Skip to content

Latest commit

 

History

History
27 lines (15 loc) · 1.18 KB

README.md

File metadata and controls

27 lines (15 loc) · 1.18 KB
Raw

DeepCT-LNM-Example

This is an example of running inference with the trained DeepCT-LNM prediction model. The model takes as inputs the CT image (arterial and portal phases) and corresponding PDAC and lymph node masks, and outputs the probability of lymph node metastasis status. An illustrative example of the input data is provided in the test_example folder. This code is developed based on nnUNet framework.

Installation

This code depends on nnUNet. Below are quick steps for installation. Please refer to (https://github.com/MIC-DKFZ/nnUNet#installation) for more detailed instruction.

  1. Install PyTorch

pip install torch torchvision

  1. Install nnUNet

pip install nnunet

Usage

The DeepCT-LNM prediction model is avaiable for research-use only. COMMERCIAL USE IS PROHIBITED for the time being.

set environment variables

Set checkpoints path to RESULTS_FOLDER

export RESULTS_FOLDER="checkpoints path"

run inference with the trained model

bash run_inference.sh test_data_dir