TomoSAM: a 3D Slicer extension using SAM for tomography segmentation
This provides a solution for researchers and practitioners in tomography imaging who need efficient segmentation, but it is incremental as it applies an existing method to a new domain.
The authors tackled the problem of laborious manual segmentation for complex 3D tomography datasets by integrating the Segment Anything Model (SAM) into 3D Slicer, resulting in a tool that enables zero-shot segmentation based on user clicks.
TomoSAM has been developed to integrate the cutting-edge Segment Anything Model (SAM) into 3D Slicer, a highly capable software platform used for 3D image processing and visualization. SAM is a promptable deep learning model that is able to identify objects and create image masks in a zero-shot manner, based only on a few user clicks. The synergy between these tools aids in the segmentation of complex 3D datasets from tomography or other imaging techniques, which would otherwise require a laborious manual segmentation process. The source code associated with this article can be found at https://github.com/fsemerar/SlicerTomoSAM