Dataset · yangzekang2000
Mouse brain neuron reconstruction benchmark
yangzekang2000/CORAL
Light microscopy images and annotations for 3D and 2D neuron reconstruction.
What's inside
The dataset was created for the CORAL benchmark and contains 1 to 10 thousand examples (images and text) for segmentation and image-to-text tasks. Data is split into two scenarios: local neuron morphology reconstruction from small 3D image blocks and full neuron recovery from 2D light microscopy slices of the whole mouse brain.
What you can do with it
- Training biomedical image and microscopy segmentation models
- Comparing algorithms for 3D and 2D reconstruction of neuronal structures
- Tasks
- Image segmentation, Image → text
- Size
- 1K–10K rows
- Downloads this month
- 19.9K
- Likes
- 1
How to load it
from datasets import load_dataset
ds = load_dataset("yangzekang2000/CORAL")