Automatic motion correction for myocardial blood flow estimation improves diagnostic performance for coronary artery disease in ¹⁸F-flurpiridaz positron emission tomography-myocardial perfusion imaging

Background: Motion correction (MC) is critical for accurate quantification of myocardial blood flow (MBF) and flow reserve (MFR) from ¹⁸F-flurpiridaz positron emission tomography (PET) myocardial perfusion imaging (MPI). However, manual correction is time consuming and introduces inter-observer variability. We aimed to validate an automatic MC algorithm for ¹⁸F-flurpiridaz PET-MPI in terms of diagnostic performance for predicting coronary artery disease (CAD). Methods: In total, 231 patients who underwent invasive coronary angiography and rest/pharmacologic stress ¹⁸F-flurpiridaz PET-MPI from the phase III Flurpiridaz trial (NCT01347710) were enrolled. For manual MC, two operators (Reader 1 and Reader 2) shifted each frame's images in three directions. The automatic MC algorithm, initially developed for ⁸²Rb-chloride PET-MPI, was optimized for ¹⁸F-flurpiridaz. Diagnostic performance was compared using minimal segmental MBF/MFR with and without MC to predict obstructive CAD by invasive coronary angiography. Results: Manual MC took 10 minutes per case (both stress and rest) on average, while automatic MC required <10 seconds. The area under the receiver operating characteristic curves (AUCs) for significant CAD using minimal segmental MBF were comparable between automatic and manual MC (AUC = 0.877 automatic, AUC = 0.888 Reader 1 and AUC = 0.892 Reader 2; all P > 0.05). AUCs of minimal segmental MBF with manual and automatic MC were significantly higher than without MC (P < 0.05 for both). Similar findings were observed with minimal segmental MFR. Conclusions: Automatic MC can be performed rapidly, with diagnostic performance for predicting obstructive CAD comparable to manual MC. This method could be utilized for analysis of MBF/MFR in patients undergoing ¹⁸F-flurpiridaz PET-MPI.