Authors

P.Revathi

Research Scholar, Department of Computer Science, NGM College, Pollachi, Tamilnadu, India

Dr. R.Jayaprakash

Assistant Professor, Department of Computer Science, NGM College, Pollachi, Tamilnadu, India

Abstract

Over several decades, machine learning has developed into a valuable approach for learning complex patterns from medical image data. This study introduces a novel weighted ensemble machine learning framework with LightGBM for glaucoma severity classification using retinal fundus images. The proposed framework applies suitable pre-processing and feature extraction to obtain informative image representations, which are subsequently provided to a set of complementary machine learning classifiers. Instead of depending on the decision of a single classifier, the proposed method combines their outputs using a weighted ensemble strategy that assigns different contributions to individual models based on their predictive behaviour. LightGBM is integrated into the ensemble to enhance the learning of nonlinear feature relationships and improve the final decision process. The combined predictions are used to distinguish different glaucoma severity categories from retinal fundus images. The proposed framework emphasizes the integration of enhanced classifier with weighted decision fusion, and LightGBM to manipulate the individual classification models effectively. In our approach unified learning strategy provides a structured and flexible approach for automated glaucoma severity classification and demonstrates the potential of ensemble-based machine learning for retinal image analysis respectively.

Keywords

Glaucoma Severity Classification Machine Learning Weighted Ensemble Learning LightGBM Retinal Fundus Images Feature Extraction Classification Decision Fusion Automated Diagnosis

Citation of this Article

P.Revathi, & Dr. R.Jayaprakash. (2026). A Novel Weighted Ensemble Approach Integrating LightGBM for Glaucoma Severity Classification on Retinal Fundus Images. International Current Journal of Engineering and Science (ICJES), 5(4), 52-57. Article DOI: https://doi.org/10.47001/ICJES/2026.504007  

Licence Copyright (c) 2026 International Current Journal of Engineering and Science. This work is licensed under a Creative Commons Attribution Non Commercial 4.0 International Licence.

References

  1. M. N. Bajwa et.al., “Two-stage framework for optic disc localization and glaucoma classification in retinal fundus images using deep learning,” BMC Medical Informatics and Decision Making, vol. 19, Art. no. 136, 2019.
  2. S. Phan et.al. “Evaluation of deep convolutional neural networks for glaucoma detection,” Japanese Journal of Ophthalmology, vol. 63, pp. 276–283, 2019.
  3. R. Hemelings et al., “Accurate prediction of glaucoma from colour fundus images with a convolutional neural network that relies on active and transfer learning,” Acta Ophthalmologica, vol. 98, no. 1, pp. e94–e100, 2020.
  4. K. Hashimoto et. al. “Glaucoma diagnosis with machine learning based on optical coherence tomography and color fundus images,” Journal of Healthcare Engineering, vol. 2019, Art. no. 4061313, 2019.
  5. Sonia Phene et al. “Deep learning and glaucoma specialists: The relative importance of optic disc features to predict glaucoma referral in fundus photographs,” Ophthalmology, vol. 126, no. 12, pp. 1627–1639, 2019.
  6. J. M. L. et al., “Predicting glaucoma before onset using deep learning,” Ophthalmology Glaucoma, vol. 3, no. 4, pp. 262–268, 2020.
  7. A.J. Thompson et al., “Human versus machine: Comparing a deep learning algorithm to human gradings for detecting glaucoma on fundus photographs,” American Journal of Ophthalmology, vol. 211, pp. 123–131, 2020.
  8. S. Ajitha et. al. “Identification of glaucoma from fundus images using deep learning techniques,” Indian Journal of Ophthalmology, vol. 69, no. 10, pp. 2702–2709, 2021.
  9. R. Shinde et. al. “Glaucoma detection in retinal fundus images using U-Net and supervised machine learning algorithms,” Intelligence-Based Medicine, vol. 5, Art. no. 100038, 2021.
  10. O. C. Devecioglu et. al. “Real-time glaucoma detection from digital fundus images using Self-ONNs,” IEEE Access, vol. 9, pp. 140031–140041, 2021.
  11. W. T. Song et. al. “A statistical robust glaucoma detection framework combining Retinex, CNN, and DOE using fundus images,” IEEE Access, vol. 9, pp. 103772–103783, 2021.
  12. H. Cho et. al. “Deep learning ensemble method for classifying glaucoma stages using fundus photographs and convolutional neural networks,” Current Eye Research, vol. 46, no. 10, pp. 1516–1524, 2021.
  13. M. Alghamdi et. al. “A comparative study of deep learning models for diagnosing glaucoma from fundus images,” IEEE Access, vol. 9, pp. 23894–23906, 2021.
  14. P. Shanmugam et. al. “An automatic recognition of glaucoma in fundus images using deep learning and random forest classifier,” Applied Soft Computing, vol. 109, Art. no. 107512, 2021.
  15. V. Sunanthini, et. al. “Comparison of CNN algorithms for feature extraction on fundus images to detect glaucoma,” Journal of Healthcare Engineering, vol. 2022, Art. no. 7873300, 2022.
  16. P. Venkatesh Ramesh et. al. “Utilizing human intelligence in artificial intelligence for detecting glaucomatous fundus images using human-in-the-loop machine learning,” Indian Journal of Ophthalmology, vol. 70, no. 4, pp. 1131–1138, 2022.
  17. S. N. Sangeethaa et. al. “Presumptive discerning of the severity level of glaucoma through clinical fundus images using hybrid PolyNet,” Biomedical Signal Processing and Control, vol. 81, Art. no. 104347, 2023.
  18. S. Pathan, et. al. “An automated classification framework for glaucoma detection in fundus images using ensemble of dynamic selection methods,” Progress in Artificial Intelligence, vol. 12, pp. 287–301, 2023.
  19. K. Sonti et. al. “A new convolution neural network model ‘KR-NET’ for retinal fundus glaucoma classification,” Optik, vol. 283, Art. no. 170861, 2023.
  20. G. D’Souza et. al. “AlterNet-K: A small and compact model for the detection of glaucoma,” Biomedical Engineering Letters, vol. 14, pp. 23–33, 2024.