Stability of radiomic features from positron emission tomography images using advanced reconstruction algorithms

Introduction: While the traditional ordered subset expectation maximization (OSEM) algorithm is widely recognized as the gold standard in positron emission tomography (PET) imaging, various innovative methods are being introduced, such as HYPER iterative (IT) based on Bayesian penalized likelihood algorithm, HYPER deep learning reconstruction (DLR), and HYPER deep progressive reconstruction (DPR). These advanced reconstruction methods have been reported to provide superior image quality characteristics compared to OSEM. However, it is not clear what contribution advanced reconstruction algorithms make to radiomic features. In this study, we compared the repeatability and reproducibility of radiomic features obtained from PET images according to the reconstruction algorithm used advanced reconstruction algorithms or OSEM to understand the potential variations and implications of using advanced reconstruction techniques in PET-based radiomics.

Methods: We used a heterogeneous phantom with acrylic spherical beads (4- or 8-mm diameter), filled with 18F. PET images were acquired and reconstructed using OSEM, IT, DLR, and DPR. Radiomic features were calculated using SlicerRadiomics. Radiomic feature repeatability was assessed using the coefficient of variance (COV) and intraclass correlation coefficient (ICC), and inter-acquisition time reproducibility was assessed using the concordance correlation coefficient (CCC).

Results: For the 4- and 8-mm diameter beads phantom, the proportion of radiomic features with a COV <10% was higher for IT, DLR, and DPR than for OSEM.The proportion of radiomic features with ICCs >0.75 was the highest for IT and DPR (14.0% and 15.1%, respectively) and for DLR (8.6%) in the 4-mm and 8-mm diameter beads phantoms, respectively. In the inter-acquisition time reproducibility analysis, the combinations of 3- and 5-min exhibited the highest reproducibility in both phantoms, with IT showing the highest proportion of radiomic features with CCC >0.8.

Conclusions: Advanced reconstruction methods, particularly IT, provided enhanced stability of radiomic features compared with OSEM, suggesting their potential for optimal image reconstruction in PET-based radiomics, offering potential benefits in clinical diagnostics and prognostics.