Dataset · Forithmus
3D MRI scans with text reports
Forithmus/MR-RATE
Brain and spine MRIs with text conclusions for multimodal medical models.
What's inside
MR-RATE is a vision-language dataset and model for MRI: 3D scans of the brain and spine mapped to text reports. Built using the CT-RATE approach; described in the card as a pioneering MRI dataset. The language is English, and the volume ranges from 10k to 100k records.
What you can do with it
- Training VLMs to generate MRI conclusions
- Visual question answering on medical scans
- Zero-shot classification of MRI images
- Tasks
- Image → text, Text → image, Image classification, Question answering, Visual question answering, Zero shot classification
- Languages
- English
- Size
- 10K–100K rows
- Downloads this month
- 95.2K
- Likes
- 138
- Access
- on request on Hugging Face
Models trained on it
How to load it
from datasets import load_dataset
ds = load_dataset("Forithmus/MR-RATE")