Primary eye care

Last updated March 2025

Tags:Real-World DataOptometryOCTRetinal PhotoMaestro

This dataset comprises paired optical coherence tomography (OCT) and color fundus photography (CFP) of hundreds of thousands of individuals being screened and managed by optometry practices (primary eye care) located in the USA and Australia.

It contains data from single screening visits as well as follow-up visits with associated demographic data such as age and gender, OCT analysis data and model generated labels, making it valuable for development and validation of screening and monitoring algorithms.

41

Locations

250K

Subjects

497K

Eyes

786K

Images

REQUEST DATASETS

Dataset overview

Dataset attributes	Details
Publishing Frequency	New major version of the dataset will be released periodically with additional data collected from new sites and/or existing sites.
Last Updated	March 2025
Geographic Coverage	USA, Australia
Sites	13
Individual Practices	41
Devices	Maestro (Topcon Corp., Tokyo, Japan)
Image Formats	DICOM

Metadata	Details
Demographic	Age, Gender
Image Metadata	scan size, scan resolution, fixation, TopQ image quality, OCT focus mode, model name, fovea position, disc center position
OCT Analysis	Disc: TSNIT circle (4 sector, 12 sector, 36 sector), disc topography (e.g. disc / cup / rim area and volume, CD ratio, disc diameter)  Macula: superpixel, 6 sector, and ETDRS grid retinal layer thicknesses

Labels	Details
Model-generated Data	Multi-factorial OCT Score¹ AutoMorph² segmentations, image quality predictions, vascular metrics  Retinal pigmentation score³

References

Fukai K, Terauchi R, Noro T, Ogawa S, Watanabe T, Nakagawa T, et al. Real-time risk score for glaucoma mass screening by spectral domain optical coherence tomography: Development and validation. Transl Vis Sci Technol. 2022 Aug 1;11(8):8.
Zhou Y, Wagner SK, Chia MA, Zhao A, Woodward-Court P, Xu M, et al. AutoMorph: Automated retinal vascular morphology quantification via a deep learning pipeline. Transl Vis Sci Technol. 2022 Jul 8;11(7):12.
Rajesh AE, Olvera-Barrios A, Warwick AN, Wu Y, Stuart KV, Biradar MI, et al. Machine learning derived retinal pigment score from ophthalmic imaging shows ethnicity is not biology. Nat Commun. 2025 Jan 2;16(1):1–14.

Dataset overview

Dataset attributes

Publishing Frequency

New major version of the dataset will be released periodically with additional data collected from new sites and/or existing sites.

Last Updated

March 2025

Geographic Coverage

USA, Australia

Sites

Individual Practices

Devices

Maestro (Topcon Corp., Tokyo, Japan)

Image Formats

DICOM

Metadata

Demographic

Age, Gender

Image Metadata

scan size, scan resolution, fixation, TopQ image quality, OCT focus mode, model name, fovea position, disc center position 

OCT Analysis

Disc: TSNIT circle (4 sector, 12 sector, 36 sector), disc topography (e.g. disc / cup / rim area and volume, CD ratio, disc diameter) 

Macula: superpixel, 6 sector, and ETDRS grid retinal layer thicknesses

Labels

Model-generated Data

Multi-factorial OCT Score¹

AutoMorph² segmentations, image quality predictions, vascular metrics 

Retinal pigmentation score³

References

Fukai K, Terauchi R, Noro T, Ogawa S, Watanabe T, Nakagawa T, et al. Real-time risk score for glaucoma mass screening by spectral domain optical coherence tomography: Development and validation. Transl Vis Sci Technol. 2022 Aug 1;11(8):8.
Zhou Y, Wagner SK, Chia MA, Zhao A, Woodward-Court P, Xu M, et al. AutoMorph: Automated retinal vascular morphology quantification via a deep learning pipeline. Transl Vis Sci Technol. 2022 Jul 8;11(7):12.
Rajesh AE, Olvera-Barrios A, Warwick AN, Wu Y, Stuart KV, Biradar MI, et al. Machine learning derived retinal pigment score from ophthalmic imaging shows ethnicity is not biology. Nat Commun. 2025 Jan 2;16(1):1–14.