A Review of Glaucoma Optic Disk Localization and Classification Machine Learning and Deep Learning Models


  • Anshul Jain LNCT University, India Author
  • Vikas Sakalle LNCT University, India Author


Glaucoma, Optic Disk, Machine Learning, Deep Learning, Convolutional Neural Networks, Diagnosis


This review aims to comprehensively synthesise recent advancements in machine learning (ML) and deep learning (DL) models specifically designed for localising and classifying the optic disk in glaucoma diagnosis. Glaucoma, a leading cause of irreversible blindness, is characterised by distinctive changes in the optic disk. Manual evaluations, although invaluable, face challenges due to inconsistencies, subjectivity, and the considerable time required. With the emergence of artificial intelligence, ML and DL models have become potent tools for enhanced and automated optic disk evaluations. An exhaustive literature search of primary studies from 2010 to 2023 focused on models to localise and classify the optic disk in glaucoma diagnosis. Selection criteria included novelty, accuracy, and clinical relevance of the models. Various architectures, datasets used, training techniques, and performance metrics were critically analysed. Numerous ML and DL models have shown promising optic disk localisation and classification results. Convolutional Neural Networks (CNN) have predominantly led the DL paradigm, with innovative architectures improving specificity and sensitivity. Hybrid models integrating traditional ML techniques with DL have also emerged, demonstrating enhanced robustness and generalizability. ML and DL models possess transformative potential in glaucoma care, offering a blend of accuracy, efficiency, and consistency. As these models evolve, integrating larger datasets and multimodal imaging, their role in clinical settings is poised to expand, bridging the gap between technological advancements and patient-centric care.




How to Cite

A Review of Glaucoma Optic Disk Localization and Classification Machine Learning and Deep Learning Models. (2024). International Journal of Innovative Research in Technology and Science, 12(2), 163-176. https://ijirts.org/index.php/ijirts/article/view/25

Similar Articles

1-10 of 31

You may also start an advanced similarity search for this article.