vishnubashyam/deepbrainnet

Convolutional Neural Network trained for age prediction using a large (n=11,729) set of MRI scans from a highly diversified cohort spanning different studies, scanners, ages, ethnicities and geographic locations around the world.

DeepBrainNet

Convolutional Neural Network trained for age prediction using a large (n=11,729) set of MRI scans from a highly diversified cohort spanning different studies, scanners, ages, ethnicities and geographic locations around the world.

Files are in HDF5(.h5) format for easy use in Keras. Model files initalize the architecture and the pre-trained weights.

Other file can be found here: https://upenn.box.com/v/DeepBrainNet

Use test.sh in the Script folder to perform brain age prediction on T1 brain scans.

• Run test.sh -h to see required parameters

----Data Requirements----

• T1 scans must be in nifti format
• Scans shoud be skull-striped and linearly registered

deepbrainnet's Issues

questions consultation

Dear authors:
Recently I have looking your this project and feel interested in it !could have a introduction, like paper or tutorial of this project.

Best regards.

Data augmentation

Hello! Would it be possible for you to share more details on the data augmentation performed on the training data?
Thank you

dataset download path

Hello, is the dataset open source? And where can I download the dataset?

the version of keras

Hi ,I got a bug describe as ValueError: Unknown layer:name,this is because the version of keras intalled in your running envrioment is different from mine,so could you please tell me the version of keras you are using?

How to convert my data formats to NIfTI?

Can I confirm the predicted ages for these sample data?

Dear,

Can I confirm the predicted ages for these sample data?
I would like to compare your prediction results using the model on sample data to confirm that I have configured this environment correctly.

Thank you.
Best wishes

OSError: Unable to open file (file signature not found)

Hi Vishnu (@vishnubashyam), did you upload the proper Models/DBN_model.h5 file to GitHub? I have been helping one of our RAs to install it and Python complained as follows when we tried Script/test.sh:

  File "py3-akb67/envs/akb67-deepbrain/lib/python3.6/site-packages/h5py/_hl/files.py", line 190, in make_fid
    fid = h5f.open(name, flags, fapl=fapl)
  File "h5py/_objects.pyx", line 54, in h5py._objects.with_phil.wrapper
  File "h5py/_objects.pyx", line 55, in h5py._objects.with_phil.wrapper
  File "h5py/h5f.pyx", line 96, in h5py.h5f.open
OSError: Unable to open file (file signature not found)

In my experience, h5 files are big and are circulated through GitHub release or Google Drive share.