Austrian researchers who used 13 PET/CT systems for whole-body phantom imaging found that the gray-level co-occurrence metric and shape features had the lowest sensitivity to variations in PET imaging systems on a one-way analysis of variance, with the use of point-spread function, narrow Gaussian post-filtering and small voxel sizes all minimizing feature variations. The findings in the Journal of Nuclear Medicine should prompt individual data processing configuration selection for every feature and prioritization of high-quality feature extraction in radiomic studies, researchers said.
Features with least PET system variation sensitivity identified
Sign up for SNMMI SmartBrief
Nuclear medicine and molecular imaging news
Get the intelligence you need: news and information that is changing your industry today, hand-curated by our professional editors from thousands of sources and delivered straight to your inbox.