Dataset Overview
Definition：Fundus Photography and OCT Imaging Datasetis provided byChangsha Langhui Information Technology Co., Ltd.A Large-Scale Ophthalmic Imaging Database Built. Based on Fundus Photogram 300,000 Casas; the allocation cases for the two cases, as well as as the meeting meetings for both eyes and for multi-media programmes of the same eye, are pending order conformation eligible Fundus Photogramy + OCT (Optical Cooperation Tomography) to check as subjects, using the DICOM standard Raw Data Format, to keep complete sequence information, spatial geometry parameters and Metadata. Overing more than 12 cases cases, from multi-center sources, with strict Quality control; capable for mediamaging AI model training and assessed-diagnosis capacity building.
| Dataset Name | Fundus Photography and OCT Imaging Dataset |
| Total Data Volume | Fundus Photography and OCT Totaling 300,000 Cases；The allocation quantities for the two categories, and the counting methods for both eyes and multiple protocols of the same eye, are pending order confirmation (Level) |
| Imaging Modality | Fundus Photography + OCT (Optical Coherence Tomography) |
| Scan Protocol | |
| Raw Data Format | De-identified raw DICOM with full hierarchy and metadata preserved |
| Core Conditions (P0) | Diabetes retinal changes, yellow mellitus of diabetes, age-related yellow-stained variability, glaucoma optic neurode, rational prognosis, etc. |
| Extended Conditions (P1) | Retinal vein occlusion, retinal artery occlusion, optic disc edema / optic atrophy, retinal detachment / tear signs, etc. |
| Source Institution | The Sanctuary Hospital. |
| Quality Control Standards | Kappa ≥ 0.75, five-tier L1–L5 quality grading |
| Use Cases | AI model training, assisted diagnosis, radiomics research, algorithm validation |
Disease Distribution Overview
Delivery Specifications and Field Requirements
The dataset strictly follows unified delivery index requirements to ensure data quality and traceability。
Delivery & Counting：Fundus photography is counted by eye (multiple fields of the same eye in the same session count as 1 case)；OCT is counted by eye as OCT examination / Volume (the same eye with the same scanning protocol in the same session counts as 1 case)
Composition of Positive Cases：
Coverage：
Raw Data Requirements：
Field Group Coverage：Batch source and location, anonymized patient information, exam primary key, modality and body part, protocol and device, specialized fields, file hierarchy, report text, diagnostic labels, clinical context, related fields, quality and disposition
Structured Text：
Data Volume Growth Trend
2026 Frontier AI Research Progress
Domain Review：The Eye Series of AI entered the basic model age in 2025-2026, and the large-scale pre-training model made breakthroughs in multi-mission broad and small sample learning. The top-level journals Nature, Nature Medicine, The Lancet and others published several clinical-level validation studies that facilitated the progress of the Eye Series of AI from laboratory to clinical deployment.
RETFound Fundus Foundation Model
Nature, 2023-2025The DeepMind RetFund series, which provides self-supervised pre-training on millions-grade eye-floor images, reaches the expert level in the diagnosis of over 70 eye diseases and the prediction of systemic diseases.
OCT Multi-Disease AI Diagnosis
Nature Medicine, 2025OCT-based Unified Multi-Disease Diagnostic System (SUD), covering yellow-stained variability, diabetes membrane retinasis, glaucoma and other diseases, 50+eye, AUC > 0.95.
Fundus + OCT Multimodal Ophthalmic AI
Ophthalmology, 2026Multimodular AI systems for integrating eye-to-eye photographs with OCT, increasing by 12 per cent the number of single-modular diagnoses and achieving joint structural-functional assessments.
Systemic Disease Prediction from Retinal Images
Cell Reports Medicine, 2025The ophthalmic AI predicts the full-body health risks of cardiovascular diseases, diabetes, neurosis, and shows the enormous potential of retina images as "human windows".
Annotation Workflow & Quality Control
Image Acquisition & De-identification
Standardized acquisition workflow: complete data is exported directly from the devices, and patient identifiers (PHI) are removed before storage to ensure data compliance。
Initial Annotation (Specialist Physician)
Attending physicians annotate case by case against the standard, including lesion localization, morphological description, disease diagnostic labels and specialized indicators。
Review (Associate Chief Physician or Above)
Experts with the title of Associate Chief Physician or above review each initial annotation result item by item, correcting erroneous annotations and supplementing missing dimensions to ensure annotation accuracy。
Consistency Assessment
10% of samples are randomly selected and independently annotated by 3 physicians to calculate Fleiss' Kappa; below 0.Dimensions scored 75 are flagged for rework。
Quality Acceptance Checklist
License and Usage Agreement
Academic Research License
For universities and research institutions, supporting academic research related to medical AI。After signing the agreement, a de-identified data subset is provided; the source must be acknowledged：Langhui Technology DataAssetsAPI。
Commercial License
For medical device companies and AI diagnostics companies, supporting medical AI product R&D and medical device registration。Provides full datasets + custom annotation + incremental update services。
Data Compliance Statement
All images come from legally authorized sources; PHI fields are fully de-identified and contain no information that can directly identify an individual, in compliance with the Personal Information Protection Law and the Data Security Law。
Customized services
Supports extended requirements such as adding specific disease types, multimodal annotation expansion, and custom training of AI-assisted diagnostic models。
Quick Facts
AI Frontier Research
The Eye Series of AI in 2025-2026 entered the basic model phase, with multiple-modular self-monitoring learning performing excellently in a number of benchmark missions, and several top-level journal papers contributed to the development of clinical AI diagnostics.