Brain tissue segmentation of brain tumor patients

Dear all,

We collected MRI data (T1w, T2w, DTI and fMRI) from some brain tumour patients and wanted to segment their T1w images to obtain grey and white matter portions. As previous studies have suggested that the original function may still be preserved in tumour-infested brain tissue, we did not use a tumour mask to generate the masked T1w image. We tried using CAT12 for automatic tissue segmentation, but the resulting grey matter tends to encapsulate the tumour-infested white matter region area as well, so I wonder if there is any more accurate method or pipeline for segmenting the brain tissue of tumour patients.

Best regards,



Have you considered SynthSeg from FreeSurfer? WMH-SynthSeg - Free Surfer Wiki


Dear Steven,

Thank you for the suggestion, I haven’t tried SyhthSeg, but I think I can try to do the segmantation again with it.

Best regard,