TNM-Classifier

Overview

TNM-Classifier is a model based on BERT designed to predict the TNM classification of cancer from radiology reports of lung cancer patients. This model is based on the NTCIR-17 MedNLP-SC Radiology Report Subtask (MedTxt-RR) and has been retrained using the corpus released in MedTxt-RR. This model is for the model in this github.

Model Features

  • Model Architecture: JMedRoBERTa (manbyo-wordpiece)
  • Training Data: MedTxt-RR corpus
  • Use Case: TNM classification of lung cancer (predicting tumor size, lymph node involvement, and distant metastasis)
Downloads last month
8
Safetensors
Model size
109M params
Tensor type
F32
·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model has no library tag.