---
title: "OCT Retinal Dataset"
description: "OCT dataset features 1,000 volumetric OCT scans (B-scans) of the retina with annotated layers, fluid regions, and clinical diagnoses, including AMD, diabetic retinopathy, and glaucoma.…"
url: "https://unidata.pro/datasets/oct-retinal-images-dataset/"
date_modified: "2025-12-09T11:14:08+03:00"
language: "en-US"
---
OCT dataset features 1,000 volumetric OCT scans (B-scans) of the retina with annotated layers, fluid regions, and clinical diagnoses, including AMD, diabetic retinopathy, and glaucoma. This DiCOM dataset supports AI model training in disease classification, pathology segmentation, and computer vision–based retinal analysis using coherence tomography images.

## Dataset Structure

### The Numbers Section

**Numbered list:**

- **Number:** 1,000 — **Text:** Scans
- **Number:** 100 — **Text:** B-scans per volume

### Tooltips Section

**Tooltip items:**

- **Name:** Medicine
- **Name:** Computer vision
- **Name:** Machine Learning
- **Name:** Segmentation
- **Name:** Classification

### Dataset Information

**Table with data:**

| Characteristic | Data |
| --- | --- |
| Description | Volumetric OCT scans (B-scans) of the retina with annotated layers, fluid regions, and clinical diagnoses |
| Data types | DiCOM |
| Annotation | Retinal layer boundaries, fluid regions, diagnosis labels (normal/AMD/diabetic/glaucoma). |
| Tasks | Recognition, classification and segmentation of pathologies, computer vision |
| Number of files | 1,000 |
| Labeling | Metadata(age, gender, device model, scan position) |

**Media Slider:**

- **Image in the slider:** ![](https://unidata.pro/wp-content/uploads/2025/04/oct-retinal-images-dataset-1.webp)
- **Image in the slider:** ![](https://unidata.pro/wp-content/uploads/2025/04/oct-retinal-images-dataset-2.webp)

### Technical Specifications

**Table with data:**

| Characteristic | Data |
| --- | --- |
| File Extension | DiCOM |
| File Resolution | Min = 512×512 px |
| Labeling Format | Json |

**Source and data collection methodology:** Source and collection methodology. Data was collected via crowdsourcing platforms.

### Dataset Use Cases - Slider

**Industry Cards:**

- **Industry:** Medical Imaging and Ophthalmology — **Title:** AI-Powered Retinal Disease Diagnosis — **Text:** *OCT Retinal Dataset* provides high-resolution retinal OCT images and tomography scans ideal for developing diagnostic tools that detect retinal diseases such as macular degeneration and diabetic retinopathy. These medical images enable ophthalmologists and researchers to build accurate disease classification systems using deep learning and computer vision models.
- **Industry:** Healthcare AI Research — **Title:** Training Deep Neural Networks for OCT Analysis — **Text:** This retinal OCT dataset is widely used in training machine learning and deep neural networks to automate retinal layer segmentation and retinal pathology recognition. The dataset’s manual annotations and OCT B-scans help improve image processing workflows and enable AI models to achieve greater precision in automated detection and clinical diagnosis.
- **Industry:** Medical Device and Software Development — **Title:** Improving OCT Imaging Systems and Algorithms — **Text:** Developers of OCT imaging systems and diagnostic software use this eye scan dataset to enhance automated segmentation and real-time analysis capabilities. It provides comprehensive training data for refining image recognition algorithms used in retinal scanners, helping manufacturers and research institutions optimize medical diagnosis tools.
- **Industry:** Academic and Clinical Research — **Title:** Benchmarking Retinal Image Segmentation Models — **Text:** This OCT dataset supports academic research and clinical studies focused on retinal structures and layer segmentation. It serves as a valuable resource for testing preprocessing methods, comparing segmentation tasks, and validating models trained on other public datasets, promoting innovation in ophthalmic imaging and retinal disease diagnosis.

### Fact

**FAQs Heading:** FAQs

**List of Questions:**

- **Question:** What is OCT Retinal Dataset used for? — **Answer:** This dataset is designed for training and evaluating machine learning models in retinal disease classification, automated segmentation, and computer vision tasks. It supports applications such as OCT layer segmentation, pathology detection, and medical image analysis for diagnosis automation.
- **Question:** What types of annotations are provided in this retinal dataset? — **Answer:** Annotations include retinal layer boundaries, fluid regions, and diagnosis labels (normal, AMD, diabetic retinopathy, and glaucoma). Each OCT image is accompanied by structured JSON metadata, supporting precise segmentation and disease classification tasks.
- **Question:** Can I request a sample of the retinal OCT dataset before purchasing it? — **Answer:** Yes. Free sample data is available for preview, allowing researchers to test data quality, annotation structure, and compatibility with their models before purchasing the dataset.
- **Question:** How are Unidata datasets stored and managed? — **Answer:** Unidata securely stores all datasets on AWS cloud infrastructure, aligned with ISO 27001 and ISO 27701 standards. This ensures data availability, reliability, and strong safeguards for sensitive or medical imaging data.
- **Question:** How long does it take to receive the dataset after purchase? — **Answer:** After submitting a request, our team will contact you to confirm details and complete the documentation process. Following payment and agreement, OCT Retinal Dataset will be delivered securely within 3–10 business days.
- **Question:** How are Unidata datasets licensed? — **Answer:** Unidata datasets follow a dual-licensing model: free samples are available for trial and testing, while full datasets are accessible exclusively through purchase. Licensing terms ensure lawful academic, research, and commercial usage.
- **Question:** Is this a real-world dataset or synthetic data? — **Answer:** OCT Retinal Dataset comprises real-world medical imaging data derived from actual retinal scans. Each image captures authentic anatomical variations, ensuring realistic training data for neural networks and medical AI research.
- **Question:** How can an OCT retinal dataset support AI-based eye disease detection? — **Answer:** An OCT retinal dataset helps AI models learn patterns associated with retinal structures and eye conditions. It supports the development of medical imaging solutions for automated disease classification, pathology detection, and clinical decision support research.

[Full list of this site's AI-readable pages](https://unidata.pro/llms.txt)