External Email - Use Caution Thank you very much, but I want to implement tf.train.F Feature of python or numpy data type. This is an essential step towards building any TFRecords database.
The method I found requires nii files to be extracted and read by SimpleITK في الأربعاء، 23 فبراير 2022 في 6:59 ص تمت كتابة ما يلي بواسطة Fischl, Bruce <bfis...@mgh.harvard.edu>: > Oops, slight edit > > > > import nibabel as nib > > > > file_list = [os.path.join(os.getenv(‘SUBJECTS_DIR’), subject, ‘mri’, > ‘brainmask.mgz’)for subject in subject_list] > > mri_list = [nib.load(fname) for fname in file_list] > > > On Feb 22, 2022, at 9:53 PM, Fischl, Bruce <bfis...@mgh.harvard.edu> > wrote: > > > > In python you should be able to do (assuming you have a list of subject > ids in subject_list): > > > > import nibabel as nib > > > > file_list = [os.path.join(os.getenv(‘SUBJECTS_DIR’), subject) for subject > in subject_list] > > mri_list = [nib.load(fname) for fname in file_list] > > > > even for 1000 subjects it won’t take that long, depending of course on > your disk speed. You shouldn’t have to convert from .mgz – nibabel can read > it > > > > *From:* freesurfer-boun...@nmr.mgh.harvard.edu < > freesurfer-boun...@nmr.mgh.harvard.edu> *On Behalf Of *REEM ABU BAKR > BAHATHIQ > *Sent:* Tuesday, February 22, 2022 9:28 PM > *To:* freesurfer@nmr.mgh.harvard.edu > *Subject:* [Freesurfer] convert .mgz to .nii > > > > * External Email - Use Caution * > > Hello FreeSurfer experts, > > > I want to run a classification task using deep learning on data processed by > Freesurfer recon-all and I have some queries. I will use brainmask .mgz > > First of all, based on my simple knowledge, I cannot feed my model with > this output directly. .mgz files must be converted to a .nii file for use in > analytics. I found that this is done by writing > mri_convert any_volume.mgz any_volume.nii.gz > > But how can I convert the files of all participants (more than 1000) into > .nii files instead of going one by one? > > > Are there any examples or tutorials provided to demonstrate the use of > Freesurfer output in machine learning applications? > > My greetings, > > _______________________________________________ > Freesurfer mailing list > Freesurfer@nmr.mgh.harvard.edu > https://secure-web.cisco.com/1d4v_JiLdgyoo1M50Rzz876te5ChiMw78p3ca1kSmYBar4K1UQpEq0Sufgu2nv873YD7i769zX2W_EtXuu5ZbPo18I7MCFdab2nHNavS40ikI56Juu-WqlT93WCw6mp7k5EBk4u2VqQfZiverUh3AGnYTeTESIgdUp8BNwQdHAsGAcfawsvQ3ISZp4Dnf0x2n5VUXeShiWe15oVL6IrkGjCK8BYcSNpXvDvZ94DInDvnDVLa7Z24qRpIVGJywyK0WP0s0kYIFFcpzWa5eKU_LQi_-xmlZqNUcvgM9s3G6eKJyDTjA9t72b02lVdVh4uoq-SeJok_13zPCHWyaIRbCPA/https%3A%2F%2Fmail.nmr.mgh.harvard.edu%2Fmailman%2Flistinfo%2Ffreesurfer
_______________________________________________ Freesurfer mailing list Freesurfer@nmr.mgh.harvard.edu https://mail.nmr.mgh.harvard.edu/mailman/listinfo/freesurfer
