Open rakshrma opened 1 week ago
The running of the segmentation model for the contrast phase segmentation is quite fast since it only uses a few ROIs and a low resolution model. The runtime you save would not be too big. Therefore this was not on the agenda so far.
totalseg_get_phase.get_ct_contrast_phase method runs the segmentation for contrast prediction. For cases, where the segmentations are already generated and user is only interested to get contrast phase, it will be very useful to input earlier generated segmentations to this method without re-computation of segmentation. Are you currently working on enabling this feature? If not, I'll be happy to contribute to that.