Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

WIP(convert tool to transform)-135 add DICOM loader #141

Closed
wants to merge 6 commits into from

Conversation

Nic-Ma
Copy link
Contributor

@Nic-Ma Nic-Ma commented Mar 4, 2020

Fixes #135 .

Description

This PR implemented a medical image format converter.
Convert medical image formats with option to resample image.
Supported input formats: .dcm, .nii, .nii.gz, .mha, .mhd.
Supported output formats: .nii, .nii.gz, .mha, .mhd.

Status

Ready

Types of changes

  • Bug fix (non-breaking change which fixes an issue)
  • Breaking change (fix or new feature that would cause existing functionality to change)
  • New tests added to cover the changes
  • Docstrings/Documentation updated

@aylward
Copy link
Collaborator

aylward commented Mar 4, 2020

I don't recommend creating dependencies on SimpleITK. Consider using the full ITK - pip install itk

Copy link
Collaborator

@aylward aylward left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

See comments regarding SITK versus ITK.

ITK provides pipelining (data streaming, parallelism, etc), meshes, the ability to explicit specify template parameters of a filter, interfaces with numpy, and access to remote modules - ITK is the way to go.

You may also want to consider ITKWidgets for image, mesh, ... visualization in jupyter notebooks/labs:
https://github.com/InsightSoftwareConsortium/itkwidgets

monai/utils/medical_image_converter.py Show resolved Hide resolved
@Nic-Ma
Copy link
Contributor Author

Nic-Ma commented Mar 5, 2020

Hi All,

I updated the code to be compatible with master.
Could you please help review it again?
Thanks.

@wyli
Copy link
Contributor

wyli commented Mar 5, 2020

i think we need to have a loader wrapped as a transform, to show the idea that monai doesn't implement its own but build wrapper around external packages for this type of IO tasks. provide a CLI script is not proper integration... as a starting point let's use pydicom

@Nic-Ma Nic-Ma changed the title 135 add DICOM loader WIP(convert tool to transform)-135 add DICOM loader Mar 12, 2020
@Nic-Ma Nic-Ma mentioned this pull request Mar 20, 2020
@mhubii mhubii mentioned this pull request Mar 23, 2020
4 tasks
@zsdqui
Copy link

zsdqui commented May 8, 2020

any update on this WIP? Any thoughts on adding support for dicom-RT. Being able to load RT-struct files would greatly assist utilizing MONAI for radiotherapy applications.

@Nic-Ma
Copy link
Contributor Author

Nic-Ma commented May 8, 2020

any update on this WIP? Any thoughts on adding support for dicom-RT. Being able to load RT-struct files would greatly assist utilizing MONAI for radiotherapy applications.

Hi @zsdqui ,

Thanks for your suggestion.
I think our working group is discussing the DICOM support.
Thanks.

@Nic-Ma Nic-Ma added working group needs working group discussions and removed working group needs working group discussions labels May 8, 2020
@wyli
Copy link
Contributor

wyli commented Jul 6, 2020

this is out-of-date and becomes really confusing, I'm closing it now (the branch will be retained)

@wyli wyli closed this Jul 6, 2020
@wyli wyli deleted the 135-add-DICOM-loader branch August 19, 2020 10:18
wyli pushed a commit that referenced this pull request Sep 24, 2020
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

add a DICOM loader
5 participants