Enhancing Glaucoma Diagnosis with Deep Learning: A Study Using ResNet-50 and DenseNet-121

Year : 2025 | Volume : 02 | Issue : 02 | Page : 9 18
    By

    Meenakshi Sharma,

  • Naman Sharma,

  • Pinu Adarsh,

  • Vikash Prasad,

  1. Professor, Department of Computer Science & Engineering, Global Group of Institutes, Punjab, India
  2. Student, Department of Computer Science & Engineering, Global Group of Institutes, Punjab, India
  3. Student, Department of Computer Science & Engineering, Global Group of Institutes, Punjab, India
  4. Student, Department of Computer Science & Engineering, Global Group of Institutes, Punjab, India

Abstract

Glaucoma is a leading cause of irreversible blindness worldwide, mainly resulting from progressive optic nerve damage, often related to elevated intraocular pressure. Early detection is essential to prevent vision loss, but traditional diagnostic methods rely on specialized equipment and trained professionals, making large-scale screening difficult. This study uses a publicly available fundus imaging dataset to explore the effectiveness of deep learning models for glaucoma detection. These datasets provide medical images, specifically fundus images (images of the back of the eye), and specifically evaluate the performance of ResNet-50 and DenseNet- 121 architectures in binary and multi-class classification tasks. In a binary classification task for glaucoma detection, the combined use of ResNet-50 and DenseNet-121 models delivered impressive results — achieving a precision of 1.0, recall of 0.92, specificity of 1.0, an F1 score of 0.958, and an overall accuracy of 96.1%. These findings suggest that binary classification offers better performance than multi-class approaches for identifying glaucoma. The study emphasizes the promise of deep learning techniques in supporting early glaucoma diagnosis and highlights the importance of continued clinical validation before these tools can be widely adopted in real-world settings.

Keywords: Glaucoma, Deep Learning, ResNet-50, DenseNet-121, Medical Image Analysis.

[This article belongs to International Journal of Brain Sciences ]

How to cite this article:
Meenakshi Sharma, Naman Sharma, Pinu Adarsh, Vikash Prasad. Enhancing Glaucoma Diagnosis with Deep Learning: A Study Using ResNet-50 and DenseNet-121. International Journal of Brain Sciences. 2025; 02(02):9-18.
How to cite this URL:
Meenakshi Sharma, Naman Sharma, Pinu Adarsh, Vikash Prasad. Enhancing Glaucoma Diagnosis with Deep Learning: A Study Using ResNet-50 and DenseNet-121. International Journal of Brain Sciences. 2025; 02(02):9-18. Available from: https://journals.stmjournals.com/ijbs/article=2025/view=216818


References

  1. World Health Organization. Report of the 2030 targets on effective coverage of eye care. World Health Organization; 2022 Oct 12.
  2. Tham YC, Li X, Wong TY, Quigley HA, Aung T, Cheng CY. Global prevalence of glaucoma and projections of glaucoma burden through 2040: a systematic review and meta-analysis. Ophthalmology. 2014 Nov 1;121(11):2081-90.
  3. Weinreb RN, Aung T, Medeiros FA. The pathophysiology and treatment of glaucoma. JAMA. 2014;311:1901.
  4. LeCun Y, Bengio Y, Hinton G. Deep learning. nature. 2015 May 28;521(7553):436-44.
  5. Prajna Y, Nath MK. Efficient blood vessel segmentation from color fundus image using deep neural network. J Intell Fuzzy Syst. 2022;42(4):3477–89.
  6. Mahum R, Ur Rehman S, Okon OD, Alabrah A, Meraj T, Rauf HT. A novel hybrid approach based on deep CNN to detect glaucoma using fundus imaging. Electronics. 2022;11(1):26.
  7. Ariyarathne G, De Silva S, Dayarathna S, Meedeniya D, Jayarathne S. ADHD identification using convolutional neural network with seed-based approach for MRI data. In: Proceedings of the 9th International Conference on Software and Computer Applications; 2020 Jan 9–11; Langkawi, Malaysia. ACM; p. 31–5.
  8. Chen X, Xu Y, Wong DWK, et al. Glaucoma detection based on deep convolutional neural networks. In: Proceedings of the 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society; 2015.
  9. 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;125:1199–206.
  10. Christopher M, Belghith A, Bowd C, Proudfoot JA, Goldbaum MH, Weinreb RN, et al. Performance of deep learning architectures and transfer learning for detecting glaucomatous optic neuropathy in fundus photographs. Sci Rep. 2018;8:16685.
  11. Kim SH, Cho J, Chae H, Lim YJ, Lee M, Oh J, et al. Efficacy of a comprehensive binary classification model using a deep convolutional neural network for wireless capsule endoscopy. Sci Rep. 2021;11:1328.
  12. Ma Y, Xu T, Han S, Kim K. Ensemble learning of multiple deep CNNs using accuracy-based weighted voting for ASL recognition. Appl Sci. 2022;12:11766.
  13. Sharma M, Bhagat B, Kumari V, Sharma N, Singh D. A Comparative Analysis of CNN and Transfer Learning Algorithms in Predicting Alzheimer’s Disease Stages Using Neuroimaging. In: 2024 OPJU International Technology Conference (OTCON) on Smart Computing for Innovation and Advancement in Industry 4.0; 2024 Jun. p. 1–6. IEEE.
  14. Puchaicela-Lozano MS, García-Zapirain B, Illarramendi A, Yanes J. Deep learning for glaucoma detection: R-CNN ResNet-50 and image segmentation. J Adv Inf Technol. 2024;14(6):1186–97.
  15. Fu H, Cheng J, Xu Y, Zhang C, Gao N, Jin K, et al. Disc-aware ensemble network for glaucoma screening from fundus image. IEEE Trans Med Imaging. 2018;37(11):2493–501.
  16. Braeu FA, Thiéry AH, Tun TA, Kadziauskiene A, Barbastathis G, Aung T, et al. Geometric deep learning to identify the critical 3D structural features of the optic nerve head for glaucoma diagnosis. Am J Ophthalmol. 2023;250:38–48.
Regular Issue Subscription Original Research
Volume 02
Issue 02
Received 25/04/2025
Accepted 09/07/2025
Published 14/07/2025
Publication Time 80 Days
290

Login


My IP

PlumX Metrics