NiftiSaver

[udiram]

Describe the bug
while trying to save niftis, error message is unclear and no clear solution, other than a rollback, appears viable

To Reproduce
import and use NiftiSaver on monai 1.2.0

Expected behavior
information on where NifiSaver is now imported from, or whether it is deprecated.

Environment (please complete the following information):

• OS: ubuntu 22.04
  MONAI version: 1.2.0
  Numpy version: 1.25.2
  Pytorch version: 2.0.1+cu117
  MONAI flags: HAS_EXT = False, USE_COMPILED = False, USE_META_DICT = False
  MONAI rev id: c33f1ba588ee00229a309000e888f9817b4f1934
  MONAI file: /home/exouser/.local/lib/python3.10/site-packages/monai/init.py

Optional dependencies:
Pytorch Ignite version: 0.4.11
ITK version: 5.3.0
Nibabel version: 5.1.0
scikit-image version: 0.21.0
Pillow version: 9.0.1
Tensorboard version: 2.14.0
gdown version: 4.7.1
TorchVision version: 0.15.2+cu117
tqdm version: 4.66.1
lmdb version: 1.4.1
psutil version: 5.9.0
pandas version: 2.0.3
einops version: 0.6.1
transformers version: 4.21.3
mlflow version: 2.6.0
pynrrd version: 1.0.0

Python 3.10.12
Driver Version: 525.85.05 CUDA Version: 12.0
GRID A100X-40C

Additional context
worked previously (1 or 2 releases ago), but fails to provide adequate resolution in user facing warnings/error.

[KumoLiu]

Hi @udiram, thanks for your suggestion here.
I think we have removed this API since v0.9, perhaps you could use NibabelWriter now.
https://github.com/Project-MONAI/MONAI/blob/dev/CHANGELOG.md#removed

Hope it helps, thanks!

[udiram]

hi @KumoLiu , thanks for your response! I am able to save it by rolling back my monai to the last working version I had, 1.0.0, but keeping other packages up to date like numpy, to avoid the "missing image reader for file .nii.gz" issue. I was wondering if there are any monai frameworks that I could use to reverse the transforms that i load the images in with in val_loader, because the images I am inferencing on are then being shifted/cropped and I would like to overlay these, which would mean reversing the original training/validation transforms after inference.

thanks,

[KumoLiu]

Hi @udiram, you can use inverse to invert your data.
For more details, you can refer to this tutorial.
https://github.com/Project-MONAI/tutorials/blob/main/modules/inverse_transforms_and_test_time_augmentations.ipynb

Or you can check the "Evaluation on original image spacings" section in most of the end-to-end tutorials.
https://github.com/Project-MONAI/tutorials/blob/main/3d_segmentation/brats_segmentation_3d.ipynb

Hope it helps, thanks!