Harnessing Deep Learning for Early Glaucoma Detection: A Review of CNN-Based Diagnostic Models

DOI

10.2991/978-94-6463-512-6_49How to use a DOI?

Keywords

Deep learning; Glaucoma detection; Fundus image; Cup–disc ratio

Abstract

One of the leading causes of permanent blindness worldwide is glaucoma. It now affects over 81 million individuals and is projected to harm 112 million people by 2040. Because symptoms are often asymptomatic in the early stages, many cases are severe when detected, resulting in vision loss and reduced quality of life. Digital fundus photography and non-contact fundus scanning are important tools for early diagnosis by providing detailed images of the eye and optic nerve. Public datasets such as ACRIMA, ORIGA, and REFUGE are widely used in the development of automated screening tools. This article reviews deep learning-based glaucoma detection method, particularly through the use of convolutional neural networks(CNN). Researchers have developed various models, such as 3-LbNets, 2s-ranking CNN, transfer learning-based models and models introducing attention modules to improve diagnostic accuracy. Glaucoma diagnosis relies on optic disc and cup segmentation and feature extraction. Success requires enough training data and medical knowledge. Despite the excellent performance of deep learning in retinal disease diagnosis, clinical applications still face challenges such as data volume, interpretability, and validation requirements. In order to achieve more precise and effective glaucoma diagnosis, future work should concentrate on strengthening data quality, improving model interpretability, and developing validation processes.

Copyright

© 2024 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Yusen Shi
PY  - 2024
DA  - 2024/09/23
TI  - Harnessing Deep Learning for Early Glaucoma Detection: A Review of CNN-Based Diagnostic Models
BT  - Proceedings of the 2024 International Conference on Artificial Intelligence and Communication (ICAIC 2024)
PB  - Atlantis Press
SP  - 459
EP  - 467
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6463-512-6_49
DO  - 10.2991/978-94-6463-512-6_49
ID  - Shi2024
ER  -