Skip to content

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

38 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

This repo is the official implementation of "Multimodal Multitask Deep Learning for Predicting Tertiary Lymphoid Structures and Peritoneal Recurrence in Gastric Cancer: A Multicenter Study".

image

Requirements

Python == 3.8 and install from the requirements.txt using:

pip install -r requirements.txt

Pre-trained model

The model weights of CTransNet can be downloaded at the link. You may need to send the request to get the access permission.

Usage

1. Training

You can train to get your own model.

python train.py

2. Evaluation

2.1. Test the Model on the prediction of the maturation stages of TLSs.

python eval.py

2.2. Test the Model on the prediction of peritoneal recurrence-free survival

python eval_os.py

2.3. Inference the Model to predict the maturation stages of TLSs and peritoneal recurrence-free survival on external validation cohort

python inference.py

Citation

@article{li2026ctrans,
  title={Multimodal Multitask Deep Learning for Predicting Tertiary Lymphoid Structures and Peritoneal Recurrence in Gastric Cancer: A Multicenter Study},
  author={Li, Zihan and Zhang, Taojun and others},
  journal={The Lancet Digital Health},
  year={2026},
  publisher={Elsevier}
}

About

[The Lancet Digital Health 2026] This repo is the official implementation of "Multimodal Multitask Deep Learning for Predicting Tertiary Lymphoid Structures and Peritoneal Recurrence in Gastric Cancer: A Multicenter Study"

Resources

Stars

Watchers

Forks

Releases

Packages

Contributors

Languages