An Artificial Intelligence Enabled System for Retinal Nerve Fiber Layer Thickness Damage Severity Staging.
Yousefi Siamak, Huang Xiaoqin, Poursoroush Asma, Majoor Julek, Lemij Hans, Vermeer Koen, Elze Tobias, Wang Mengyu, Nouri-Mahdavi Kouros, Mohammadzadeh Vahid
AI Summary
An AI system objectively staged glaucoma severity using RNFL thickness, finding optimal thresholds for normal, early, moderate, and advanced loss, offering a consistent clinical tool.
Abstract
Purpose
To develop an objective glaucoma damage severity classification system based on OCT-derived retinal nerve fiber layer (RNFL) thickness measurements.
Design
Algorithm development for RNFL damage severity classification based on multicenter OCT data.
Subjects and participants: A total of 6561 circumpapillary RNFL profiles from 2269 eyes of 1171 subjects to develop models, and 2505 RNFL profiles from 1099 eyes of 900 subjects to validate models.
Methods
We developed an unsupervised k -means model to identify clusters of eyes with similar RNFL thickness profiles. We annotated the clusters based on their respective global RNFL thickness. We computed the optimal global RNFL thickness thresholds that discriminated different severity levels based on Bayes' minimum error principle. We validated the proposed pipeline based on an independent validation dataset with 2505 RNFL profiles from 1099 eyes of 900 subjects.
Main outcome measures
Accuracy, area under the receiver operating characteristic curve, and confusion matrix.
Results
The k -means clustering discovered 4 clusters with 1382, 1613, 1727, and 1839 samples with mean (standard deviation) global RNFL thickness of 58.3 (8.9) μm, 78.9 (6.7) μm, 87.7 (8.2) μm, and 101.5 (7.9) μm. The Bayes' minimum error classifier identified optimal global RNFL values of > 95 μ m , 86 to 95 μ m , 70 to 85 μ m , and < 70 μ m for discriminating normal eyes and eyes at the early, moderate, and advanced stages of RNFL thickness loss, respectively. About 4% of normal eyes and 98% of eyes with advanced RNFL loss had either global, or ≥ 1 quadrant, RNFL thickness outside of normal limits provided by the OCT instrument.
Conclusions
Unsupervised machine learning discovered that the optimal RNFL thresholds for separating normal eyes and eyes with early, moderate, and advanced RNFL loss were 95 μ m , 85 μm, and 70 μ m , respectively. This RNFL loss classification system is unbiased as there was no preassumption or human expert intervention in the development process. Additionally, it is objective, easy to use, and consistent, which may augment glaucoma research and day-to-day clinical practice.
Financial disclosures: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.
Shields Classification
Key Concepts4
An unsupervised k-means model identified 4 clusters of eyes with similar retinal nerve fiber layer (RNFL) thickness profiles, with mean global RNFL thicknesses of 58.3 (8.9) μm, 78.9 (6.7) μm, 87.7 (8.2) μm, and 101.5 (7.9) μm, from a dataset of 6561 circumpapillary RNFL profiles from 2269 eyes of 1171 subjects.
The Bayes' minimum error classifier identified optimal global retinal nerve fiber layer (RNFL) values of > 95 μm, 86 to 95 μm, 70 to 85 μm, and < 70 μm for discriminating normal eyes and eyes at the early, moderate, and advanced stages of RNFL thickness loss, respectively, based on multicenter OCT data.
Approximately 4% of normal eyes and 98% of eyes with advanced retinal nerve fiber layer (RNFL) loss had either global, or ≥ 1 quadrant, RNFL thickness outside of normal limits provided by the OCT instrument, according to an unsupervised machine learning model.
Unsupervised machine learning discovered that the optimal retinal nerve fiber layer (RNFL) thresholds for separating normal eyes and eyes with early, moderate, and advanced RNFL loss were 95 μm, 85 μm, and 70 μm, respectively, based on multicenter OCT data.
Related Articles5
Longitudinal Changes of Retinal Nerve Fiber Layer and Ganglion Cell-Inner Plexiform Layer in Highly Myopic Glaucoma: A 3-Year Cohort Study.
Cohort StudyIndependent Evaluation of RETFound Foundation Model's Performance on Optic Nerve Analysis Using Fundus Photography.
Observational StudyProximal Location of Optic Disc Hemorrhage and Glaucoma Progression.
Cohort StudyPrediction of Visual Field Progression with Baseline and Longitudinal Structural Measurements Using Deep Learning.
Observational StudyNumber of macula optical coherence tomography scans needed to detect glaucoma progression.
Cohort StudyIs this article assigned to the wrong chapter(s)? Let us know.