Downloads · 30 days
1.8K
0% of all-time downloads
StanfordAIMI/RadBERT
RadBERT is a fill-mask model from StanfordAIMI. Use it when you need the model to fill a missing word. It is set up for transformers. The card lists the license as mit.
RadBERT was continuously pre-trained on radiology reports from a BioBERT initialization.
Downloads · 30 days
1.8K
0% of all-time downloads
All-time downloads
394K
Public
Repo size
872 MB
Likes
28
Public
Click a slice to open those files.
.bin436 MB · 100%
From the Hugging Face model README
RadBERT was continuously pre-trained on radiology reports from a BioBERT initialization.
@article{chambon_cook_langlotz_2022,
title={Improved fine-tuning of in-domain transformer model for inferring COVID-19 presence in multi-institutional radiology reports},
DOI={10.1007/s10278-022-00714-8}, journal={Journal of Digital Imaging},
author={Chambon, Pierre and Cook, Tessa S. and Langlotz, Curtis P.},
year={2022}
}