Steve Pieper

After further testing is sees this work with a target of 0.5 or higher but fails with .4 or lower.

Changing line 465 of DistanceMapBasedRegistration to: ``` parameters = {'inputImageName':parameterNode.GetAttribute('FixedLabelSmoothedID'),'outputMeshName':fixedModel.GetID(), 'decimationConst': 1.0} ``` and line 480 to: ``` parameters = {'inputImageName':parameterNode.GetAttribute('MovingLabelSmoothedID'),'outputMeshName':movingModel.GetID(), 'decimationConst': 1.0} ``` works around my issue for now.

FYI @fedorov

This is probably a core slicer issue with tag cache performance and nothing specific to the PET/DICOM extension.

As an update: I used numpy to adjust the CT data range to be 0-255 stored in a uint8 array and then created a new node and copied over the...

Here are the steps to make a volume that passes the embedding: ``` >>> n = getNode("4:*") >>> a = arrayFromVolume(n) >>> aa = a + 1024 >>> aa =...

Once I used this data, the embeddings were calculated and I was able to create segments and enter the point selection mode. However my points never seemed to be accepted...

I'll try with one of your tif files, but in general tif is not a good medical image file format since it doesn't preserve the image orientations [see these notes](https://www.slicer.org/wiki/Coordinate_systems)...

It looks like the issue is this code: https://github.com/fsemerar/SlicerTomoSAM/blob/b9f5e6d92974292800cf67d93d3f638c35880f6a/TomoSAM/tomosam.py#L486-L497 When you load data from a file there can be a storage node but no `DICOM.instanceUIDs` so it should be easy...

Just to report: I was able to download your tiff file of the CT and was able to calculate the embeddings. But when I add a point I get the...