4D respiratory motion-corrected Rb-82 myocardial perfusion PET image reconstruction

Abstract

Routine clinical myocardial perfusion (MP) PET imaging involves the use of cardiac gating only. Nonetheless, respiratory motion of the heart can considerably degrade the quality of MP images and the quantitative accuracy of myocardial uptake estimates. We first performed a quantitative evaluation of the degrading contributions of cardiac (C) and respiratory (R) motion, as well as non-motion factors of Rb-82 positron range, photon non-collinearity, crystal scattering and penetration. For a normal human simulated phantom, we showed that the combination of all above factors resulted in −48% underestimation of myocardial activity, while corrections for all non-motion factors resulted in 21%, 36% and 41% underestimated myocardial activities in the presence of C, R and C&R motion. This means that compensation for respiratory motion must be considered as critical towards achieving overall motion compensation and/or resolution modeling. To achieve respiratory motion compensation, we used translation motion vectors to first match respiratory-only gated images to the end-expiration reference frame. Next, for each cardiac gate, a 4D EM reconstruction algorithm was applied to the R-gated data within that cardiac phase. Three techniques were compared involving reconstructions of (a) a single R-gate only, and all R-gates (b) without and (c) with respiratory motion correction (MC). Using simulated PET data, quantitative comparisons of noise vs. bias trace-off curves indicated notable improvements for the proposed 4D respiratory MC method. Using CHO analysis as applied to the task of perfusion defect detection, ROC analysis of the three methods resulted in AUC values of 0.610±0.039, 0.645±0.038 and 0.821±0.029. The CLABROC statistical test revealed that the proposed MC technique significantly outperformed the other two methods in the task of defect detection.