Deep learning features from diffusion tensor imaging improve glioma stratification and identify risk groups with distinct molecular pathway activities
Release date:
2021-05-06
Description:
To develop and validate a deep learning signature (DLS) from diffusion tensor imaging (DTI) for predicting overall survival in patients with infiltrative gliomas, and to investigate the biological pathways underlying the developed DLS.The DLS was developed based on a deep learning cohort (n = 766). The key pathways underlying the DLS were identified on a radiogenomics cohort with paired DTI and RNA-seq data (n=78), where the prognostic value of the pathway genes was validated in public databases (TCGA, n = 663; CGGA, n = 657).We found that DTI-derived DLS can improve glioma stratification by identifying risk groups with dysregulated biological pathways that contributed to survival outcomes. Therapies inhibiting neuron-to-brain tumor synaptic communication may be more effective in high-risk glioma defined by DTI-derived DLS.
Organization: The First Affiliated Hospital of Zhengzhou University
Submission date: 2021-04-30
Aspera Command Line
You need to install the Aspera Connect plugin before uploading your files. If you dont have Aspera Connect plugin installed in your computer, please Download Aspera Connectand install it first.
[path/to/ascp]: Microsoft Windows: C:\Program Files\Aspera\Aspera Connect\bin\ascp.exe or
c:\users\[username]\AppData\Local\Programs\Aspera\Aspera Connect\bin\ascp.exe
Mac OS X: /Applications/Aspera/Connect.app/Contents/Resources/ascp (for admin's installation) or
/Users/[username]/Applications/Aspera/Connect.app/Contents/Resources/ascp (for non-admin's installation)
Linux: /opt/aspera/bin/ascp or
/home/[username]/aspera/connect/bin/ascp
[path/to/key/file] must be an absolute path, e.g.: /home/keys/aspera.openssh
[path/to/folder/containing/files] needs to specify the local folder that contains all the files to upload.