An Artificial Intelligence Enabled System for Retinal Nerve Fiber Layer Thickness Damage Severity Staging

Siamak Yousefi; Xiaoqin Huang; Asma Poursoroush; Julek Majoor; Hans Lemij; Koen Vermeer; Tobias Elze; Mengyu Wang; Kouros Nouri-Mahdavi; Vahid Mohammadzadeh; Paolo Brusini; Chris Johnson

doi:10.1016/j.xops.2023.100389

An Artificial Intelligence Enabled System for Retinal Nerve Fiber Layer Thickness Damage Severity Staging

Ophthalmol Sci. 2023 Aug 23;4(2):100389. doi: 10.1016/j.xops.2023.100389. eCollection 2024 Mar-Apr.

Authors

Affiliations

¹ Department of Ophthalmology, University of Tennessee Health Science Center, Memphis, Tennessee.
² Department of Genetics, Genomics, and Informatics, University of Tennessee Health Science Center, Memphis, Tennessee.
³ Rotterdam Ophthalmic Institute, The Rotterdam Eye Hospital, Rotterdam, The Netherlands.
⁴ Schepens Eye Research Institute of Massachusetts Eye and Ear, Harvard Medical School, Boston, Massachussetts.
⁵ Department of Ophthalmology, University of California Los Angeles, Los Angeles, California.
⁶ Department of Ophthalmology, "Città di Udine" Health Center, Udine, Italy.
⁷ Department of Ophthalmology & Visual Sciences, University of Iowa Hospitals and Clinics, Iowa City, Iowa.

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.

Keywords: Artificial intelligence; Glaucoma; Glaucoma severity damage; Optical coherence tomography; Retinal nerve fiber layer (RNFL); Staging; Unsupervised machine learning.

Abstract

Grants and funding