Skip to content

update MRI recon demo #1024

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 5 commits into from
Nov 5, 2022
Merged

update MRI recon demo #1024

Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
7a3d1fe
dummy commit
mersad95zd Nov 4, 2022
7ec441d
Merge branch 'main' into 00-update-dataset
mersad95zd Nov 4, 2022
bb913d2
another dummy commit
mersad95zd Nov 4, 2022
013205b
Merge branch '00-update-dataset' of https://github.com/mersad95zd/tut…
mersad95zd Nov 4, 2022
2b443dc
data description added
mersad95zd Nov 4, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 3 additions & 1 deletion reconstruction/MRI_reconstruction/unet_demo/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,12 +31,14 @@ This folder contains code to train and validate a U-Net for accelerated MRI reco

# Dataset

The experiments are performed on the [fastMRI](https://fastmri.org/dataset) dataset. Users should request access to the dataset
The experiments are performed on the [fastMRI](https://fastmri.org/dataset) brain multi-coil dataset (AXT2 modality). Users should request access to the dataset
from the [owner's website](https://fastmri.org/dataset). Remember to use the `$PATH` where you downloaded the data in `train.py`
or `inference.ipynb` accordingly.

For our experiments we created a subset of the fastMRI dataset which contains a `500/179/133` split for `train/val/test`. Please download [fastmri_data_split.json](https://github.com/Project-MONAI/MONAI-extra-test-data/releases/download/0.8.1/fastmri_data_split.json) and put it here under `./data`.

**Note.** The dataset files that need to be downloaded from [fastMRI](https://fastmri.org/dataset) are `brain_multicoil_train.tar.gz` (~1228.8 GB) and `brain_multicoil_val.tar.gz` (~350.9 GB).

# Model checkpoint

We have already provided a model checkpoint [unet_mri_reconstruction.pt](https://github.com/Project-MONAI/MONAI-extra-test-data/releases/download/0.8.1/unet_mri_reconstruction.pt) for a U-Net with `7,782,849` parameters. To obtain this checkpoint, we trained
Expand Down