taotianli / petmr Goto Github PK

The whole project consists two parts: Clinica Surface Processing and Graph Neural Network construction (VGAE and GIN).

##Model

The conda environment is as follows

dgl=0.9.0
nibabel=4.0.1
pytorch=1.10.2
scikit-learn=1.0.2
scipy=1.7.3

Quick distribution:

conda install --yes --file requirements.txt

Use area under the ROC curve (AUC) and average precision (AP) scores for each model on the test set. Numbers show mean results and standard error for 10 runs with random initializations on fixed dataset splits.

特征种类、脑区数量

• Clinica - The web framework used
• DGL - Main framework

• Tianli Tao @ShanghaiTech University - Initial work