Pushed new branch to rMITK MITK: bugfix/T30334-FixPlaneGeometryDataToSurfaceFilter.

Live wire tool (and Lasso) is already reworked.

This fitting task was applied not to many cases, therefore AVID batch processing was not required and fitting was done in MITK using the formula parser.

SegmentAnyBone is SAM with an extra attention pathway as well, pretrained on MRI dataset.
They have trained the visual transformer vit_t type model and released new pretrained weights. From code perspective, they have modified down SAM code to include attention map and packs with it in the repo.
Salient points:

Is solved by the pixel value view.

Deleted branch from rMITK MITK: bugfix/T30321-FixVTK.

Pushed new branch to rMITK MITK: bugfix/T30321-FixVTK.

VTK 9.3 has a build issue in debug mode with Visual Studio. It's a known issue but it is not yet fixed upstream.

I also vote for 3.

The difference between my build tree version and the installed version is that the former is using the wayland or wayland-egl backend, while the latter is using the xcb backend. Forcing the build tree version to use xcb results in the same GLEW warnings, which is good, so I can now try to get rid of it.

Code needs to be adapted to API changes, which cannot be done without domain knowledge.

Pushed new branch to rMITK MITK: bugfix/T30321-Ubuntu_23.10_Compatibility.

While compiling VTK 9.3.0, I noticed the following warning which may be interesting:

Conclusion: still needs subtasks

• can the binary tag be removed?
• convert binary images easier into segmentations
• offer python utility package as a way to convert -> T29389

Conclusion: makes sense to do, will be tackled implicitly in the future.

Discussion: the listed parts can be removed + semantic relations can also be removed (in its current implementation state, because it would need to be reimplemented with property relation rules).

Has been clarified

Conclusion: In general it makes sense, but we would want to get rid of the "locked state" of the perspective. Needs further research if the locked state can be removed easily or be made more clearly visible, e.g. by a UI element.

• To configure the MITK superbuild, I had to install libegl1-mesa-dev.
• To run the Qt online installer, I had to install libxcb-xinerama0.

The attempt of Qt to look for the wayland platform plugin can be disabled by adding export QT_QPA_PLATFORM=xcb to CMake/RunInstalledApp.sh, which is preferrable since we do not distribute the wayland platform plugin anyway.

Deleted branch from rMITK MITK: release/T30315-2024-Week-05.

Pushed new branch to rMITK MITK: release/T30315-2024-Week-05.

Reason: see my comment above.

Thank you for looking into that. Let's discuss it further in the next meeting, but I think we should try to get it available in the next release.
For Boundingboxes, I would align with the Bounding Box interactions we have to build up at some point for generating detection labels.

MedSAM is same old SAM, pretrained using medical image-based dataset.
They have trained the visual transformer vit_b type model and released new pretrained weights. So fundamentally, there is no change in architecture. However, from code perspective, they have modified/trimmed down SAM code to their application and packs with it in the repo.
Salient points:

Pushed new branch to rMITK MITK: feature/T30294-Remove_LabelSet_class.

Ok, I have updated the task description.

I think the slicer plugin is not so interesting, but the MedSAM branch it used LiteMedSAM https://github.com/bowang-lab/MedSAM/blob/LiteMedSAM/README.md.

I think I found the problem while doing the refactoring of the LabelSetImage (T30294). Should be verified as soon as T30294 is tested/merged.

Closed, we put everythin in own installer and solve it by configuration:
T30284
T30310

Pushed new branch to rMITK MITK: feature/T30152-MoveIGTIntoExtension.

Pushed new branch to rMITK MITK: feature/T30171-python-wrapping-new.