Automated Detection and Biomarker Identification Associated with the Structural and Functional Progression of Glaucoma on Longitudinal Color Fundus Images
The diagnosis of primary open-angle glaucoma (POAG) progression based on structural imaging such as color fundus photos (CFPs) is challenging due to the limited number of early biomarkers, as commonly determined by clinicians, and the inherent variability in optic nerve heads (ONHs) between individu...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-02-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/3/1627 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850068540186427392 |
|---|---|
| author | Iyad Majid Zubin Mishra Ziyuan Chris Wang Vikas Chopra Dale Heuer Zhihong Jewel Hu |
| author_facet | Iyad Majid Zubin Mishra Ziyuan Chris Wang Vikas Chopra Dale Heuer Zhihong Jewel Hu |
| author_sort | Iyad Majid |
| collection | DOAJ |
| description | The diagnosis of primary open-angle glaucoma (POAG) progression based on structural imaging such as color fundus photos (CFPs) is challenging due to the limited number of early biomarkers, as commonly determined by clinicians, and the inherent variability in optic nerve heads (ONHs) between individuals. Moreover, while visual function is the main concern for glaucoma patients, and the ability to infer future visual outcome from imaging will benefit patients by early intervention, there is currently no available tool for this. To detect glaucoma progression from ocular hypertension both structurally and functionally, and identify potential objective early biomarkers associated with progression, we developed and evaluated deep convolutional long short-term memory (CNN-LSTM) neural network models using longitudinal CFPs from the Ocular Hypertension Treatment Study (OHTS). Patients were categorized into four diagnostic groups for model input: healthy, POAG with optic disc changes, POAG with visual field (VF) changes, and POAG with both optic disc and VF changes. Gradient-weighted class activation mapping (Grad-CAM) was employed for the post hoc visualization of image features, which may be associated with the objective POAG biomarkers (rather than the biomarkers determined by clinicians). The CNN-LSTM models for the detection of POAG progression achieved promising performance results both for the structural and functional models, with an area under curve (AUC) performance of 0.894 for the disc-only group, 0.911 for the VF-only group, and 0.939 for the disc and VF group. The model demonstrated high precision (0.984) and F1-score (0.963) in the both-changes group (disc + VF). Our preliminary investigation for early POAG biomarkers with Grad-CAM feature visualization signified that retinal vasculature could serve as an early and objective biomarker for POAG progression, complementing the traditionally used optic disc features and improving clinical workflows. |
| format | Article |
| id | doaj-art-79327aa3f63c490a9edaa4dfbed10d07 |
| institution | DOAJ |
| issn | 2076-3417 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-79327aa3f63c490a9edaa4dfbed10d072025-08-20T02:48:02ZengMDPI AGApplied Sciences2076-34172025-02-01153162710.3390/app15031627Automated Detection and Biomarker Identification Associated with the Structural and Functional Progression of Glaucoma on Longitudinal Color Fundus ImagesIyad Majid0Zubin Mishra1Ziyuan Chris Wang2Vikas Chopra3Dale Heuer4Zhihong Jewel Hu5Doheny Image Analysis Laboratory, Doheny Eye Institute, Pasadena, CA 91103, USADoheny Image Analysis Laboratory, Doheny Eye Institute, Pasadena, CA 91103, USADoheny Image Analysis Laboratory, Doheny Eye Institute, Pasadena, CA 91103, USADoheny Image Analysis Laboratory, Doheny Eye Institute, Pasadena, CA 91103, USADepartment of Ophthalmology and Visual Sciences, Medical College of Wisconsin, Milwaukee, WI 53226, USADoheny Image Analysis Laboratory, Doheny Eye Institute, Pasadena, CA 91103, USAThe diagnosis of primary open-angle glaucoma (POAG) progression based on structural imaging such as color fundus photos (CFPs) is challenging due to the limited number of early biomarkers, as commonly determined by clinicians, and the inherent variability in optic nerve heads (ONHs) between individuals. Moreover, while visual function is the main concern for glaucoma patients, and the ability to infer future visual outcome from imaging will benefit patients by early intervention, there is currently no available tool for this. To detect glaucoma progression from ocular hypertension both structurally and functionally, and identify potential objective early biomarkers associated with progression, we developed and evaluated deep convolutional long short-term memory (CNN-LSTM) neural network models using longitudinal CFPs from the Ocular Hypertension Treatment Study (OHTS). Patients were categorized into four diagnostic groups for model input: healthy, POAG with optic disc changes, POAG with visual field (VF) changes, and POAG with both optic disc and VF changes. Gradient-weighted class activation mapping (Grad-CAM) was employed for the post hoc visualization of image features, which may be associated with the objective POAG biomarkers (rather than the biomarkers determined by clinicians). The CNN-LSTM models for the detection of POAG progression achieved promising performance results both for the structural and functional models, with an area under curve (AUC) performance of 0.894 for the disc-only group, 0.911 for the VF-only group, and 0.939 for the disc and VF group. The model demonstrated high precision (0.984) and F1-score (0.963) in the both-changes group (disc + VF). Our preliminary investigation for early POAG biomarkers with Grad-CAM feature visualization signified that retinal vasculature could serve as an early and objective biomarker for POAG progression, complementing the traditionally used optic disc features and improving clinical workflows.https://www.mdpi.com/2076-3417/15/3/1627automated detectionearly glaucoma biomarkersprimary open-angle glaucomastructural and functional progressionlongitudinal color fundus imagesartificial intelligence |
| spellingShingle | Iyad Majid Zubin Mishra Ziyuan Chris Wang Vikas Chopra Dale Heuer Zhihong Jewel Hu Automated Detection and Biomarker Identification Associated with the Structural and Functional Progression of Glaucoma on Longitudinal Color Fundus Images Applied Sciences automated detection early glaucoma biomarkers primary open-angle glaucoma structural and functional progression longitudinal color fundus images artificial intelligence |
| title | Automated Detection and Biomarker Identification Associated with the Structural and Functional Progression of Glaucoma on Longitudinal Color Fundus Images |
| title_full | Automated Detection and Biomarker Identification Associated with the Structural and Functional Progression of Glaucoma on Longitudinal Color Fundus Images |
| title_fullStr | Automated Detection and Biomarker Identification Associated with the Structural and Functional Progression of Glaucoma on Longitudinal Color Fundus Images |
| title_full_unstemmed | Automated Detection and Biomarker Identification Associated with the Structural and Functional Progression of Glaucoma on Longitudinal Color Fundus Images |
| title_short | Automated Detection and Biomarker Identification Associated with the Structural and Functional Progression of Glaucoma on Longitudinal Color Fundus Images |
| title_sort | automated detection and biomarker identification associated with the structural and functional progression of glaucoma on longitudinal color fundus images |
| topic | automated detection early glaucoma biomarkers primary open-angle glaucoma structural and functional progression longitudinal color fundus images artificial intelligence |
| url | https://www.mdpi.com/2076-3417/15/3/1627 |
| work_keys_str_mv | AT iyadmajid automateddetectionandbiomarkeridentificationassociatedwiththestructuralandfunctionalprogressionofglaucomaonlongitudinalcolorfundusimages AT zubinmishra automateddetectionandbiomarkeridentificationassociatedwiththestructuralandfunctionalprogressionofglaucomaonlongitudinalcolorfundusimages AT ziyuanchriswang automateddetectionandbiomarkeridentificationassociatedwiththestructuralandfunctionalprogressionofglaucomaonlongitudinalcolorfundusimages AT vikaschopra automateddetectionandbiomarkeridentificationassociatedwiththestructuralandfunctionalprogressionofglaucomaonlongitudinalcolorfundusimages AT daleheuer automateddetectionandbiomarkeridentificationassociatedwiththestructuralandfunctionalprogressionofglaucomaonlongitudinalcolorfundusimages AT zhihongjewelhu automateddetectionandbiomarkeridentificationassociatedwiththestructuralandfunctionalprogressionofglaucomaonlongitudinalcolorfundusimages |