Impact of image reconstruction method on dose distributions derived from 90Y PET images: phantom and liver radioembolization patient studies.

Abstract

PET images acquired after liver 90Y radioembolization therapies are typically very noisy, which significantly challenges both visualization and quantification of activity distributions. To improve their noise characteristics, regularized iterative reconstruction algorithms such as block sequential regularized expectation maximization (Q.Clear for GE Healthcare, USA) have been proposed. In this study, we aimed to investigate the effects which different reconstruction algorithms may have on patient images, with reconstruction parameters initially narrowed down using phantom studies. Moreover, we evaluated the impact of these reconstruction methods on voxel-based dose distribution in phantom and patient studies (lesions and healthy livers). The International Electrotechnical Commission (IEC)/NEMA phantom, containing six spheres, was filled with 90Y and imaged using a GE Discovery 690 PET/CT scanner with time-of-flight enabled. The images were reconstructed using Q.Clear (with β parameter ranging from 0 to 8000) and ordered subsets expectation maximization. The image quality and quantification accuracy were evaluated by computing the hot ([Formula: see text]) and cold ([Formula: see text]) contrast recovery coefficients, background variability (BV) and activity bias. Next, dose distributions and dose volume histograms were generated using MIM® software's SurePlan LiverY90 toolbox. Subsequently, parameters optimized in these phantom studies were applied to five patient datasets. Dose parameters, such as Dmax, Dmean, D70, and V100Gy, were estimated, and their variability for different reconstruction methods was investigated. Based on phantom studies, the β parameter values optimized for image quality and quantification accuracy were 2500 and 300, respectively. When all investigated reconstructions were applied to patient studies, Dmean, D50, D70, and V100Gy showed coefficients of variation below 8%; whereas the variability of Dmax was up to 30% for both phantom and patient images. Although β = 300-1000 would provide accurate activity quantification for a region of interest, when considering activity/dose voxelized distribution, higher β value (e.g. 4000-5000) would provide the greatest accuracy for dose distributions. In this 90Y radioembolization PET/CT study, the β parameter in regularized iterative (Q.Clear) reconstruction was investigated for image quality, accurate quantification and dose distributions based on phantom experiments and then applied to patient studies. Our results indicate that more accurate dose distribution can be achieved from smoother PET images, reconstructed with larger β values than those yielding the best activity quantifications but noisy images. Most importantly, these results suggest that quantitative measures, which are commonly used in clinics, such as SUVmax or SUVpeak( equivalent of Dmax), should not be employed for 90Y PET images, since their values would highly depend on the image reconstruction.