-
Notifications
You must be signed in to change notification settings - Fork 481
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
How can I convert DCM to NRRD with SimpleITK? #361
Comments
The approach you use may not result in geometrically ordered slices. You can use existing tools, such as dcm2niix or plastimatch to convert a DICOM series into a volume. Prior to running the converter, you will need to ensure the input DICOM folder contains just one series, and that series is a scalar volume. |
@fedorov Thank you for your reply. Can PyRadiomics process nii directly? |
Yes |
OK,I got it. Thanks again! |
After I used dcm2nii to convert a DICOM series into a nii volume, the direction changed and led to mismatch between the image and segmentation. My image is DICOM and segmentation is Nifti, I want to process them in Nii format. Why the problem happened? |
The only way to investigate this is to look at the dataset where you observed this issue. |
how to use stk-snap to make mask?when I segmentate dcm format file used to pyradiomics。 |
Hi everyone!
I'm trying to use the PyRadiomics to extract features from a serious DICOM images(2D), and I have two questions.
As the document says, PyRadiomics can not process the DCM image directly, so I translate my data from DCM to NRRD by simpleITK, code like this:
`
reader = sitk.ImageSeriesReader()
dicomReader = reader.GetGDCMSeriesFileNames(inputPath) #input is the DCM file path
reader.SetFileNames(dicomReader)
dicoms = reader.Execute()
sitk.WriteImage(dicoms, fileName) #fileName like "brain.nrrd"
`
Then, I input a NRRD file as img, which generated by above codes, and a nii(NIFTI) file as mask, it works! But I'm not sure if this is feasible, what do you think?
How to determine the appropriate parameters to extract good features? Do you have any good suggestions?
Thanks a lot.
Qi Chen
The text was updated successfully, but these errors were encountered: