harvardairobotics/Harvard-GD

---
license: cc-by-nc-nd-4.0
task_categories:
- image-classification
modality:
- image
language:
- en
tags:
- medical
- ophthalmology
- glaucoma
- OCT
- representation-learning
- artifact-correction
pretty_name: Harvard-GD
size_categories:
- n<1K
---

# Dataset Card: Harvard-GD

## Dataset Summary

Harvard-GD (Harvard Glaucoma Detection) is an ophthalmology dataset of OCT retinal nerve fiber layer thickness (RNFLT) maps from 500 unique glaucoma patients. It includes glaucoma labels and visual field mean deviation (MD) values, and was released alongside the EyeLearn framework for artifact-tolerant contrastive representation learning on ophthalmic images.

This dataset was introduced in the IEEE Journal of Biomedical and Health Informatics 2023: [Artifact-Tolerant Clustering-Guided Contrastive Embedding Learning for Ophthalmic Images in Glaucoma](https://ieeexplore.ieee.org/document/10159482).

## Dataset Details

### Dataset Description

| Field | Value |
|----------------|-------|
| **Institution**| Department of Ophthalmology, Harvard Medical School |
| **Task** | Glaucoma detection |
| **Modality** | OCT RNFLT maps |
| **Scale** | 500 patients, 500 OCT RNFLT maps |
| **Image size** | 225 × 225 (RNFLT map) |
| **License** | [CC BY-NC-ND 4.0](https://creativecommons.org/licenses/by-nc-nd/4.0/) |

- **Curated by:** Min Shi, Anagha Lokhande, Mojtaba S. Fazli, Vishal Sharma, Yu Tian, Yan Luo, Louis R. Pasquale, Tobias Elze, Michael V. Boland, Nazlee Zebardast, David S. Friedman, Lucy Q. Shen, Mengyu Wang
- **License:** [CC BY-NC-ND 4.0](https://creativecommons.org/licenses/by-nc-nd/4.0/) — non-commercial research only
- **Paper:** [IEEE JBHI 2023](https://ieeexplore.ieee.org/document/10159482)
- **Contact:** [e-mail], [e-mail]

### Data Fields

The dataset is stored as a `.npy` file (`rnflt_map.npy`) containing RNFLT maps for all 500 subjects:

| Field | Description |
|------------|-------------|
| `rnflt` | OCT retinal nerve fiber layer thickness (RNFLT) map, size 225 × 225 |
| `glaucoma` | Glaucomatous status: `0` = non-glaucoma, `1` = glaucoma |
| `md` | Mean deviation value of visual field |

## Uses

### Direct Use

- Glaucoma detection benchmarking with OCT RNFLT imaging
- Representation learning and contrastive embedding research for ophthalmic images
- Artifact detection and correction in RNFLT maps
- Pretraining and evaluation of ophthalmic image encoders

### Out-of-Scope Use

Clinical decisions, patient care, or any commercial application. This dataset shall not be used for clinical decisions at any time.

## Access

The "Harvard" designation indicates the dataset originates from the Department of Ophthalmology at Harvard Medical School. It does not imply endorsement, sponsorship, or legal responsibility by Harvard University or Harvard Medical School.

## Citation

**BibTeX:**

```bibtex
@article{10159482,
author={Shi, Min and Lokhande, Anagha and Fazli, Mojtaba S. and Sharma, Vishal and Tian, Yu and Luo, Yan and Pasquale, Louis R. and Elze, Tobias and Boland, Michael V. and Zebardast, Nazlee and Friedman, David S. and Shen, Lucy Q. and Wang, Mengyu},
journal={IEEE Journal of Biomedical and Health Informatics},
title={Artifact-Tolerant Clustering-Guided Contrastive Embedding Learning for Ophthalmic Images in Glaucoma},
year={2023},
volume={27},
number={9},
pages={4329-4340},
doi={10.1109/JBHI.2023.3288830}
}
```

**APA:**

Shi, M., Lokhande, A., Fazli, M. S., Sharma, V., Tian, Y., Luo, Y., Pasquale, L. R., Elze, T., Boland, M. V., Zebardast, N., Friedman, D. S., Shen, L. Q., & Wang, M. (2023). Artifact-Tolerant Clustering-Guided Contrastive Embedding Learning for Ophthalmic Images in Glaucoma. *IEEE Journal of Biomedical and Health Informatics*, *27*(9), 4329–4340. https://doi.org/10.1109/JBHI.2023.3288830