Feature Request
A script mri_recon/experiments/run_all.py covering all possible combinations of distortions and reconstruction algorithms on single cases from each available datasubset (fast-MRI knee/breast/prostate/brain, Oasis).
Input data
Copy the following files into mri_recon/data/experiments_run1/:
- file1000036.h5 (knee_singlecoil_test)
- fastMRI_breast_001_1.h5 (fastMRI_breast_IDS_001_010)
- file_prostate_AXDIFF_001.h5 (fastMRI_prostate_DIFF_IDS_001_011)
- file_prostate_AXT2_001.h5 (fastMRI_prostate_T2_IDS_001_020)
- *t88_gfc.img (oasis_cross_sectional_data/OAS1_0001_MR1/PROCESSED/MPRAGE/T88_111/) (todo: select correct filename)
if multi coil data can be supported:
- file1000082.h5 (knee_multicoil_test)
- file_brain_AXT1POST_205_2050255.h5 (brain_multicoil_train_batch_0)
- file_brain_AXFLAIR_201_6003008.h5 (brain_multicoil_train_batch_0)
- file_brain_AXT2_200_2000566.h5 (brain_multicoil_train_batch_0)
Reconstruction Algorithms
- zero-filled
- conjugate-gradient
- ram
- dip
- tv-pgd
- wavelet-fista
- tv-fista
- tv-pdhg
- unet
-
Distortions
- Cartesian undersampling (variable density)
- Cartesian undersampling (uniform random)
- Cartesian undersampling (uniform random, zero ACS)
- Cartesian undersampling (equispaced)
- Cartesian undersampling (equispaced, zero ACS)
- Phase-encode ghosting
- Segmented translation motion
- Segmented rotational motion
- Translation motion
- Rotational motion
- Off-center anisotropic Gaussian bias field
- Gaussian bias field
- Anisotropic LP
- Hann taper LP
- Kaiser taper LP
- Gaussian noise
- Isotropic LP
- Radial high-pass emphasis
Acceptance Criteria:
Script creates .tif images for all combinations:
reports/experiment_run1/
- <case>
- <reconstruction_algorithm1>_nodistortion.tif
- <reconstruction_algorithm1>_<distortion1>.tif
- <reconstruction_algorithm1>_<distortion1>_corrected.tif
- <reconstruction_algorithm1>_<distortion2>.tif
- <reconstruction_algorithm1>_<distortion2>_corrected.tif
- ....
- <reconstruction_algorithm2>_nodistortion.tif
- <reconstruction_algorithm2>_<distortion1>.tif
- <reconstruction_algorithm2>_<distortion1>_corrected.tif
- <reconstruction_algorithm2>_<distortion2>.tif
- <reconstruction_algorithm2>_<distortion2>_corrected.tif
...
Feature Request
A script mri_recon/experiments/run_all.py covering all possible combinations of distortions and reconstruction algorithms on single cases from each available datasubset (fast-MRI knee/breast/prostate/brain, Oasis).
Input data
Copy the following files into mri_recon/data/experiments_run1/:
if multi coil data can be supported:
Reconstruction Algorithms
Distortions
Acceptance Criteria:
Script creates .tif images for all combinations:
reports/experiment_run1/