[WIP] Create script for distributed processing of HIP-CT datasets. #5
+97
−0
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
kabilar
reviewed
Dec 24, 2024
scripts/hipct-distributed.py
Outdated
| zarr.save(output_path, processed_data) | ||
| print(f"Processed data saved to {output_path}") | ||
|
|
||
| if __name__ == "__main__": |
There was a problem hiding this comment.
Thanks @Laurabtt152. Let's create a high-level/wrapper function. For an example, please see convert.
kabilar
reviewed
Dec 24, 2024
scripts/hipct-distributed.py
Outdated
Comment on lines
80
to
83
| # Paths | ||
| nifti_path = "path/to/input.nii.gz" # Path to the NIfTI file (if applicable) | ||
| zarr_path = "path/to/data.zarr" # Path to the Zarr file (output or input) | ||
| processed_output_path = "path/to/processed_output.zarr" |
There was a problem hiding this comment.
Please pass these variables in as arguments to the wrapper function.
kabilar
reviewed
Dec 24, 2024
scripts/hipct-distributed.py
Outdated
Comment on lines
18
to
25
| def nifti_to_zarr(nifti_path, zarr_path): | ||
| """Convert a NIfTI file to Zarr format.""" | ||
| img = nib.load(nifti_path) | ||
| data = img.get_fdata() | ||
| z = zarr.open(zarr_path, mode='w', shape=data.shape, dtype=data.dtype) | ||
| z[:] = data | ||
| print(f"Converted {nifti_path} to {zarr_path}") | ||
| return z |
There was a problem hiding this comment.
Please use @balbasty's tool to create the NIfTI-Zarr file - https://github.com/neuroscales/nifti-zarr/tree/impl/0.3/python
There was a problem hiding this comment.
I will use this as a guide: https://github.com/neuroscales/nifti-zarr/tree/impl/0.3/python/python. Thank you!
@balbasty's tool to create the NIfTI-Zarr file.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This code is a work in process to facilitate the preprocessing and analysis of large 3D imaging datasets, such as those in NIfTI format, by converting them into Zarr format for efficient processing. Leveraging Dask for distributed computation, the pipeline applies techniques like proportional thresholding, CLAHE (contrast enhancement), and 8-bit quantization, with optional masking to isolate regions of interest. The initial focus is to develop a scalable, cluster-enabled computational framework for pre- and post-processing of whole-brain imaging datasets, with initial applications to HiP-CT data and the flexibility to extend to other modalities.