You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I am very interested in your work and noticed that GE data was used in FastMRI Challenge 202 Transfer track. I have recently started working with MRI data and have had difficulty extracting GE data in proper format. I have access to ACR Phantom raw data from GE scanner, however a direct ifftshift(ifft2(..)) over the raw kspace data gives me the following reconstruction:
A simple workaround is to flip the images but the data in such a format might interfere with learning the network weights in a non-generic fashion(for multiple vendors. SIEMENS doesn't have this issue). I was wondering if you can provide details regarding any library/tool readily available for easy conversion to h5 files.
Thank you for your time!
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
Hi,
I am very interested in your work and noticed that GE data was used in FastMRI Challenge 202 Transfer track. I have recently started working with MRI data and have had difficulty extracting GE data in proper format. I have access to ACR Phantom raw data from GE scanner, however a direct ifftshift(ifft2(..)) over the raw kspace data gives me the following reconstruction:
A simple workaround is to flip the images but the data in such a format might interfere with learning the network weights in a non-generic fashion(for multiple vendors. SIEMENS doesn't have this issue). I was wondering if you can provide details regarding any library/tool readily available for easy conversion to h5 files.
Thank you for your time!
Beta Was this translation helpful? Give feedback.
All reactions