. Med Biol Eng Comput 58(10):2567–2586
Gupta P, Malhotra P, Narwariya J, Vig L, Shroff G (2020) Transfer learning for clinical time series analysis using deep neural networks. J Healthcare Inf Res 4(2):112–137
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition (pp 770–778)
Hemelings R, Elen B, Barbosa-Breda J, Lemmens S, Meire M, Pourjavan S, Stalmans I et al (2020) Accurate prediction of glaucoma from colour fundus images with a convolutional neural network that relies on active and transfer learning. Acta Ophthalmol 98(1):e94–e100
Huang G, Liu Z, Van Der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition (pp 4700–4708)
Jiang Z, Yepez J, An S, Ko S (2017) Fast, accurate and robust retinal vessel segmentation system. Biocybern Biomed Eng 37(3):412–421
Kanse SS, Yadav DM (2020) HG-SVNN: harmonic genetic-based support vector neural network classifier for the glaucoma detection. J Mech Med Biol 20(01):1950065
Kaur J, Mittal D (2017) A generalized method for the detection of vascular structure in pathological retinal images. Biocybern Biomed Eng 37(1):184–200
Kausu TR, Gopi VP, Wahid KA, Doma W, Niwas SI (2018) Combination of clinical and multiresolution features for glaucoma detection and its classification using fundus images. Biocybern Biomed Eng 38(2):329–341
Khanna M, Agarwal A, Singh LK, Thawkar S, Khanna A, Gupta D (2021) Radiologist-level two novel and robust automated computer-aided prediction models for early detection of COVID-19 infection from chest X-ray images. Arab J Sci Eng 2021:1–33
Khojasteh P, Júnior LAP, Carvalho T, Rezende E, Aliahmad B, Papa JP, Kumar DK (2019) Exudate detection in fundus images using deeply-learnable features. Comput Biol Med 104:62–69
Kumar JH, Seelamantula CS, Kamath YS, Jampala R (2019) Rim-to-disc ratio outperforms cup-to-disc ratio for glaucoma prescreening. Sci Rep 9(1):1–9
Lee J, Kim YK, Park KH, Jeoung JW (2020) Diagnosing glaucoma with spectral-domain optical coherence tomography using deep learning classifier. J Glaucoma 29(4):287–294
Li Z, He Y, Keel S, Meng W, Chang RT, He M (2018) Efficacy of a deep learning system for detecting glaucomatous optic neuropathy based on color fundus photographs. Ophthalmology 125(8):1199–1206
Li L, Xu M, Liu H, Li Y, Wang X, Jiang L, Wang N et al (2019) A large-scale database and a CNN Model For Attention-Based Glaucoma Detection. IEEE Trans Med Imaging 39(2):413–424
Li T, Bo W, Hu C, Kang H, Liu H, Wang K, Fu H (2021) Applications of deep learning in fundus images: a review. Med Image Anal 2021:101971
Maninis KK, Pont-Tuset J, Arbeláez P, Van Gool L (2016) Deep retinal image understanding. In: International conference on medical image computing and computer-assisted intervention (pp 140–148). Springer, Cham
Martins J, Cardoso JS, Soares F (2020) Offline computer-aided diagnosis for Glaucoma detection using fundus images targeted at mobile devices. Comput Methods Progr Biomed 192:105341
Natarajan D, Sankaralingam E, Balraj K, Karuppusamy S (2021) A deep learning framework for glaucoma detection based on robust optic disc segmentation and transfer learning. Int J Imaging Syst Technol 2021:5
Nirmala K, Venkateswaran N, Kumar CV (2017) HoG based Naive Bayes classifier for glaucoma detection. In: TENCON 2017–2017 IEEE Region 10 Conference (pp 2331–2336), IEEE
Orlando JI, Fu H, Breda JB, van Keer K, Bathula DR, Diaz-Pinto A, Bogunović H et al (2020) Refuge challenge: a unified framework for evaluating automated methods for glaucoma assessment from fundus photographs. Med Image Anal 59:101570
Orlando JI, Prokofyeva E, del Fresno M, Blaschko MB (2017) Convolutional neural network transfer for automated glaucoma identification. In: 12th international symposium on medical information processing and analysis (Vol. 10160, p. 101600U). International Society for Optics and Photonics
Panda R, Puhan NB, Panda G (2016) New binary Hausdorff symmetry measure based seeded region growing for retinal vessel segmentation. Biocybern Biomed Eng 36(1):119–129
Panda R, Puhan NB, Panda G (2017) Robust and accurate optic disk localization using vessel symmetry line measure in fundus images. Biocybern Biomed Eng 37(3):466–476
Phasuk S, Poopresert P, Yaemsuk A, Suvannachart P, Itthipanichpong R, Chansangpetch S, Tantibundhit C et al (2019) Automated glaucoma screening from retinal fundus image using deep learning. In: 2019 41st annual international conference of the IEEE engineering in medicine and biology society (EMBC) (pp 904–907), IEEE
Raghavendra U, Fujita H, Bhandary SV, Gudigar A, Tan JH, Acharya UR (2018a) Deep convolution neural network for accurate diagnosis of glaucoma using digital fundus images. Inf Sci 441:41–49
Raghavendra U, Bhandary SV, Gudigar A, Acharya UR (2018b) Novel expert system for glaucoma identification using non-parametric spatial envelope energy spectrum with fundus images. Biocybern Biomed Eng 38(1):170–180
Serte S, Serener A (2021) Graph-based saliency and ensembles of convolutional neural networks for glaucoma detection. IET Image Process 2021:1
Sevastopolsky A (2017) Optic disc and cup segmentation methods for glaucoma detection with modification of U-Net convolutional neural network. Pattern Recogn Image Anal 27(3):618–624
Sharma A, Agrawal M, Roy SD, Gupta V (2020) Automatic glaucoma diagnosis in digital fundus images using deep CNNs. In: Advances in computational intelligence techniques (pp 37–52). Springer, Singapore
Shibata N, Tanito M, Mitsuhashi K, Fujino Y, Matsuura M, Murata H, Asaoka R (2018) Development of a deep residual learning algorithm to screen for glaucoma from fundus photography. Sci Rep 8(1):14665
Singh LK, Khanna M (2022) A novel multimodality based dual fusion integrated approach for efficient and early prediction of glaucoma. Biomed Signal Process Control 73:103468
Singh LK, Garg H, Khanna M, Bhadoria RS (2021) An enhanced deep image model for glaucoma diagnosis using feature-based detection in retinal fundus. Med Biol Eng Compu 59(2):333–353
Sreng S, Maneerat N, Hamamoto K, Win KY (2020) Deep learning for optic disc segmentation and glaucoma diagnosis on retinal images. Appl Sci 10(14):4916
Szegedy C, Ioffe S, Vanhoucke V, Alemi AA (2017) Inception-v4, inception-resnet and the impact of residual connections on learning. In: Thirty-first AAAI conference on artificial intelligence.
Tabassum M, Khan TM, Arsalan M, Naqvi SS, Ahmed M, Madni HA, Mirza J (2020) CDED-Net: joint segmentation of optic disc and optic cup for glaucoma screening. IEEE Access 8:102733–102747
Thawkar S, Sharma S, Khanna M, Kumar Singh L (2021) Breast cancer prediction using a hybrid method based on Butterfly Optimization Algorithm and Ant Lion Optimizer. Comput Biol Med 2021:104968
Tiwari S, Jain A (2021) Convolutional capsule network for COVID-19 detection using radiography images. Int J Imaging Syst Technol 31(2):525–539
Tulsani A, Kumar P, Pathan S (2021) Automated segmentation of optic disc and optic cup for glaucoma assessment using improved UNET++ architecture. Biocybernetics and Biomedical Engineering 2021:5
Uribe-Valencia LJ, Martínez-Carballido JF (2019) Automated Optic Disc region location from fundus images: using local multi-level thresholding, best channel selection, and an Intensity Profile Model. Biomed Signal Process Control 51:148–161
Yu S, Xiao D, Frost S, Kanagasingam Y (2019) Robust optic disc and cup segmentation with deep learning for glaucoma detection. Comput Med Imaging Graph 74:61–71
Zhang R, Zong Q, Dou L, Zhao X, Tang Y, Li Z (2021) Hybrid deep neural network using transfer learning for EEG motor imagery decoding. Biomed Signal Process Control 63:102144
Zilly J, Buhmann JM, Mahapatra D (2017) Glaucoma detection using entropy sampling and ensemble learning for automatic optic cup and disc segmentation. Comput Med Imaging Graph 55:28–41
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Singh, L.K., Pooja, Garg, H. et al. Deep learning system applicability for rapid glaucoma prediction from fundus images across various data sets. Evolving Systems 13, 807–836 (2022). https://doi.org/10.1007/s12530-022-09426-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12530-022-09426-4