407 docs tagged with "resource-role-current-dataset"

Observation-level human or human-derived measurements/signals. from Chinese new-onset optic-neuritis cohort followed three years.

Human/derived image or image-annotation observations. from Patients imaged at Rajbari Eye Clinic and Specialised Hospital, Bangladesh.

The 123-eye diagnostic workbook directly evaluates clinical OCT ultrasonography and biomicroscopy for vitreous detachment.

Official Dryad deposit of source-described tabular ophthalmic data for the associated study.

705 optic disc-centred fundus photographs (396 normal + 309 glaucoma) from Hospital Clinico San Carlos. Expert-annotated binary glaucoma classification.

1200 fundus images for AMD classification, five-class lesion segmentation, fovea/optic disc localisation.

Observation-level human or human-derived measurements/signals. from Human RPE and retinal endothelial cells cultured under hypoxia.

One hundred retinal fundus images from Armed Forces Institute of Ophthalmology, Rawalpindi, with expert annotations for vessels and hypertensive retinopathy, diabetic retinopathy, and papilledema task

The first public AGAR300 release contains 28 color fundus images with microaneurysms, captured at a 45 degree field of view and 2448 by 3264 pixel resolution.

4800 AS-OCT images from 199 patients. Two tasks: angle closure classification and scleral spur localization.

The named DATA.xls and README define a human pediatric ocular-biometry cohort even though the deposit does not state one primary total.

~113,893 color fundus images labelled as referable glaucoma (RG), no referable glaucoma (NRG), or ungradable. Large-scale, multi-ethnic, multi-site screening dataset.

AMD complement/zinc clinical-trial data directly support human retinal disease biomarker and outcome analysis.

3,049 OCT B-scan images (1,140×380 px) from 138 wet AMD patients (156 eyes) with pixel-level annotations for 5 lesion classes: Subretinal Fluid (SRF), Intraretinal Fluid (IRF), Ellipsoid Zone Continui

Observation-level source data, annotations, or signals. from Glaucoma patients and human serum are explicitly stated.

De-identified fluorescein and indocyanine-green angiography images paired with structured lesion descriptions and reports.

Observation-level source data, annotations, or signals. from Source describes de-identified infant fundus images.

Tabular anterior-segment and ocular-biometry measurements before and after SMILE surgery, including slit-lamp examination, Pentacam, and IOLMaster variables.

De-identified anterior-uveitis corneal-endothelial parameters and related variables.

Official Dryad deposit of source-described tabular ophthalmic data for the associated study.

Adaptive-optics scanning-light-ophthalmoscopy montages and regions of interest for RPE morphometry and cone-to-RPE analysis.

Image-level conjunctival observations with anemia target from Human conjunctiva images from Ghana used for iron-deficiency-anemia detection.

3662 fundus images from Aravind Eye Hospital, graded 0-4 for diabetic retinopathy severity.

Peripapillary RNFL and segmented-macular OCT measurements in optic-neuritis cohorts and healthy controls.

1,136 OCT B-scans from 24 AMD patients. Expert annotations for 3 retinal fluid types (IRF, SRF, PED) and 3 retinal layer boundaries for joint layer and fluid segmentation.

Retinal OCTA scans labeled for artifact type, artifact severity, signal strength, and image quality.

1,168 anterior-segment OCT images of keratitis with per-pixel lesion, cornea, and iris segmentation labels. Enables 3D reconstruction from B-scan stacks.

Official Dryad deposit of source-described tabular ophthalmic data for the associated study.

Human eye-tracking observations from an ASD study.

The 452-participant longitudinal pediatric biometric workbook is core myopia progression data.

Small four-class eye-disease image dataset with normal, cataract, glaucoma, and retinal disease categories.

One thousand seven hundred eighty-six original color fundus images for diabetic retinopathy, age-related macular degeneration, and glaucoma grading/classification.

Longitudinal human ophthalmic and OCT measurements in the bariatric cohort are directly reusable clinical data.

Fundus photographs from Bangladesh Eye Hospital for glaucoma detection. Includes optic cup/disc crops and vessel segmentation masks alongside binary glaucoma/normal labels.

Expert-curated ophthalmology multiple-choice benchmark with rationales, assembled for held-out language-model evaluation.

Paired left- and right-eye fundus images.

The 18-participant final CSV is a direct human geographic-atrophy rehabilitation outcome resource.

Observation-level human or human-derived measurements/signals. from 55 high-myopia patients (110 eyes) after ICL implantation.

Longitudinal widefield fundus photographs from birdshot chorioretinitis eyes and age- and sex-matched controls.

Observation-level human or human-derived measurements/signals. from 45 children aged 6–15 years.

Portable/smartphone fundus photographs of Brazilian glaucoma and non-glaucoma volunteers.

16,266 color fundus images from 8,524 Brazilian patients with 14 disease labels (DR, AMD, glaucoma, drusen, others), image quality flags, and demographic attributes.

The 27-eye BRVO archive contains named OCT, fluorescein, and mfERG research objects for retinal treatment analysis.

Six near-infrared or synthetic iris subsets spanning close-range, lamp variation, twins, distance, large-scale, and synthetic recognition.

Human CASIA2 anterior-segment OCT repeatability measurements.

Human anterior-segment OCT keratometric-astigmatism measurements.

601 fundus images in 4 classes: Normal, Cataract, Glaucoma, and Retina Disease. Intended for ocular disease classification.

Human cataract-surgery biometry and clinical outcome measurements.

Bilateral LenStar biometrics from a human cataract population.

101 cataract surgery videos with 10-phase workflow annotations. Canonical older cataract benchmark.

1000 cataract surgery videos from multiple surgeons annotated for 10 surgical phases, instrument segmentation, and tool presence detection. First large-scale cataract surgical video dataset.

3,000 cataract surgery procedures, 1,134.2 hours of video with phase annotations, instance segmentation, tracking, and skill scoring. Largest public cataract-surgery-video resource.

50 cataract surgery videos (>9 hours total) with frame-level annotations of 21 surgical tools. Earlier and larger sibling to Cataract-1K.

50 annotated 3D SD-OCT volumes (7,050 B-scans, 640×385 px) from subjects with vitreomacular adhesion (VMA, 25 eyes) and vitreomacular traction (VMT, 25 eyes). Each volume: 141 B-scans over 2×7×7 mm. A

The 8,697-image fungal-keratitis dataset has explicit classification and segmentation splits and is directly usable for translational corneal imaging.

Single-cell transcriptomes, organoid time series, and human retinal-periphery ischemia series from Functionally intact human retina and light-responsive human retinal organoids.

Central retinal vessel-trunk and OCT-related measurements in open-angle glaucoma eyes.

Fundus photographs and segmentation masks for subretinal fluid in central serous chorioretinopathy, with healthy-eye classification controls.

1,345 fundus images captured across multiple camera manufacturers with OD/OC segmentation + glaucoma classification labels.

This 88-eye human Corvis-ST workbook directly supports corneal measurement after glaucoma therapy.

Observation-level human or human-derived measurements/signals. from Diabetic-retinopathy patients undergoing treatment.

28 fundus images with manual vessel segmentations (two annotators).

Human-derived cell experimental measurements from Human fibroblasts chemically reprogrammed into functional retinal pigment epithelium cells.

Human fundus and carotid intima-media-thickness measurements.

Human retinitis-pigmentosa WES/SNP data from eight families directly support inherited-retinal-disease analysis.

This 160-patient clinical workbook is directly relevant to ocular injury outcomes and ophthalmic epidemiology.

Eye-level device biometry measurements from Human ocular-biometry comparison study.

Observation-level source data, annotations, or signals. from Pseudoexfoliative glaucoma/syndrome and control groups are described.

Composite fundus and OCT dataset with retinal layer, retinal lesion, and macular/glaucomatous disorder markings.

Swept-source OCT volumes for AMD and DME with three-dimensional pigment epithelial detachment and intraretinal-fluid masks.

Experiment tables and scripts evaluate postural stability and optic-flow sensitivity after sight restoration from congenital bilateral cataracts.

Human/derived image or image-annotation observations. from Human ocular anterior-segment images gathered from public web sources; source-level provenance remains limited.

Multicenter uveal-melanoma gene-expression, PRAME, clinical, and metastasis-free-survival data for prognostic modeling.

100 infant eyes with 491 image pairs annotated with ground-truth control points and vessel masks. Enables pediatric / ROP-relevant fundus registration research.

Human conjunctivitis count matrices and sample metadata are direct corneal-disease biomarker data.

Fundus photographs grouped for corneal curvature prediction, with 50 images per group.

The 111-participant raw corneal endothelial dataset is direct pediatric ocular-biometric data.

Two clinical workbooks cover 72 treated eyes and directly support surgical corneal outcome evaluation.

Human corneal-nerve measurements in Parkinson disease study participants.

Right-eye corneal OCT and rotating Scheimpflug tomography data with MATLAB code for automatic corneal-layer segmentation.

Observation-level human or human-derived measurements/signals. from 2,545 patients without corneal disease (5,074 eyes).

Orbscan corneal topography maps and structured clinical annotations for keratoconus detection.

Image-level conjunctival-pallor observations with anemia-related target from Conjunctival photographs of children aged 6-59 months presenting at assigned Ghanaian health facilities.

The 32-eye CRVO tortuosity/VEGF table is direct human retinal vascular disease data.

187 cataract cases with color fundus images and paired professional cataract-grading diagnostic reports. Designed for medical multimodal-LLM evaluation.

Observation-level source data, annotations, or signals. from Source explicitly describes consenting human subjects and 720 unique irises.

Human POAG genotype observations.

Eye-movement sequences and supporting code from Human fixation/eye-movement experiment, as stated by the linked study title.

The 132-participant retinal-artery-occlusion multi-omics release is directly translational and contains data beyond its analysis code.

Observation-level human or human-derived measurements/signals. from Diabetic-retinopathy patients.

Participant/eye-level visual-acuity and contrast-sensitivity measurements from Subjects wearing high-addition multifocal contact lenses for myopia-progression control.

Observation-level source data, annotations, or signals. from Patients with Stevens-Johnson syndrome/toxic epidermal necrolysis are described.

Observation-level human or human-derived measurements/signals. from Glaucoma patients with repeated visual-field observations.

Participant/eye-level raw visual-function measurements from Human phakic-IOL study participants undergoing visual-function testing.

Observation-level source data, annotations, or signals. from Study reports human subjects with vision-degrading vitreopathy.

Participant-level neurophysiologic and ophthalmic outcome measures from Patients diagnosed with hematologic cancer assessed for chemotherapy-related cognitive impairment.

Observation-level source data, annotations, or signals. from Source describes de-identified conjunctival swab observations from ophthalmic patients.

Observation-level source data, annotations, or signals. from Ten patients with Stargardt syndrome and ten healthy controls are described.

Observation-level human or human-derived measurements/signals. from Pseudophakic open-angle-glaucoma eyes.

Official Dryad deposit of source-described tabular ophthalmic data for the associated study.

Official Dryad deposit of source-described tabular ophthalmic data for the associated study.

Official Dryad deposit of source-described tabular ophthalmic data for the associated study.

Official Dryad deposit of source-described tabular ophthalmic data for the associated study.

Official Dryad deposit of source-described tabular ophthalmic data for the associated study.

Official Dryad deposit of source-described tabular ophthalmic data for the associated study.

Human/derived image or image-annotation observations. from 16 human participants, both eyes.

Fifty OCT and fundus images with healthy/glaucomatous labels and cup-to-disc ratio annotations by ophthalmologists.

Sample-level mass-spectrometry metabolomics measurements from Plasma measurements from people with primary angle-closure glaucoma, as stated by the linked study title and source description.

Image-level ultrasound observations with characterization target from Multicentre transorbital ultrasound imaging of human optic nerves, as stated by the dataset/paper title.

Observation-level human or human-derived measurements/signals. from Children completing a two-year orthokeratology/atropine trial.

Observation-level human or human-derived measurements/signals. from 110 chemical-burn patients (155 eyes) in Tashkent.

Participant-level osdi, schirmer, and tear-film-breakup measurements from Healthy adult computer users and contact-lens wearers without dry-eye symptoms.

Participant-level myopia, exposure, and covariate analytic measurements from Human NHANES 2003-2008 participants, as explicitly stated by the source description.

12522 fundus images with DR grading (0-5) and lesion-level segmentation annotations.

Observation-level source data, annotations, or signals. from Source describes OCT-based refractive-error prediction, consistent with human clinical imaging; confirm population wording at addition.

2,000 regular fundus images (500 patients × 2 fields × 2 eyes) plus 256 ultra-widefield fundus images labeled for DR severity (ICDR grades 0-4) and image quality assessment (gradable/ungradable). From

15,709 fundus images with paired medical reports and extracted keywords. Only public fundus report-generation dataset — useful for VLM / captioning evaluation.

Patient-level demographic and clinical tabular observations from Patients with acute ocular burns presenting at two South Indian tertiary eye-care centres during 2016-2020.

Official Dryad deposit of source-described tabular ophthalmic data for the associated study.

Fundus-image-level erm observations/labels from Retrospectively collected colour-fundus photographs from patients diagnosed with epiretinal membrane at B&VIIT Eye Center, Seoul.

Observation-level human or human-derived measurements/signals. from 104 eyes with advanced proliferative diabetic retinopathy in randomized trial.

The human diabetic retinal-capillary case-control measurements directly support retinal vascular analysis.

The 413-patient diabetic-retinopathy/macular-edema table is direct human ophthalmic clinical data.

The 17-participant optic-neuritis psychophysics archive is a direct human visual-function evaluation resource.

Observation-level human or human-derived measurements/signals. from Red blood cells from glaucoma patients and healthy controls.

Fundus-image-level dme class labels and etdrs-guided annotations from Fundus imaging for diabetic macular edema; human clinical image provenance is inherent to the stated DME dataset.

Synthetic visible-spectrum ocular biometric morph images generated from documented human VISOB source imagery.

174 OCTA images for DR lesion segmentation (IRMA, NPA, NV), image quality assessment, and DR grading (3-class).

Fifty color fundus images with expert markings of diabetic retinopathy lesions, blood vessels, optic disc, and macula.

110 color fundus images with optic-disc contour annotations by two experts. Foundational OD-segmentation dataset.

101 fundus images annotated for optic disc and cup segmentation by 4 clinicians. Train/test: 50/51.

Forty color fundus photographs from a diabetic retinopathy screening program, divided into 20 training and 20 test images, with vessel reference annotations and field of view masks.

3,100 paired two-field fundus images with DR grading labels. Only public two-field paired DR benchmark.

Dry-eye clinical, tear, and ocular-surface molecular data directly support human ocular-surface disease analysis.

Participant-level questionnaire/repeatability measurements from Child participants completing dry-eye symptom assessment.

Human ocular-biometry measurements from dual Scheimpflug and swept-source OCT instruments.

Twenty OCT volumes with 220 selected B-scans from eyes with non-neovascular AMD, drusen, and geographic atrophy, including manual and automated pathology markings.

Human and human-derived paired retinal OCT images used to study sparse acquisition, denoising, interpolation, and reconstruction in healthy and non-neovascular AMD eyes.

110 OCT B-scans from 10 DME subjects with 8 layer boundaries and fluid region annotations by 2 clinicians.

OCT data from 384 subjects, including 269 with AMD and 115 normal subjects, with 38,400 B-scans and derived total retina and RPE-drusen complex thickness measurements.

Forty-five retinal OCT volumes acquired with a Spectralis system: 15 dry AMD, 15 diabetic macular edema, and 15 normal volumes. The official Duke release provides the study data.

463 color fundus images with pixel-level segmentation: 82 with exudate (EX) + 381 with microaneurysm (MA) annotations. Standard DR lesion-segmentation benchmark.

Pediatric external-eye photographs with gaze-view annotations, corneal masks, eyelid/eyelash-line keypoints, and clinical tabular parameters for astigmatism-related research.

Observation-level human or human-derived measurements/signals. from Human nasal-orbital mesenchymal stem cells.

Official Dryad deposit of source-described tabular ophthalmic data for the associated study.

Observation-level human or human-derived measurements/signals. from Four human participants.

5,381 B-scan ocular ultrasound video clips with retinal-detachment presence and macula-on/off status labels. Total runtime approximately 5 hours 10 minutes. Only public ocular ultrasound video benchma

Observation-level source data, annotations, or signals. from The Parkinson disease and healthy-control gaze study is a human visual/gaze resource.

High-resolution multi-camera face images with calibrated gaze targets, extreme head poses, and varied illumination.

Observation-level human or human-derived measurements/signals. from 22 pemphigus/pemphigoid patients and 21 controls.

Eye-level one-year refractive, visual, and rotational-stability outcomes from Cataract patients implanted with the double-loop haptic toric IOL.

Observation-level human or human-derived measurements/signals. from Six inherited-macular-disorder patients and three healthy relatives from Japanese families.

Official Dryad deposit of source-described iris biometric data for the associated study.

External eye photographs curated from publicly available web sources for binary classification of referable blepharitis versus normal.

Five hundred forty-seven smartphone eye photographs with conjunctiva masks annotated independently by two annotators.

Original and augmented eye-disease image dataset covering retinitis pigmentosa, retinal detachment, pterygium, myopia, macular scar, glaucoma, disc edema, diabetic retinopathy, central serous choriore

Raw and processed eye-tracking data from glaucoma patients with asymmetrical visual-field loss during free viewing.

Questionnaire and clinical eye-screening data from first-year university students in Ghana.

~102K VQA pairs derived from 58,485 images across 8 ophthalmic modalities (fluorescein angiography, ICGA, OCT, CFP, ultrasound biomicroscopy, slit-lamp, fundus auto-fluorescence, CT) covering 100+ dis

Visual-field data from glaucoma home monitoring: mean deviation, duration, and pointwise differential light sensitivity values across HFA and Eyecatcher tests.

~88,000 fundus images graded 0–4 for DR severity. Largest public DR dataset; competition images from EyePACS clinics.

10,000 scanning-laser ophthalmoscopy fundus images paired with de-identified clinical notes, visual-field measurements, glaucoma labels, and demographic attributes.

Wide-field fundus images from premature infants for ROP staging (Stages 1–5 + Plus Disease). Expert-annotated for AI-assisted ROP diagnosis and screening.

Clinically validated color fundus photographs from routine ophthalmic examinations with expert disease annotations.

Fundus fluorescein angiography images paired with Chinese and translated English reports for report-generation research.

Observation-level source data, annotations, or signals. from Healthy controls at a university eye hospital are explicitly stated.

A set of 2,246 fundus images with continuous mean opinion scores from 0 to 100, three quality grades, and the individual scores of six ophthalmologists.

129 fundus images from 39 patients forming 134 registration pairs with anatomical ground-truth control points. Only public registration benchmark for ophthalmology.

800 high-resolution (2048x2048) fundus images with pixel-wise vessel segmentation. Covers normal, DR, AMD, glaucoma.

SD-OCT B-scans with bounding-box and polygon annotations for paracentral acute middle maculopathy lesions.

40 patients with paired pre-operative fundus images and intra-operative biomicroscopy video clips. Annotated for optic disc and vessel segmentation across domains.

Observation-level source data, annotations, or signals. from Source describes human foveolar cone observations.

Fundus photography, multispectral and functional retinal imaging, retinal blood-flow and pupillary-light videos, retina-characteristic labels, quality labels, demographics, and psychological assessmen

Repeated light/dark SD-OCT acquisitions and retinal reflectivity profiles from healthy, neuromyelitis-optica, and Alzheimer groups.

1,099 pediatric fundus images from 483 premature infants annotated for retinopathy of prematurity (ROP) staging. Standard fundus (RetCam) — not ultra-widefield; `rop_uwf_intelligent` is retained as th

Fundus-image-level class-labelled observations from Classified human fundus images for myopia, choroidal neovascularization, tessellation, and normal categories.

Seventy retinal image pairs with visible myopia development and manually annotated corresponding control points.

Twelve human fundus-image sequences are a direct ocular imaging resource for venous-pulsation measurement.

Fundus-focused text dataset for LLM/RAG workflows.

100 high-resolution color fundus images with pixel-wise artery / vein / crossing labels from a mixed disease cohort.

Large fundus-related multilingual text corpus for LLM pretraining or retrieval.

1020 fundus images with binary glaucoma labels (697 normal, 323 glaucoma), plus optic disc/cup annotations.

Indoor and outdoor panoramic-camera recordings with continuous three-dimensional gaze labels across wide head poses and distances.

Crowdsourced iPhone and iPad face videos with screen-fixation coordinates for appearance-based mobile gaze estimation.

Optic-nerve diffusion-MRI assessment data directly support ischemic optic-neuropathy classification.

Official Dryad deposit of source-described tabular ophthalmic data for the associated study.

Systemic mitochondrial-function measurements are directly linked to human glaucoma and LHON disease mechanisms.

De-identified per-patient glaucoma fundus/OCT images with processed labels and annotated spreadsheet.

Eye-level demographics, clinical measurements, and SD-OCT-derived macular ganglion-cell-complex thickness for glaucoma assessment.

SLO, circumpapillary OCT, and visual-field pattern-deviation maps with four-class glaucoma labels.

300 circumpapillary OCT images. RNFL/GCIPL/choroid layer segmentation plus binary glaucoma classification.

263 eyes × 1,115 visits. Multi-modal: VF (HFA 24-2), fundus photographs, OCT RNFL, IOP, CCT. Labels: VF progression, OD segmentation, glaucoma stage.

1,000 patients with OCT RNFLT maps (225×225), visual field measurements, and demographics for glaucoma detection (binary) and longitudinal progression forecasting (6 definitions). First public glaucom

Fundus images for glaucoma detection from Harvard Medical School / Mass Eye and Ear. Binary glaucoma classification.

30,000 subjects (10K each AMD, DR, glaucoma) with paired SLO fundus and OCT B-scans, demographic attributes (race, ethnicity, gender, language), for fairness analysis.

HD-OCT scans and clinical outcome variables for macular-hole visual-improvement prediction after surgery.

A collection of 169 fundus photographs with expert exudate and bright lesion annotations, clinical metadata, optic nerve locations, vessel estimates, and image quality scores.

Time-series bright-field imaging of human embryonic-stem-cell-derived retinal organoid aggregates.

Human embryonic-stem-cell-derived RPE electrophysiology data.

4,011 color fundus images labeled for high-myopia vs pathological-myopia classification — largest public dataset for HM/PM separation.

Observation-level source data, annotations, or signals. from Human pluripotent stem cell-derived photoreceptors are explicitly stated.

45 high-resolution fundus images (healthy/DR/glaucoma) with manual vessel segmentation.

Phase-contrast microscopy fields of cultured human conjunctival goblet cells with semantic and instance-compatible masks.

Counts and metadata for 22 people form a directly translational human keratitis transcriptomics resource.

The 28-eye human adaptive-optics archive is directly reusable for foveal cellular imaging and biometric measurement.

Observation-level source data, annotations, or signals. from Human foveal cone topography and fixation locations are explicitly stated.

Human/derived image or image-annotation observations. from Preterm infants screened at H.V. Desai Eye Hospital.

High-resolution fundus images from Hillel Yaffe Medical Center for age-related macular degeneration diagnosis.

Synchronized human eye-tracking, webcam eye images, facial landmarks, and gaze annotations.

747 fundus images from 288 patients with glaucoma labels confirmed by paired OCT + visual field. First public dataset with gold-standard multimodal glaucoma confirmation.

400 training fundus images with AMD classification (non-AMD vs AMD) and lesion annotations. Challenge dataset from ISBI 2020.

The large Indian cataract/UV exposure survey is direct human ophthalmic epidemiology data.

Single-cell multi-omics and organoid-derived cell measurements from Human neural retinal stem-like cells, isolated using human retinal/organoid experimental methods.

Four exome difference files for three congenital-glaucoma families are directly translational human ocular genetics data.

516 fundus images with DR grade (0-4), macular edema grade (0-2), and pixel-level lesion segmentation for 81 images.

Image and symptom dataset for normal, uveitis, conjunctivitis, cataract, and eyelid-drooping classification, with source-reported SMOTE balancing to 649 images per class.

Retinal-image montages, cone annotation maps, and participant-level supporting measurements from In-vivo human foveolar imaging; individual-participant MATLAB files are stated.

The 42-participant UV-transmission workbook is direct human ocular-optics measurement data.

The anonymized 7,802-eye human AMD CSV is a clearly defined long-term ophthalmic survival resource.

Retinal-location/eye-level rnfl thickness measurements from Human circumpapillary RNFL measurements from the study population.

The 42-eye pediatric optical-quality workbook is directly usable for ocular-biometric measurement and repeatability evaluation.

Retinal fundus dataset for five-class diabetic-retinopathy grading.

Individual human iris-feature records are directly reusable for iris biometrics and phenotype classification.

The named CSV and README form a direct human retinal OCT biomarker resource.

Subject/eye-level full-field erg amplitude and peak-time measurements from Healthy volunteers and clinical-reference subjects at two centres.

9,939 color fundus images from Japanese patients with DR grading labels (Davis grading scale).

Multi-modal retinal vessel segmentation dataset spanning fluorescence angiography, fundus autofluorescence, and infrared imaging.

1,000 fundus images spanning 39 ophthalmic disease categories from the Joint Shantou International Eye Center. Used for multi-class fundus disease classification.

101,442 gradable fundus images labeled as referable (RG) or non-referable (NRG) for glaucoma. Image data from EyePACS LLC; labels from Rotterdam Eye Hospital expert graders.

Karachi cataract-surgery quality data are direct human ophthalmic population outcomes.

Small corneal confocal fluorescence imaging dataset for keratoconus epithelium analysis.

Corneal map images for three-class keratoconus detection.

~84,000 retinal OCT B-scan images across 4 classes: CNV, DME, DRUSEN, NORMAL. Train: ~83,484 / Test: 1000.

11,760 fundus images with glaucoma classification labels and ophthalmologist-derived attention maps. Largest public glaucoma dataset with attention ground truth.

Text/tabular dataset supporting readability and language-access analyses in ophthalmology.

Light-adapted electroretinogram and oscillatory-potential waveform dataset from 253 pediatric participants, with structured JSON, tabular metadata, and electrode-position eye images.

The 131-participant longitudinal lens-fluorescence workbook is core human ocular biometrics data.

High-speed head-mounted eye-region videos with pupil-center annotations under varied indoor, outdoor, eyewear, and lighting conditions.

The 2,049-surgery cataract outcome file is direct human ophthalmic care data.

Anonymized retinal fundus images from an ophthalmology clinic in M'Sila, Algeria for diabetic-retinopathy classification.

198 fundus images (from MESSIDOR) with pixel-wise segmentation for 10 biomarkers (lesions + structures) + DR and ME severity grades.

~30,000 longitudinal OCT B-scans across multiple patient visits, annotated for AMD change detection and progression monitoring.

5,164 fundus images from 1,291 patients captured with the Phelcom Eyer handheld smartphone-based fundus camera. Labels for DR grading + clinical/demographic prediction.

6,272 AS-OCT images + 392 anterior-segment photographs for corneal opacity assessment with expert grading. First large public multimodal AS-OCT + photo dataset for cornea.

1748 fundus images with DR grading (0-3 Retinopathy Grade) and macular edema risk (0-2).

34,452 fundus images from 4,344 patients across multiple fields per eye, with DR screening labels. Largest public four-field DR dataset.

One thousand infrared meibography images with meibomian-gland masks, eyelid masks, and six rounds of expert meiboscore grading.

Human tissue transcriptional and microbiome measurements from Orbital tissue from people with Graves' orbitopathy and relevant human microbiome samples.

The Moorfields nAMD fellow-eye dataset is direct human retinal-disease longitudinal outcome data.

Anonymized clinical metadata and automated 3D OCT segmentation volumes for neovascular age-related macular degeneration.

Longitudinal quantitative OCT biomarkers and treatment-response variables for predicting visual acuity in neovascular AMD.

Longitudinal laptop-camera images captured during natural daily use with gaze targets, face geometry, and normalized views.

Human clinical ocular-manifestation data from four South-Kivu health zones.

Pentacam-derived corneal tomography variables for intraocular-lens and corneal subtype modeling.

Multi-source heterogeneous retinal fundus image-quality assessment dataset for training and evaluating quality-control models.

A multicenter collection of 186 minimally invasive glaucoma surgery (MIGS) videos with annotations for surgical-phase recognition and semantic segmentation of instruments and anatomical structures.

1,693 color and 1,739 infrared ocular-surface images from five clinical centers with pixel-level tear-meniscus segmentation. First multi-center dry-eye imaging benchmark.

Observation-level source data, annotations, or signals. from Source explicitly identifies 3,000 unique patients.

The 270-eye glaucoma visual-field dataset directly supports prognosis and progression analysis.

Public sample fundus photographs and measurements for modeling myopic regression after corneal refractive surgery.

Observation-level human or human-derived measurements/signals. from 50 cataract patients (100 eyes).

Tobii Pro Glasses 3 natural-scene viewing recordings with gaze, IMU, event, video, and snapshot files.

Longitudinal near-infrared iris images with subject, eye, age, sex, and ethnicity metadata used in ICE iris-recognition evaluations.

Retinal OCT B-scans from Noor Eye Hospital for classification of Normal, Drusen, and CNV (choroidal neovascularisation) cases. 16,822 B-scans from 441 eyes (Normal 120 / Drusen 160 / CNV 161 eyes).

Eye-level treatment and intraocular-pressure outcome measurements from Retrospective human cohort of goniotomy-treated and goniotomy-naive eyes.

The documented Nigerian cataract-service survey is direct human ophthalmic epidemiology data.

Observation-level source data, annotations, or signals. from Source describes clinical slit-lamp images for nuclear cataract classification.

The 1,384-eye high-myopia database is a directly reusable human macular clinical cohort.

A collection of 640 retinal OCT images with expert choroidal region annotations for choroid segmentation.

Linked color fundus and macular OCT images for diabetic macular edema and diabetic retinopathy classification, with CSV labels and shared patient/eye/image nomenclature.

35 Spectralis OCT volumes (1,715 B-scans) with 9 manually delineated retinal layer boundaries. 14 healthy controls, 21 MS subjects.

A set of 1,110 optic nerve head OCT volumes from 624 patients, including 847 scans with primary open angle glaucoma and 263 healthy scans.

1,672 OCT B-scans from AMD, DME, and healthy controls with 5,016 multi-grader layer annotations + lesion detection labels.

A derived OCT angiography resource with 640 coronal PNG views for each of 129 subjects: 90 normal, 29 diabetic retinopathy, 5 AMD, and 5 choroidal neovascularization cases.

500 subjects with OCTA volumes, vessel segmentation, FAZ (foveal avascular zone) annotations, and layer segmentation. Largest public OCTA dataset.

198 annotated 3D SD-OCT volumes (3,762 B-scans) with pixel-level labels for 13 anatomic and pathological retinal features: retina, choroid, vitreous, RPE, hyaloid, ERM, fluid, subretinal material, hyp

2,000+ OCT images labeled for 7 conditions: AMD, DME, ERM, NO (normal), RAO, RVO, VID.

500 OCT images: NORMAL (206), AMD (50), CSC (128), DR (59), MH (57). High-resolution B-scans for 5-class classification.

Anonymized South Korean cohort clinical, serologic, electrophysiologic, thymic, and treatment data.

Observation-level source data, annotations, or signals. from Cataract surgery data imply human clinical observations; confirm consent context at addition.

Human/derived image or image-annotation observations. from Human ocular-neoplasm cases are indicated by clinical and histopathology images.

Per-patient ocular-surface AMR counts and metadata are direct human keratitis translational data.

Observation-level source data, annotations, or signals. from Patient and non-diseased control groups are stated.

844,000 simulated patient-physician dialogue rows generated from AREDS clinical visits. Enables ophthalmic dialogue and counseling VLM training.

16,530 ultra-widefield fundus images from 8,405+ patients (age 0–90) annotated for 38 ophthalmic diseases and 67 fundus features. Released alongside the FairerOPTH study on sexism and ageism in ophtha

8000 patients (16000 fundus images, left + right eye) with 8 disease labels for multi-label ocular disease classification.

3,859 OCT B-scan images (125 eyes, 119 patients) for macular hole segmentation. Each PNG is side-by-side: left half raw B-scan, right half colour-coded mask for 4 classes: Retina, Macular Hole, Intrar

Longitudinal OCT + fundus dataset from AMD/DME patients across multiple clinical visits. 9,408 OCT B-scans have biomarker labels for 8 categories (fluid, drusen, scarring, PED variants, etc.); 78,000+

The de-identified 8,174-eye Moorfields AMD CSV is an explicitly released human longitudinal outcome resource.

700 Optos ultra-wide-field fundus images with multi-disease classification labels and image-quality flags from real-world clinical practice.

Cropped periorbital images with multi-structure masks for the iris, sclera, eyelid, caruncle, and eyebrow.

Large-scale multi-procedure ophthalmic surgical video dataset covering 66 surgery types, 102 phases, 150 operations (~285 h). 1,969 untrimmed videos; 17,508 trimmed operation-level clips; 14,674 trimm

162,185 video clip-instruction pair samples from 9,819 ophthalmic surgical videos, covering multiple procedure types. Designed for text-guided surgical video generation and understanding. Published at

Observation-level source data, annotations, or signals. from Source describes ocular/facial anthropometry in Malawian participants aged 6-25.

Observation-level human or human-derived measurements/signals. from Hospital-based stroke survivors.

Ophthalmology-focused PubMed text corpus for retrieval, pretraining, or RAG experiments.

Russian-English ophthalmology sentence-pair and glossary dataset for translation and LLM evaluation.

Text-only ophthalmology explanatory/free-form question-answering dataset for LLM training/evaluation.

Text-only ophthalmology multiple-choice question-answering dataset for LLM training/evaluation.

Ophthalmic visual question-answering benchmark dataset released as supplementary data for evaluating multimodal language models in ophthalmology.

Ophthalmology-oriented WeChat article metadata and image-link dataset for visual question answering and multimodal language-model evaluation.

Oct image-level disease/normal observations from OCT images labelled as proliferative vitreoretinopathy, uveitis, and normal eyes imply clinical human eye imaging.

High-resolution swept-source OCT images and mechanical-model data for outer retinal corrugations in rhegmatogenous retinal detachment.

Paired tabletop and portable retinal images from the same patients, enabling cross-device domain-adaptation research.

1200 fundus images for pathologic myopia classification and optic disc / lesion segmentation. 50 % PM / 50 % non-PM.

488 fundus images from 244 patients (both eyes). Expert OD/OC segmentation, glaucoma stage, IOP, and clinical metadata.

757 color fundus images from a Paraguayan cohort with 7-class DR grading labels. Adds Latin-American representation.

Processed outer-retinal thickness and reflectance measurements from a Parkinson disease directional-OCT study.

Retinal structure, electrophysiology, and visual-perception measurements from Parkinson disease and comparison participants.

Paired color-fundus/OCT images with expert MNV subtype labels and treatment-response follow-up.

The pediatric secondary-IOL spreadsheet is a defined direct clinical ophthalmic outcome object.

Transient pattern electroretinogram responses from 304 subjects in 336 records with clinical metadata.

Human eye-tracking observations from a visual-preference study.

The defined plane-wave ultrasound/OCTA data file and README directly support human ocular vascular measurement.

Observation-level human or human-derived measurements/signals. from Patients with ocular disease, including POAG context.

Fourteen thousand nine hundred seventy-six near-infrared ocular images for eye-state detection and coarse gaze-direction classification during ophthalmic measurement workflows.

De-identified human glaucoma-surgery clinical records with postoperative ptosis and strabismus outcomes.

15 ultra-widefield (Optos) fundus images with pixel-level vessel segmentation ground truth.

Processed human OCT/OCTA data including segmentations and ETDRS-grid materials.

Observation-level human or human-derived measurements/signals. from Vitreous from two AIR patients and three macular-hole controls.

Human synchronized pupillometry, EEG, and fMRI salience measurements.

Pediatric ultra-widefield fundus images with professional artery-vein segmentation annotations.

A human corneal confocal microscopy dataset containing 410 source images from 88 participants, 410 filename-matched pixel-level nerve segmentation masks, 20 repeat annotations, and image-linked clinic

Observation-level source data, annotations, or signals. from Source explicitly identifies 22 people with and without proliferative retinopathy.

The named longitudinal OCT measurement CSV covers 2,115 treated AMD eyes and fits core clinical OCT progression analysis.

148 Heidelberg Spectralis SD-OCT volumes (~4,254 B-scans) for 3-class volume-level classification: Normal (50 volumes), AMD (48 volumes), DME (50 volumes). Variable B-scans per volume: 19, 25, 31, or

RAVI cataract-surgery outcomes are direct human ophthalmic population data.

42 infrared reflectance fundus images with separate artery and vein segmentation masks. 23 train / 19 test.

Observation-level source data, annotations, or signals. from Human retinal organoids are explicitly stated.

Fundus-image benchmark with retinal vessel branching-angle annotations for evaluating branching-angle detection and measurement algorithms.

One hundred twenty paired low quality and high quality clinical fundus photographs of the same eyes at 2560 by 2560 pixels for image restoration and enhancement research.

Observation-level source data, annotations, or signals. from MESSIDOR is a human retinal-image benchmark; this deposit adds lesion-localization data.

Observation-level source data, annotations, or signals. from Schoolchildren in Blantyre are explicitly described.

2000 fundus images for glaucoma classification, optic disc/cup segmentation, and fovea localisation. Extends REFUGE1.

Fundus images and age labels for retinal age prediction and regression.

Human/derived image or image-annotation observations. from 20 individuals without retinal disease.

Fundus-image-level vessel-segmentation data from Retinopathy-of-prematurity retinal images; human infant provenance is inherent to the stated ROP source.

Baseline and two-year follow-up color fundus image pairs from Tianjin Medical University for diabetic-retinopathy progression research.

6,004 pediatric RetCam fundus images from 188 newborns in Ostrava (Czech Republic), annotated for retinopathy of prematurity (ROP) screening + classification.

~24,000 retinal OCT images across 8 disease classes: AMD, BRAO, BRVO, CSC, CRAO, CRVO, DME, MH.

Human retinal optic-flow and locomotion observations.

Human retinal photoplethysmography and retinal-nerve-fiber-layer measurements.

112 OCT volumes from three vendors (Cirrus / Spectralis / Topcon) with pixel-level segmentation of intraretinal fluid (IRF), subretinal fluid (SRF), and pigment epithelium detachment (PED).

3200 fundus images annotated for 45 retinal conditions. Used for multi-label disease classification.

750 fundus images with optic disc and optic cup segmentations from 6 ophthalmologists per image. Multi-rater benchmark.

485 fundus images (313 normal, 172 glaucoma) with optic disc region of interest crops for deep learning.

Clinical records combining retinal nerve fiber layer, visual-field, corneal-thickness, and intraocular-pressure features.

100 fundus images with microaneurysm annotations from the Retinopathy Online Challenge.

Grand Challenge OCT classification dataset for diabetic-retinopathy related OCT classification.

Observation-level source data, annotations, or signals. from Source identifies serum metabolomic data from infants with retinopathy of prematurity.

The ROP Doppler examination table is a defined direct neonatal retinal measurement resource.

Color fundus photographs paired with biological metadata and structured descriptions for retinopathy of prematurity.

229 OCTA images (ROSE-1 + ROSE-2) with pixel-level retinal vessel segmentation ground truth.

The paired FASTQ files represent a defined human RPGR cone-rod-dystrophy sequencing object.

3,012 OCT B-scans from 146 eyes / 130 patients with retinal vein occlusion. Dual-task labels: fluid segmentation + retinal-layer segmentation. Detection of macular lesions.

Human-derived ocular cell experimental measurements from Human adult donor-eye cells and hESC-derived ocular lineages.

Observation-level human or human-derived measurements/signals. from Keratoconus, post-laser ectasia, PMD and control participants.

Small-incision cataract surgery video dataset with train/validation/test video archives for phase-recognition research.

Official Dryad deposit of source-described ocular omics data for the associated study.

Slit-lamp photographs with expert epiphora-severity labels.

~2,617 annotated slit-lamp frames covering anterior-segment anatomy + multi-lesion detection (cataract, corneal disease, conjunctivitis).

Anonymized slit-lamp photographs with English clinical annotations and vision-language conversations.

Official Dryad deposit of source-described tabular ophthalmic data for the associated study.

Longitudinal OCT angiography projection maps with vessel labels, clinical text, and treatment/follow-up groupings.

Human pupil and light-exposure measurements.

20 fundus images with manual vessel segmentation (two annotators).

The 33-proband Stargardt variant table is a direct inherited-retinal-disease genomics resource.

Restricted corneal confocal microscopy image set with pixel-level corneal-nerve masks annotated for high-precision segmentation.

Observation-level source data, annotations, or signals. from Adult dupilumab-treated patients with ocular adverse events; paired conjunctival-impression samples at baseline/follow-up.

Official Dryad deposit of source-described visual-field and retinal measurement data for the associated study.

Human corneal-ulcer clinical images and labels.

1,219 color fundus images with DR severity grading + pixel-level exudate segmentation masks. Multi-center (SUSTech + Sun Yat-sen University).

Synthetic circumpapillary OCT images for healthy and glaucomatous eyes with retinal-layer masks and RNFL thickness values.

Retinopathy-of-prematurity fundus-image dataset and synthetic-image resources for privacy-preserving AI training.

The 103-patient ten-year AMD outcome CSV is a clearly defined human survival-analysis resource.

Observation-level human or human-derived measurements/signals. from Glaucoma and healthy human participants.

Head-mounted eye images with pupil, iris, eyelid, eyeball, gaze, landmark, segmentation, and eye-movement annotations.

The 2,006-participant original-data workbook is directly relevant to human cataract epidemiology and prognosis.

Observation-level human or human-derived measurements/signals. from School-aged children in one-hour smartphone-gaming intervention.

Observation-level human or human-derived measurements/signals. from 28 cataract patients (56 eyes) after trifocal IOL implantation.

A collection of 1,800 preprocessed retinal OCT B-scans, with 600 images each for AMD, diabetic macular edema, and normal retina.

External ocular photographs of thyroid eye disease collected from web sources, with surgery-related images removed by the source curator.

10 Heidelberg Spectralis SD-OCT volumes (510 B-scans, 496×644×51 voxels) from healthy subjects with 8 retinal layer boundary annotations by 2 independent observers. MATLAB .mat format; used as the OCT

Official Dryad deposit of source-described tabular ophthalmic data for the associated study.

T2-weighted orbital MRI volumes with multi-organ segmentation labels (extraocular muscles, optic nerve, lacrimal gland, orbital fat) and paired clinical data. First public orbital MRI benchmark for th

Human toric-IOL surgical outcome table directly supports cataract-surgery outcome analysis.

Participant-level ocular and clinical measurements from Korean nationwide cross-sectional human study; source text states ocular measurements used to model sarcopenia risk.

Fundus photographs for ocular toxoplasmosis detection: active toxoplasmosis, inactive (scarred) lesions, and normal. ~412 images total (adult + pediatric cases).

Portable fundus images and segmentations for retinal microvascular network analysis.

13,047 ultra-widefield fundus photographs (Optos, 200° FOV) from Tsukazaki Hospital, annotated with 8 binary disease labels: AO, AMD, DR, Glaucoma, MH, RD, RP, RVO. Associated with Scientific Data 202

Clinically acquired retinal OCT images for AMD, DME, rhegmatogenous retinal detachment, and normal classification.

Ophthalmoscopy image/measurement data plus processing software from Exemplary two-photon fluorescence ophthalmoscope recordings from a healthy subject's eye.

The human uveitis expression workbook has a stated 103-enrollment cohort and supports ocular biomarker classification.

Visible-light iris images captured at a distance and on the move with realistic blur, reflection, occlusion, pose, and illumination noise.

600 Spectralis OCT B-scans from 24 exudative AMD subjects. Three fluid region classes: IRF, SRF, PED. Dual expert annotation.

Fundus and synthetic OCTA vessel-segmentation resource for domain-transfer research.

The 536-person eye-care quality-of-life dataset is directly usable for human ophthalmic service evaluation.

The prospective multicentre uveitis vitreous biomarker table is direct human ocular disease data.

Ultra-widefield fundus photographs for diabetic retinopathy grading (5-level ICDR scale). Released alongside the Reasoning-Enhanced VLM paper for interpretable UWF DR detection. Related to the UWF4DR

1,630 Optos ultra-wide-field fundus images from 809 patients graded for diabetic retinopathy (5-class ICDR) by senior ophthalmologists.

2,031 ultra-widefield fundus images for AI-assisted intraocular tumor detection and classification. Six categories: Normal, Choroidal Hemangioma (CH), Retinal Capillary Hemangioma (RCH), Choroidal Ost

28,943 HFA 24-2 visual field tests with per-point sensitivities, MD/PSD indices, glaucoma labels, and longitudinal follow-up data. Input: 52-element sensitivity array (not an image).

A multilabel fundus classification challenge with 3,435 labeled training images and 350 test images covering six disease groups and normal findings.

The four retinal-prosthesis participant dataset is a direct human device-rehabilitation resource rather than generic behavior data.

Human visual-field perception observations.

Visual-field and psychophysics experiment data for scotoma-detection comparisons.

VKH PBMC transcriptomics and proteomics are a direct translational uveitis biomarker resource.