add a DICOM loader

[wyli]

Nibabal is used to load Nifti files,
would be great to have preliminary support of loading DICOM (using pydicom)

[mhubii]

is this still an open issue? Happy to contribute here as well

[wyli]

yes it is, would be great to have it in a similar format to LoadNifti
https://github.com/Project-MONAI/MONAI/blob/master/monai/transforms/transforms.py#L140

[mhubii]

all right. Would it belong to data where the Dataset is also generated https://github.com/Project-MONAI/MONAI/blob/master/monai/data/nifti_reader.py?

[Nic-Ma]

Hi @mhubii ,

Glad to see your contribution here!

1. Please develop a LoadDICOM/LoadDICOMd transform referring to the LoadNifti/LoadNiftid transform as Wenqi said:
   https://github.com/Project-MONAI/MONAI/blob/master/monai/transforms/transforms.py#L140
   https://github.com/Project-MONAI/MONAI/blob/master/monai/transforms/composables.py#L116
   You can also check this example to see how to use the LoadNiftid transform:
   https://github.com/Project-MONAI/MONAI/blob/master/examples/integrate_to_spleen_program.ipynb
2. I will try to refactor the nifti_reader Dataset to be compatible with common Dataset soon:
   https://github.com/Project-MONAI/MONAI/blob/master/monai/data/dataset.py
3. And we already have a WIP PR WIP(convert tool to transform)-135 add DICOM loader #141 that contains a DICOM reader tool, you can leverage the code to contribute to that branch or create a new PR as you like.

Thanks.

[aylward]

Support for ITK Python (and SimpleITK). ITK Python provides direct support for numpy arrays, xarrays, and other data formats. It also exposes more of ITK and is more "pythonic" than SimpleITK. See
ITK Python Quick Start

[pfdamasceno]

Hi all, I'd happy to contribute as well.

In particular, after reading the DICOM, properly sorting slices can be a bit tricky. Is this a useful / desired feature?

[aylward]

ITK has a fairly good function for sorting DICOM. Here is the Python code for using it: https://itk.org/ITKExamples/src/IO/GDCM/ReadDICOMSeriesAndWrite3DImage/Documentation.html

…

On Mon, Jul 6, 2020 at 11:07 AM Pablo F. Damasceno ***@***.***> wrote: Hi all, I'd happy to contribute as well. In particular, after reading the DICOM, properly sorting slices can be a bit tricky <https://github.com/UCSF-intelligent-imaging/I2T2/blob/master/I2T2/io.py#L163>. Is this a useful / desired feature? — You are receiving this because you commented. Reply to this email directly, view it on GitHub <#135 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AACEJL2ELGDTX4WYIAQPYYLR2HSCHANCNFSM4LAMICJA> .

-- Stephen R. Aylward, Ph.D. Senior Director of Strategic Initiatives --- Kitware: *Advancing the frontiers of understanding* *by developing innovative open-source software platforms* *and integrating them into research, processes, and products.*

[Nic-Ma]

Hi @mjorgecardoso ,

Could you please help share the latest status of DICOM discussion in our IO working group?
Thanks.

[aylward]

https://github.com/Project-MONAI/MONAI/wiki/IO-Working-Group-Meeting-Notes

…

On Mon, Jul 6, 2020 at 12:18 PM Nic Ma ***@***.***> wrote: Hi @mjorgecardoso <https://github.com/mjorgecardoso> , Could you please help share the latest status of DICOM discussion in our IO working group? Thanks. — You are receiving this because you commented. Reply to this email directly, view it on GitHub <#135 (comment)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AACEJL2MUX4EWBMYPJIMPVDR2H2M7ANCNFSM4LAMICJA> .

-- Stephen R. Aylward, Ph.D. Senior Director of Strategic Initiatives --- Kitware: *Advancing the frontiers of understanding* *by developing innovative open-source software platforms* *and integrating them into research, processes, and products.*

[wyli]

closing this in favour of #856