Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Jun 2;14(6):30.
doi: 10.1167/tvst.14.6.30.

Optic Cup and Disc Segmentation of Fundus Images Using Artificial Intelligence Externally Validated With Optical Coherence Tomography Measurements

Scott Kinder  1 , Steve McNamara  1 , Christopher Clark  1 , Benjamin Bearce  1   2 , Upasana Thakuria  1 , Yoga Advaith Veturi  1 , Galia Deitz  1 , Talisa E de Carlo Forest  1 , Naresh Mandava  1 , Malik Y Kahook  1 , Praveer Singh  1 , Jayashree Kalpathy-Cramer  1
Affiliations

Optic Cup and Disc Segmentation of Fundus Images Using Artificial Intelligence Externally Validated With Optical Coherence Tomography Measurements

Scott Kinder et al. Transl Vis Sci Technol. .

Abstract

Purpose: To develop an artificial intelligence (AI) optic cup and disc segmentation pipeline for obtaining optic nerve head (ONH) measurements such as vertical cup-to-disc ratio (VCDR) from fundus images and externally validate performance against optical coherence tomography (OCT) measurements.

Methods: This diagnostic study used a retrospectively collected dataset of 27,252 fundus images associated with 12,477 OCT reports and 21,714 expert assessments of VCDR from electronic health records (EHRs) for 4289 patients inclusive of glaucoma suspects, primary and secondary glaucoma. The AI pipeline was trained on nine public glaucoma datasets and externally validated on a private hospital dataset and a publicly available dataset.

Results: AI VCDR predictions against OCT yielded mean absolute error (MAE), Pearson's R, and concordance correlation coefficient (CCC) values of 0.097 (95% confidence interval [CI], 0.095-0.099), 0.80 (95% CI, 0.79-0.81), and 0.66 (95% CI, 0.64-0.67), respectively. EHR VCDRs against OCT had MAE, Pearson's R, and CCC values of 0.086 (95% CI, 0.084-0.087), 0.77 (95% CI, 0.76-0.78), and 0.74 (95% CI, 0.73-0.75), respectively. The coefficient of variation (CV) of the AI pipeline on same-day images was 2.79%.

Conclusions: The proposed AI pipeline had strong correlation with OCT measurements and performed comparably to EHR assessments, with high repeatability. Increased diversity and cardinality of training data improved performance and generalizability to unseen datasets.

Translational relevance: AI pipelines for fundus images can provide ONH measurements such as VCDR near expert level in new patient populations without the need for additional model training.

PubMed Disclaimer

Conflict of interest statement

Disclosure: S. Kinder, None; S. McNamara, Evolution Optiks (C); C. Clark, None; B. Bearce, None; U. Thakuria, None; Y.A. Veturi, None; G. Deitz, None; T.E. de Carlo Forest, Genentech (C); N. Mandava, Soma Logic (C, R), ONL Therapeutics (C), Alcon (P), 2C Tech (P, I, O), Aurea Medical (I, O); M.Y. Kahook, New World Medical (R, C), Alcon (R), SpyGlass Pharma (O, C, R); P. Singh, None; J. Kalpathy-Cramer, Boston AI Lab (R), Genentech (F), GE Healthcare (F), Siloam Vision (C)

Figures

Figure 1.
Figure 1.
Architecture for the proposed AI pipeline to handle both full fundus and stereoscopic images. Images are cropped tightly to the ONH before being segmented by the segmentation model and are then recovered onto the original image.
Figure 2.
Figure 2.
AI VCDR predictions versus public data label VCDR. Public test set VCDR scatterplot; G1020 contained many samples without an optic cup segmentation.
Figure 3.
Figure 3.
AI and EHR VCDR predictions versus OCT. (A) Scatterplot of AI VCDR predictions versus OCT VCDR measurements with a detection threshold above 0.9 on the retrospectively collected private data. (B) EHR VCDR assessments against OCT VCDR measurements with a detection threshold above 0.9 on the retrospectively collected private data.
Figure 4.
Figure 4.
Longitudinal example of a patient eye. AI segmentation masks and fundus images are shown above and below the AI prediction values.
See this image and copyright information in PMC

References

    1. Stein JD, Khawaja AP, Weizer JS. Glaucoma in adults—screening, diagnosis, and management: a review. JAMA. 2021; 325(2): 164–174. - PubMed
    1. Tham Y-C, Li X, Wong TY, Quigley HA, Aung T, Cheng C-Y. Global prevalence of glaucoma and projections of glaucoma burden through 2040: a systematic review and meta-analysis. Ophthalmology. 2014; 121(11): 2081–2090. - PubMed
    1. Tatham AJ, Weinreb RN, Medeiros FA. Strategies for improving early detection of glaucoma: the combined structure–function index. Clin Ophthalmol. 2014; 8: 611–621. - PMC - PubMed
    1. Fleming C, Whitlock EP, Beil T, Smit B, Harris RP. Screening for primary open-angle glaucoma in the primary care setting: an update for the US preventive services task force. Ann Fam Med. 2005; 3(2): 167–170. - PMC - PubMed
    1. Hart WM, Yablonski M, Kass MA, Becker B. Multivariate analysis of the risk of glaucomatous visual field loss. Arch Ophthalmol. 1979; 97(8): 1455–1458. - PubMed