Problem running inference on new data

[jcohenadad]

Problem

According to private discussions between @plbenveniste and Benjamin, running the code version https://github.com/ivadomed/model_seg_mouse-sc_wm-gm_t1/releases/tag/v0.3 on new data produced the following error:

The cause of the issue, identified by @plbenveniste, is that the input data have a corrupted NIfTI header. More specifically, the physical dimensions of the voxels are wrong, which cause memory saturation during resampling as part of the nnUnet preprocessing pipeline.

Solution

A solution is to make sure the data are correct. To do so:

• in the first place, the data coming from the scanner should be converted to NIfTI using proper software. Dcm2niix is an example of a good software.
• Alternatively (although the previous solution is best), the NIfTI headers could be manually corrected:

[plbenveniste]

To solve this problem, I added the file correct_file_header.py in utils which corrects the Nifti header.
This script updates the xdim, ydim, zdim and sets the sform matrix equal to the qform matrix.
The resolution has to be given in mm.

To use this file, run the following command (in the virtual environment):
python utils/correct_file_header.py --path-image /path/to/image --path-out /path/to/output/folder --resolution XX YY ZZ

For example, for 0.05 mm isotropic:
python utils/correct_file_header.py --path-image image.nii --path-out ~/Folder --resolution 0.05 0.05 0.05