---
license: mit
language:
- en
tags:
- medical
- radiology
model-index:
- name: rate-ner-rad
  results: []
widget:
- text:  No focal enhancing brain parenchymal lesion.
  example_title: Example in radiopaedia
pipeline_tag: token-classification
---

# RaTE-NER-Deberta

This model is a fine-tuned version of [DeBERTa](https://huggingface.co./microsoft/deberta-v3-base) on the [RaTE-NER](https://huggingface.co./datasets/Angelakeke/RaTE-NER/) dataset.

## Model description

This model is trained to serve the RaTEScore metric, if you are interested in our pipeline, please refer to our [paper](https://angelakeke.github.io/RaTEScore/) and [Github](https://github.com/Angelakeke/RaTEScore).

This model also can be used to extract  **Abnormality, Non-Abnormality, Anatomy, Disease, Non-Disease**
in medical radiology reports.

## Usage
```python
from transformers import AutoTokenizer, AutoModelForTokenClassification

ner_labels = ['B-ABNORMALITY', 'I-ABNORMALITY', 'B-NON-ABNORMALITY', 'I-NON-ABNORMALITY', 'B-DISEASE', 'I-DISEASE', 'B-NON-DISEASE', 'I-NON-DISEASE', 'B-ANATOMY', 'I-ANATOMY', 'O']

tokenizer = AutoTokenizer.from_pretrained("Angelakeke/RaTE-NER-Deberta")
model = AutoModelForTokenClassification.from_pretrained("Angelakeke/RaTE-NER-Deberta",
                                                        num_labels=len(ner_labels),
                                                        ignore_mismatched_sizes=True,
                                                        )
```

## Author

Author: [Weike Zhao](https://angelakeke.github.io/)

If you have any questions, please feel free to contact zwk0629@sjtu.edu.cn.

## Citation
```

```