search

JacobBumgarner / VesselVio

An open-source application for the analysis and visualization of segmented vasculature datasets
https://jacobbumgarner.github.io/VesselVio/
GNU General Public License v3.0
99 stars 21 forks source link

[Feature Request]: Option to export the skeleton as an image #52

Closed saskra closed 1 year ago

saskra commented 2 years ago

Describe the feature you would like to be added.

As the title says, it would be handy for me to be able to export the skeleton as an image so I could visually compare it to the segmentation and results of other skeletonization algorithms. Alternatively, I would appreciate tips on if and how I can convert the GraphML file back to a skeleton and save it as an image.

Code of Conduct

PS: Did you actually change anything besides the speed on the Lee94 skeleton algorithm? Despite the same segmentation and skeletonization (Lee94 using scikit), I got different results with other software. Or is that due to post-processing?

JacobBumgarner commented 1 year ago

Hi @saskra , I have had extremely minimal time to maintain the app, so I don't think I'm going to add this feature. If you are interested in creating a PR for the feature, I'd be happy to check it over.

As far as your other question, I implemented algorithm as it was described in the original Lee94 paper. It does produce minimally different skeletons than the scikit algorithm for one reason: The direction of the scans are different. This minimally affects the final shape of the skeleton, but I didn't observe significant differences between mine & the scikit learn skeleton voxel counts. If you observe other implementations of this algorithm that float around (many in MATLAB), you will notice similar minor differences.

saskra commented 1 year ago

Thanks for your answer! In fact, after a change of job, I no longer work on this topic, so there is no longer a need from my side.