Login / Signup

Parameters Influencing PET Imaging Features: A Phantom Study with Irregular and Heterogeneous Synthetic Lesions.

Francesca GallivanoneMatteo InterlenghiDaniela D'AmbrosioGiuseppe TrifiròIsabella Castiglioni
Published in: Contrast media & molecular imaging (2018)
The choice of the segmentation method has a strong impact on the stability of radiomic features (less than 20% can be considered stable features). Reconstruction affects the estimate of radiomic features (only 26% are stable). Thirty-one radiomic features (53%) resulted to be reproducible, 11 of them are able to discriminate heterogeneity. Among these, we found a subset of 3 radiomic features strongly correlated with GS heterogeneity index that can be suggested as good features for retrospective evaluations.
Keyphrases
  • pet imaging
  • single cell
  • deep learning
  • machine learning