OCTA-500

OCTA-500

Optical coherence tomography angiography (OCTA) is a retinal imaging modality that allows a micron-level resolution to present the three-dimensional structure of the retinal vascular.

We propose a new dataset dubbed OCTA-500, which contains OCTA imaging under two fields of view (FOVs) from 500 subjects. The dataset provides rich images and annotations including two modalities (OCT/OCTA volumes), six types of projections, four types of text labels (age / gender / eye / disease) and seven types of segmentation labels (large vessel / capillary / artery / vein / 2D FAZ / 3D FAZ / retinal layers). 

Get Password:

To get the password of the compressed package, an application email must be sent to  chen2qiang@njust.edu.cn with a specified form like below, otherwise may be ignored.

• Title of Mail: 
• OCTA500: your_organization: your_name

Note that: The string of 'OCTA500' can not be empty. It is the fixed form and a special sign we use to identifying your downloading intention from other disturbers like spams.

• Body of Mail:
• Organization Detail: Your Organization Details
• Main Works: Your Main Works
• Usages: YourUsages About This Data Set

Related Papers:

Dataset:

• Mingchao Li, Kun Huang, Qiuzhuo Xu, Jiadong Yang, Yuhan Zhang, Zexuan Ji, Keren Xie, Songtao Yuan, Qinghuai Liu, and Qiang Chen. "OCTA-500: A Retinal Dataset for Optical Coherence Tomography Angiography Study," Medical Image Analysis, 2024: 103092.

Vessel segmentation:

• Mingchao Li, Yerui Chen, Zexuan Ji, Keren Xie, Songtao Yuan, Qiang Chen, and Shuo Li."Image projection network: 3D to 2D image segmentation in OCTA images," IEEE Trans. Med. Imaging, vol.39, no.11, pp.3343-3354, 2020.
• Mingchao Li, Weiwei Zhang, and Qiang Chen. "Image magnification network for vessel segmentation in OCTA images," in Chinese Conference on Pattern Recognition and Computer Vision. arXiv:2110.13428, 2022.
• Mingchao Li, Kun Huang, Zetian Zhang, Xiao Ma, and Qiang Chen. "Label adversarial learning for skeleton-level to pixel-level adjustable vessel segmentation," arXiv: 2205.03646, 2022.

Layer segmentation:

• Yuhan Zhang, Chen Huang, Mingchao Li, Sha Xie, Keren Xie, Songtao Yuan, and Qiang Chen. "Robust layer segmentation against complex retinal abnormalities for en face OCTA generation," in MICCAI, 2020.
• Jiadong Yang, Yuhui Tao, Qiuzhuo Xu,Yuhan Zhang, Xiao Ma, Songtao Yuan, and Qiang Chen. "Self-supervised sequence recovery for semi-supervised retinal layer segmentation," IEEE Journal of Biomedical and Health Informatics, vol.26, no.8, pp.3872-3883, 2022.

FAZ segmentation:

• Qiuzhuo Xu, Weiwei Zhang, Hongjing Zhu, and Qiang Chen. "Foveal avascular zone volume: a new index based on optical coherence tomography angiography images," Retina, vol.41, no.3, pp.595-601, 2021.
• Qiuzhuo Xu, Mingchao Li, Nairong Pan, Qiang Chen, and Weiwei Zhang. "Priors-guided convolutional neural network for 3D foveal avascular zone segmentation," Optics Express, vol.30, no.9, pp.14723-14736, 2022.

Dataset Update Log: 

• [2020.10] OCTA-500 was released, including labels for Large Vessels and FAZ
• [2021.3] Added Capillary labels
• [2022.3] Added 3D FAZ labels
• [2022.7] Added Artery-Vein labels  and Layer segmentation labels
• [2023.10] Optimized Capillary labels
• [2023.11] Optimized Layer segmentation labels

Dataset Structure:

OCTA-500 includes two subsets: OCTA_6M and OCTA_3M.

OCTA_6M(No.10001-No.10300):

• FOV: 6mm*6mm*2mm
• Volume: 400pixel*400pixel*640pixel

OCTA_3M(No.10301-No.10500):

• FOV: 3mm*3mm*2mm
• Volume: 304pixel*304pixel*640pixel

Both subsets contain the following information:

• OCT volumes
• OCTA volumes
• Projection Maps

1. OCT FULL(average)
2. OCT ILM_OPL (average)
3. OCT OPL_BM (average)
4. OCTA FULL (average)
5. OCTA ILM_OPL (maximum)
6. OCTA OPL_BM (maximum)

• Text Label

1. Gender
2. Age
3. OS/OD
4. Disease

• Segmentation Label

1. Large Vessel
2. Artery
3. Vein
4. Capillary
5. 2D FAZ
6. 3D FAZ
7. Retinal Layer