Closed YuyangXueEd closed 1 year ago
Hi @YuyangXueEd, thanks for your interest in VORTEX and meddlr! We are looking to add support for single coil data, but do not have a set timeline for when that would be available.
In the interim, you should be able to use all functionality in meddlr by passing a dummy maps
argument, which corresponds to sensitivity maps to each coil. Because there is only one coil, the sensitivity maps would be the 1-tensor (where all entries of the matrix are 1).
The maps tensor should be a complex-valued tensor of shape [batch, height, width, # coils, # maps], which in this case would be [batch, height, width, 1, 1].
I am closing this comment for now. let me know if you run into any issues
Hello, I am new to MRI reconstruction and plan to learn to use fastMRI with singlecoil dataset and using meddlr to reproduce the VORTEX work. I just read the "VORTEX" paper and I think it was a great work. However, I go through the code and found most functions, such as
meddlr.utils.transforms
ordatasets/format_fastmri.py
is mainly used for multicoil data. Could you please consider adding singlecoil support?Lookingforward to your reply. Thank you very much!