Artificial intelligence and glaucoma structure-function map: a systematic review.
6 affiliations
- 1State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Guangdong Provincial Key Laboratory of Ophthalmology and Visual Science, Guangdong Provincial Clinical Research Center for Ocular Diseases, Sun Yat- Sen University, No. 7 Jinsui Road, Guangzhou, 510060, China.
- 2Shanghai Artificial Intelligence Innovation Center, Shanghai, 200232, China.
- 3Ophthalmology, Mayo Clinic Health System, Eau Claire, WI, USA.
- 4Yunnan Eye Institute & Key Laboratory of Yunnan Province, Yunnan Eye Disease Clinical Medical Center, Affiliated Hospital of Yunnan University, Yunnan University, 176 Qingnian, Kunming, 650021, China.
- 5State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Guangdong Provincial Key Laboratory of Ophthalmology and Visual Science, Guangdong Provincial Clinical Research Center for Ocular Diseases, Sun Yat- Sen University, No. 7 Jinsui Road, Guangzhou, 510060, China. [email protected].
- 6State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Guangdong Provincial Key Laboratory of Ophthalmology and Visual Science, Guangdong Provincial Clinical Research Center for Ocular Diseases, Sun Yat- Sen University, No. 7 Jinsui Road, Guangzhou, 510060, China. [email protected].
Abstract
Introduction
With advancing insights into the structure-function relationship in glaucoma, developing visual field (VF) predictive models based on optical coherence tomography (OCT)-detected structural changes have emerged as a significant research hotspot. Artificial Intelligence (AI) technologies have been widely applied in this area, demonstrating significant potential.Methods
A comprehensive search was conducted using databases such as PubMed, Scopus, Web of Science, and Embase with key search terms including "artificial intelligence," "machine learning," "deep learning," "optical coherence tomography," "visual field," "structure-function map," and "glaucoma". Following rigorous and meticulous inclusion, exclusion, and review processes, a total of 36 studies were ultimately selected for analysis.Results
Several studies reported favorable performance for predicting global VF indices, pointwise VF sensitivity, or longitudinal VF progression, although performance varied across tasks, datasets, OCT devices, VF patterns, validation designs, and performance metrics. Various visualization techniques, including heatmaps, simulation of structure-function maps, and occlusion maps, have been employed to interpret the predictions of these models. The generated structure-function maps are consistent with the current clinical understanding of the relationship between glaucoma structure and function. However, current AI models generally suffer from decreased performance in the advanced stage glaucoma and are limited by the narrow scanning range of OCT.Conclusions
Current glaucoma structure-function AI prediction models have been applied to pointwise VF prediction. However, to further deploy these models in glaucoma clinical settings, it is necessary to construct models that can predict pattern deviation probability maps based on wide-field volumetric OCT scans.
Related
- Evaluating the impact of social determinants of health on model performance and fairness in artificial intelligence for glaucoma progression prediction
- Early Structure–Function Correlates in Neovascular Age-Related Macular Degeneration Using Artificial Intelligence–Derived OCT Biomarkers
- Generative Artificial Intelligence Models in Breast Cancer Diagnosis: A Systematic Review
- Utility of Artificial Intelligence in Detecting Lymph Node Metastasis in Oral Cancer: A Systematic Review
- External validation of artificial intelligence-guided electrocardiogram (AI-ECG) in detecting asymptomatic left ventricular dysfunction: A systematic review and meta-analysis
BibTeX
@article{wang2026artificial,
title = {{Artificial intelligence and glaucoma structure-function map: a systematic review.}},
author = {Deming Wang and Zefeng Yang and Diping Song and Zihan Li and Fengqi Zhou and Yinhang Zhang and Jiaxuan Jiang and Kangjie Kong and Zige Fang and Xiaoyi Liu and Fei Li and Xiulan Zhang},
journal = {BMC ophthalmology},
year = {2026},
month = aug,
doi = {10.1186/s12886-026-05175-z},
url = {https://europepmc.org/article/MED/42958112},
note = {CC BY-NC-ND},
}
RIS
TY - JOUR
TI - Artificial intelligence and glaucoma structure-function map: a systematic review.
AU - Deming Wang
AU - Zefeng Yang
AU - Diping Song
AU - Zihan Li
AU - Fengqi Zhou
AU - Yinhang Zhang
AU - Jiaxuan Jiang
AU - Kangjie Kong
AU - Zige Fang
AU - Xiaoyi Liu
AU - Fei Li
AU - Xiulan Zhang
PY - 2026
DA - 2026/08/03
JO - BMC ophthalmology
DO - 10.1186/s12886-026-05175-z
UR - https://europepmc.org/article/MED/42958112
AB - Introduction With advancing insights into the structure-function relationship in glaucoma, developing visual field (VF) predictive models based on optical coherence tomography (OCT)-detected structural changes have emerged as a significant research hotspot. Artificial Intelligence (AI) technologies have been widely applied in this area, demonstrating significant potential.Methods A comprehensive search was conducted using databases such as PubMed, Scopus, Web of Science, and Embase with key search terms including "artificial intelligence," "machine learning," "deep learning," "optical coherence tomography," "visual field," "structure-function map," and "glaucoma". Following rigorous and meticulous inclusion, exclusion, and review processes, a total of 36 studies were ultimately selected for analysis.Results Several studies reported favorable performance for predicting global VF indices, pointwise VF sensitivity, or longitudinal VF progression, although performance varied across tasks, datasets, OCT devices, VF patterns, validation designs, and performance metrics. Various visualization techniques, including heatmaps, simulation of structure-function maps, and occlusion maps, have been employed to interpret the predictions of these models. The generated structure-function maps are consistent with the current clinical understanding of the relationship between glaucoma structure and function. However, current AI models generally suffer from decreased performance in the advanced stage glaucoma and are limited by the narrow scanning range of OCT.Conclusions Current glaucoma structure-function AI prediction models have been applied to pointwise VF prediction. However, to further deploy these models in glaucoma clinical settings, it is necessary to construct models that can predict pattern deviation probability maps based on wide-field volumetric OCT scans.
SN - 1471-2415
ER -