WIP: add labs script for using pyradiomics with DICOM #437
Conversation
|
@JoostJM I am confused about flake8 errors - local checks pass. Do you know why it behaves differently on CI? @zhenweishi the updated script is here. Once this PR is merged, it will be ready for your use. |
fedorov
force-pushed
the
add-pyradiomics-dcm
branch
from
012b33b
to
51bc87f
Compare
|
TODO:
|
I think I understand - I did not take into account the project specific settings in https://github.com/Radiomics/pyradiomics/blob/2b98e8b15a2a8a3574869cb82dc32473591a2e09/.flake8 |
Should not matter if you run flake8 from the root directory. |
JoostJM
force-pushed
the
add-pyradiomics-dcm
branch
from
2b98e8b
to
4bdca06
Compare
| "modifierValue": self.makePrivateCode("Exponent transformation")}) | ||
|
|
||
| # parameterized processing operations | ||
| elif re.match("wavelet-([HL]{3})", prefix): |
There was a problem hiding this comment.
Should allow 2 characters in case of forced 2d extraction.
JoostJM
force-pushed
the
add-pyradiomics-dcm
branch
from
ef094cc
to
5c07999
Compare
JoostJM
force-pushed
the
add-pyradiomics-dcm
branch
from
3d7ce55
to
a5df037
Compare
|
Hi, Andrey and Joost
Thanks both. I will continue to work on that.
Best,
Zhenwei
…On Mon, 8 Oct 2018 at 20:18, Andrey Fedorov ***@***.***> wrote:
@JoostJM <https://github.com/JoostJM> I am confused about flak8 errors -
local checks pass. Do you know why it behaves differently on CI?
@zhenweishi <https://github.com/zhenweishi> the updated script is here.
Once this PR is merged, it will be ready for your use.
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub
<#437 (comment)>,
or mute the thread
<https://github.com/notifications/unsubscribe-auth/AQOCxYQoasf1OU6u2Koy_EhnFXvr5qvwks5ui5b_gaJpZM4XNYuB>
.
|
|
btw @fedorov, I did a forced-push to remove an unnecessary merge from the history. |
|
Thank you @JoostJM! I will make a new release of dcmqi so it is easier to reference, and then will update the version pointer and merge. Sorry about the "dirty" commit history, thank you for fixing that. |
|
I may need to do few adjustments. I found a meaningful place to put pyradiomics processing parameters, but I will need to add things to dcmqi first to allow encoding of those attributes. |
|
@zhenweishi can you tell me when you are planning to do the conversion? There is this one issue about encoding algorithm identification that I would like to fix, and it would help me prioritize things if I know your plans a bit better. |
Initial commit, copy of the script from https://github.com/QIICR/dicom4miccai-handson/tree/master/scripts Re #434
Mapping of features to ISBI is added temporarily, pending resolution of #435
* added README * added sample command line and parameter file that will be use in the @zhenweishi study
Update import order to adhere to coding style (prevents flake8 errors) Additionally, remove usage of pathlib, as it is not available in python 2.7 (It is only part of the std lib since 3.4).
* recognize wavelet features computed with forced 2d * do not require both plastimatch and dcm2niix installed
Update style to follow PyRadiomics Style (2 space indent, logger child of 'radiomics' logger). Additionally, add some minor changes (e.g. use of choices in argument parser, mark methods as static where applicable)
Depends on the functionality added to dcmqi in this commit: QIICR/dcmqi@ef688c4
This corresponds to the v7 of the IBSI document, and was used as a basis for generating featureDict.tsv in resources.
Use updated names of the pyradiomics features, and map them to the IBSI concepts more precisely
The CP is using different (more precise) than in IBSI feature names for some of them. In the future, we could add tools to automatically extract feature nomenclature from the IBSI TeX file and from the DICOM standard, and automatically assemble the mapping table. Added here for the reference. File provided by David Clunie.
fedorov
force-pushed
the
add-pyradiomics-dcm
branch
from
0071c30
to
394d5b3
Compare
Re #434