How to Cite
Abstract
Objective: The proposed research aims to develop a novel deep learning method based on a 2D Convolutional Neural Network (CNN), which would successfully merge information from two essential ocular imaging techniques, including fundus photography and optical coherence tomography.
Methods: The proposed CNN model achieved both high diagnostic precision and generalization capability through its use of the RMSprop optimizer and categorical cross-entropy loss function. Multiple publicly available datasets were used to evaluate the proposed method, including RIM-ONE, Drishti-GS, ORIGA-light, HRF, and ACRIMA (fundus images), as well as a specialized clinical OCT dataset. The proposed method was tested using standard performance metrics against previous notable studies.
Results: The proposed CNN model produced AUC scores of 0.97 for OCT images and 0.96 for fundus images, which outperformed previous results. The OCT images delivered vital information about the optic nerve head structure, which fundus images confirmed through their display of essential clinical indicators for glaucoma diagnosis.
Conclusion: The research shows that the proposed deep learning method can perform real-time glaucoma detection during medical procedures. The proposed model produced exceptional diagnostic results for subclinical glaucoma suspects through its dual imaging system, which improved the ability to protect vision quality and reduce the impact on life quality.
Keywords: Glaucoma, Fundus Oculi, Diagnostic Imaging, Computer-Aided Diagnosis, OCT
References
Mehta P, Petersen CA, Wen JC, Banitt MR, Chen PP, Bojikian KD, et al. Automated detection of glaucoma with interpretable machine learning using clinical data and multimodal retinal images. Am J Ophthalmol. 2021;231:154-169. https://doi.org/10.1016/j.ajo.2021.04.021
Rasel RK, Wu F, Chiariglione M, Choi SS, Doble N, Gao XR. Assessing the efficacy of 2D and 3D CNN algorithms in OCT-based glaucoma detection. Sci Rep. 2024;14(1):11758. https://doi.org/10.1038/s41598-024-62411-6
García G, Amor R, Aspirot A, Verdú-Monedero R, Ayala G, Molina R, et al. Circumpapillary OCT-focused hybrid learning for glaucoma grading using tailored prototypical neural networks. Artif Intell Med. 2021;118:102132. https://doi.org/10.1016/j.artmed.2021.102132
Maetschke S, Antony B, Ishikawa H, Wollstein G, Schuman J, Garnavi R. A feature agnostic approach for glaucoma detection in OCT volumes. PLoS One. 2019;14(7):e0219126. https://doi.org/10.1371/journal.pone.0219126
George Y, Antony BJ, Ishikawa H, Wollstein G, Schuman JS, Garnavi R. Attention-guided 3D-CNN framework for glaucoma detection and structural-functional association using volumetric images. IEEE J Biomed Health Inform. 2020;24(12):3421-3430. https://doi.org/10.1109/JBHI.2020.3001019
Alghamdi HS, Tang HL, Waheeb SA, Peto T. Automatic optic disc abnormality detection in fundus images: a deep learning approach. In: Proceedings of the Ophthalmic Medical Image Analysis International Workshop; 2016. p. 17-24. https://doi.org/10.17077/omia.1042
Abbas Q. Glaucoma-Deep: detection of glaucoma eye disease on retinal fundus images using deep learning. Int J Adv Comput Sci Appl. 2017;8(6):41-45. https://doi.org/10.14569/IJACSA.2017.080606
Orlando JI, Prokofyeva E, del Fresno M, Blaschko MB. Convolutional neural network transfer for automated glaucoma identification. In: Proc SPIE. 2017;10160:101600U. https://doi.org/10.1117/12.2255740
Latif J, Tu S, Xiao 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. https://doi.org/10.1007/s42452-022-04984-3
Li Z, He Y, Keel S, Meng W, Chang RT, He M. Efficacy of a deep learning system for detecting glaucomatous optic neuropathy based on color fundus photographs. Ophthalmology. 2018;125(8):1199-1206. https://doi.org/10.1016/j.ophtha.2018.01.023
Akter N, Fletcher-Lartey SM, Kaidonis G, Hasan M, Chansangpetch S, Tham YC, et al. Glaucoma diagnosis using multi-feature analysis and a deep learning technique. Sci Rep. 2022;12:8064. https://doi.org/10.1038/s41598-022-12147-y
Gómez-Valverde JJ, Antón A, Fatti G, Liefers B, Herranz A, Santos A. Automatic glaucoma classification using color fundus images based on convolutional neural networks and transfer learning. Biomed Opt Express. 2019;10(2):892-913. https://doi.org/10.1364/BOE.10.000892
Mangipudi PS, Pandey HM, Choudhary A. Improved optic disc and cup segmentation in glaucomatic images using deep learning architecture. Multimed Tools Appl. 2021;80(20):30143-30163. https://doi.org/10.1007/s11042-020-10430-6
Hemelings R, Elen B, Barbosa-Breda J, Blaschko MB, Stalmans I, Janssens O. Deep learning on fundus images detects glaucoma beyond the optic disc. Sci Rep. 2021;11(1):20313. https://doi.org/10.1038/s41598-021-99605-1
Afreen N, Aluvalu R. Glaucoma detection using explainable AI and deep learning. EAI Endorsed Trans Pervasive Health Technol. 2024;10. https://doi.org/10.4108/eetpht.10.5658
Shinde R. Glaucoma detection in retinal fundus images using U-Net and supervised machine learning algorithms. Intell Based Med. 2021;5:100038. https://doi.org/10.1016/j.ibmed.2021.100038
Abdel-Hamid L. TWEEC: computer-aided glaucoma diagnosis from retinal images using deep learning techniques. Int J Imaging Syst Technol. 2022;32(1):387-401. https://doi.org/10.1002/ima.22621
Surya J, Garima, Pandy N, Rim TH, Lee G, Priya MNS, et al. Efficacy of deep learning-based artificial intelligence models in screening and referring patients with diabetic retinopathy and glaucoma. Indian J Ophthalmol. 2023;71(8):3039-3045. https://doi.org/10.4103/IJO.IJO_11_23
Juneja M, Minhas JS, Singla N, Thakur S, Thakur N, Jindal P. Fused framework for glaucoma diagnosis using Optical Coherence Tomography (OCT) images. Expert Systems with Applications. 2022 Sep 1;201:117202. https://doi.org/10.1016/j.eswa.2022.117202
Fumero F, Alayón S, Sanchez JL, Sigut J, Gonzalez-Hernandez M. RIM-ONE: an open retinal image database for optic nerve evaluation. In: 24th International Symposium on Computer-Based Medical Systems; 2011. p. 1-6. https://doi.org/ 10.1109/CBMS.2011.5999143
Sivaswamy J, Krishnadas SR, Chakravarty A, Joshi GD, Syed TA. A comprehensive retinal image dataset for the assessment of glaucoma from the optic nerve head analysis. JSM Biomed Imaging Data Pap. 2015;2(1):1004.
Zhang Z, Yin FS, Liu J, Wong WK, Tan NM, Lee BH, et al. ORIGA-light: an online retinal fundus image database for glaucoma analysis and research. In: Annu Int Conf IEEE Eng Med Biol Soc. 2010. p. 3065-3068. https://doi.org/ 10.1109/IEMBS.2010.5626137
Budai A, Bock R, Maier A, Hornegger J, Michelson G. Robust vessel segmentation in fundus images. Int J Biomed Imaging. 2013;2013:154860. https://doi.org/ 10.1155/2013/154860
Díaz-Pinto A, Morales S, Naranjo V, Köhler T, Mossi JM, Navea A. CNNs for automatic glaucoma assessment using fundus images: an extensive validation. Biomed Eng Online. 2019;18(1):29. https://doi.org/ 10.1186/s12938-019-0649-y.
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Copyright (c) 2026 Nadia Rasool, Mahmood Ali, Amna Manzoor, Tehreem Tanveer, Farah Akhter, Furqan Shaukat