Adjust Label after resampling medical volume
1 次查看(过去 30 天)
显示 更早的评论
I resampled a medical volume (nifti) following these instructions:
ctFile=medicalVolume('E:\git\maskRCNN\norm\LD\case_00167.nii.gz');
targetVoxelSize=[3.11 1.59 1.59];
ratios = targetVoxelSize ./ ctFile.VoxelSpacing;
origSize = size(ctFile.Voxels);
newSize = round(origSize ./ ratios);
origRef = ctFile.VolumeGeometry;
origMapping = intrinsicToWorldMapping(origRef);
tform = origMapping.A;
newMapping4by4 = tform.* [ratios([2 1 3]) 1];
newMapping = affinetform3d(newMapping4by4);
newRef = medicalref3d(newSize,newMapping);
newRef = orient(newRef,origRef.PatientCoordinateSystem);
newCTFile = resample(ctFile,newRef,Method='linear');
write(newCTFile,"E:\git\maskRCNN\norm\LD\case_00167");
ctFile is an image with Voxels 512x512,103 , taken from the kits19 challenge (https://github.com/neheller/kits19/tree/master/data)
However, the label (also a nifti file) that marked a organ on the original image (ctFile), does not mark the same area on the new, resampled image (newCTFile). I assume I need to tranform the label too. How do I do that?
1 个评论
cr
2022-11-14
Please consider providing more information like data sizes, code etc for community to be able to understand and possibly answer.
采纳的回答
Harsha
2022-11-18
Hi Odo Luo
Consider the Labels Nifti files also as a medical volume and apply all the transformations(that are performed on the CT file) as given in the link mentioned by you.
更多回答(0 个)
另请参阅
类别
在 Help Center 和 File Exchange 中查找有关 Biomedical Imaging 的更多信息
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!