Welcome!

DPABI

This is a website to demonstrate BrainImageNet: an Industrial-Grade Brain Imaging Based Deep Learning Classifier. We openly shared our trained model, code and framework (https://github.com/Chaogan-Yan/BrainImageNet), and here built an online predicting website for whoever are interested in testing our classifier with brain imaging data from anybody and any scanner. Please upload brain structural data (raw data or preprocessed gray matter density/volume data) to predict the sex of the participant(s). OF NOTE: FOR RESEARCH PURPOSE ONLY!


1. Predicting sex by preprocessed gray matter density/volume data. This will significantly enhance the speed of prediction. Please preprocess your structural image to get the gray matter density data (wc1*) and gray matter volume data (mwc1*) by SPM or DPABI/DPARSF. The data required is NIfTI format (.nii or .nii.gz) in MNI space with a resolution of 91*109*91. The filenames should be wc1_XXXXX.nii(.gz) and mwc1_XXXXX.nii(.gz) (XXXXX is subject ID). Please compress all of your files (could be many participants) in a single .zip file for uploading. Please see an example of DemoData_BrainImageNet. As the prediction may take minutes (even tens of minutes depending on the number of participants), you can wait here or leave your email in the textbox to receive the prediction results from email attachment. MAX: 10 SUBJECTS!



2. Predicting sex by raw T1 structural image. The data required is NIfTI format (.nii or .nii.gz). Please compress all of your files (could be many participants) in a single .zip file for uploading. As the prediction may take tens of minutes depending on the number of participants, you can wait here or leave your email in the textbox to receive the prediction results from email attachment. MAX: 10 SUBJECTS!


Reference: Lu, B., Li, H.-X., Chang, Z.-K., Li, L., Chen, N.-X., Zhu, Z.-C., Zhou, H.-X., Li, X.-Y., Wang, Y.-W., Cui, S.-X., Deng, Z.-Y., Fan, Z., Yang, H., Chen, X., Thompson, P.M., Castellanos, F.X., Yan, C.-G. (2022). A practical Alzheimer’s disease classifier via brain imaging-based deep learning on 85,721 samples. Journal of Big Data, 9(1), 101, doi:10.1186/s40537-022-00650-y.
Under patent protection (ZL 2020 1 0821445.1 and ZL 2020 1 0820669.0), all rights reserved.
For commercial use, please contact Prof. Chao-Gan Yan.
For more information about our research, please visit The R-fMRI Lab.