PETTumorSegmentation: Semi-automatic segmentation of tumors in PET

3D Slicer extension for "just enough interaction" segmentation


PETTumorSegmentation is an extension of 3D Slicer that provides “just enough interaction” tools for automated segmentation of metabolically active regions in Positron Emission Tomography (PET) images. The extension provides segmentation tools implemented as “effects” for the 3D Slicer Segment Editor and legacy Editor modules. As such, these tools can be used in combination with the other automated and manual segmentation approaches already available in those modules. These effects are also available within the Quantitative Reporting module of 3D Slicer.


Installation: PETTumorSegmentation can be installed as an extension to 3D Slicer via 3D Slicer Extension manager.

Documentation: link

Source code: link


  • Beichel RR, Van Tol M, Ulrich EJ, et al. Semiautomated segmentation of head and neck cancers in 18F-FDG PET scans: A just-enough-interaction approach. Med Phys. 2016;43(6):2948–2964 link - This publication describes in detail the algorithm implemented in the module, and its evaluation in a clinical dataset.

  • Fedorov A, Clunie D, Ulrich E, et al. DICOM for quantitative imaging biomarker development: a standards based approach to sharing clinical data and structured PET/CT analysis results in head and neck cancer research. PeerJ. 2016;4:e2057 link - This publication describes the dataset that includes segmentations produced using the PETTumorSegmentation tool.

  • Beichel RR, Smith BJ, Bauer C, et al. Multi-site quality and variability analysis of 3D FDG PET segmentations based on phantom and clinical image data. Med Phys. 2017;44(2):479–496 link. - This publication applied the PETTumorSegmentationTool in the context of a community challenge organized by the NCI Quantitative Imaging Network (QIN)

Grants support

  • U01 CA140206
  • U24 CA180918

Dialogue & Discussion