New data hosting and access


#1

Hi all,

Since the data continues to be downloaded at a fairly high rate, and the cost of fast bandwidth through Git-LFS was getting kind of high, I’ve moved the image files to a static location off of GitHub. I think this makes sense because they’re much larger than the label files when compressed, and they’re unlikely to change so a version history for them doesn’t add much value. The segmentation labels will remain on GitHub indefinitely. A python script to download the imaging from this new location and place it in the repository file tree like before has been added to the repository’s starter code. It’s designed to be robust to spotty internet connection. Please let me know if you have any questions or concerns with the new workflow.

Cheers!
Nick


#2

Hi,
Much to my regret, I know the time of this game, challenge is over, but I’m still interested in the challenge.When I downloaded .gz file, I encountered some trouble. There was an error when uncompressing the downloaded file, so I need to download it for many times. I am not sure whether it is the problem of my computer.because there was no error in the segmentation file downloaded from github.
you said you have patient demographics (e.g. age, gender, comorbidities) and surgical outcomes (e.g. blood loss, ischemia time, complications),These data will be released with the TCIA collection.I’d like to know if you release it.
I am looking forward to your reply. And thank you for holding such a meaningful competition.


#3

Hi,

The .nii.gz files are in a NIFTI file format, and gzip won’t know how to uncompress them. They are meant to be opened with a viewer such as ITK-SNAP or a dedicated Python package such as NiBabel.

Quality control and regulatory barriers on the outcomes data have turned out to take much longer than we anticipated, but we are still working hard to release them as soon as possible.


#4

Thanks for the reply neheller. Maybe .nii.gz could be uncompressed by gzip ,because I have uncompressed successfully for some case。For those files that cannot be uncompressed ,like master_00035,master_00040,when I run visualize.py , one error show me thatimage .
when I use ITK-SNAP ,I could not see anything like this

.
For files that can be uncompressed, none of these problems exist.
If you are sure that the file you downloaded now is ok, the problem may be on my computer


#5

Everything seems to be working on my end for those cases. Maybe something went wrong with your download. If you delete those imaging.nii.gz files and re-run the download script, it will re-download only those cases. e.g.

rm data/case_00035/imaging.nii.gz
rm data/case_00040/imaging.nii.gz
python3 -m starter_code.get_imaging