One Hundred Knee MRI Cases
|
|
|
|
|
| The 100 cases comprise five 20-case sets for each of the following sequences: (from left) coronal spin density weighted with fat supression, coronal spin density weighted without fat suppression, axial T2 weighted with fat suppression, saggital T2 weighted with fat suppression, and sagittal spin density weighted. | ||||
We are making available the training and test data used for our 2018 MRM article, Learning a Variational Network for Reconstruction of Accelerated MRI Data.*
The 100 cases comprise five sequences, 20 cases each.
The data set accompanies the code repository at: https://github.com/VLOGroup/mri-variationalnetwork
There are 20 cases from each of the following five sequences:
- coronal spin density weighted with fat suppression
- coronal spin density weighted without fat suppression
- axial T2 weighted with fat suppression
- sagittal T2 weighted with fat suppression
- sagittal spin density weighted
The data are organized slice by slice, and consist of two files:
-
rawdata*.mat:
The rawdata and some additional metadata variables (the acquisition includes phase oversampling and a rectangular field of view, see example matlab reconstruction script) -
espirit*.mat:
ESPIRiT [1] coil sensitivity maps and a reference reconstruction
In addition, the parallel imaging subsampling mask that was used for some of the experiments in our manuscript is included in a separate folder for the data of each sequence.
* This is a joint project with Thomas Pock's vision, learning, and optimization group at the Institute of Computer Graphics and Vision at Graz University of Technology.
Download Data
via Globus
Related publications:
- Hammernik K, Klatzer T, Kobler E, Recht M, Sodickson D, Pock T, Knoll F. Learning a Variational Network for Reconstruction of Accelerated MRI Data. Magnetic Resonance in Medicine 79:3055-3071 (2018). https://onlinelibrary.wiley.com/doi/abs/10.1002/mrm.26977
- Knoll F, Hammernik K, Kobler E, Pock T, Recht M, Sodickson D. Assessment of the generalization of learned image reconstruction and the potential for transfer learning. Magnetic Resonance in Medicine. 2018 May 17. doi: 10.1002/mrm.27355
Footnotes:
[1] Uecker M, Lai P, Murphy MJ, Virtue P, Elad M, Pauly JM, Vasanawala SS, Lustig M. ESPIRiT–an eigenvalue approach to auto- calibrating parallel MRI: where SENSE meets GRAPPA. Magnetic Resonance in Medicine 71:990–1001 (2014).
More about the research:
- MRM Highlights interview with the reserach team and video slides. (June 2018)
- Video of a presentation delivered at the inaugural i2i workshop in New York. (October 2016)
Sponsors
