This code is the implement of our paper "Improving Alzheimer’s Disease Diagnosis with Multi-Modal PET Embedding Features by a 3D Multi-task MLP-Mixer Neural Network", including both the proposed model and other competing methods.
- The sMRI data should be arranged like "ADNI/subject_id/viscode.nii".
- Using the CAT12 toolbox for SPM to preprocess the sMRI.
- Specify the sMRI data path in utils/datasets.py
- Download ADNIMERGE.csv, UCBERKELEYAV45_01_14_21.csv, and UCBERKELEYFDG_05_28_20.csv from the ADNI website and store them in data/.
python main.py --cuda_index 0 --method RegMixer --dataset ADNI_PET --clfsetting regression --batch_size 8 --n_epochs 100 \ --save_path regmodel.pth
python main.py --cuda_index 0 --method ClfMixer --clfdataset ADNI_dx --clfsetting CN-AD --batch_size 8 --n_epochs 100 \
--save_path clfmodel_cn_ad.pthREGPREPATH=regmodel.pth CLFPREPATH=clfmodel_cn_ad.pth \
python main.py --method FuseMixer --dataset ADNI_dx --clfsetting CN-AD --batch_size 8 --n_epochs 100
CLFPREPATH=classfication_pretrain_model_path REGPREPATH=regression_pretrain_model_path \
python main.py --method FuseMixer --dataset ADNI_dx --clfsetting sMCI-pMCI --batch_size 8 --n_epochs 100If you use this code, please cite our paper:
@ARTICLE{10137746,
author={Zhang, Zi-Chao and Zhao, Xingzhong and Dong, Guiying and Zhao, Xing-Ming},
journal={IEEE Journal of Biomedical and Health Informatics},
title={Improving Alzheimer's Disease Diagnosis with Multi-Modal PET Embedding Features by a 3D Multi-task MLP-Mixer Neural Network},
year={2023},
volume={},
number={},
pages={1-12},
doi={10.1109/JBHI.2023.3280823}}