Abstract
PURPOSE: Precise quantification of myocardial blood flow (MBF) and flow reserve (MFR) in (18)F-flurpiridaz PET significantly relies on motion correction (MC). However, the manual frame-by-frame correction leads to significant inter-observer variability, time-consuming, and requires significant experience. We propose a deep learning (DL) framework for automatic MC of (18)F-flurpiridaz PET. METHODS: The method employs a 3D-ResNet based architecture that takes 3D PET volumes and outputs motion vectors. It was validated using 5-fold cross-validation on data from 32-sites of a Phase-III clinical trial (NCT01347710). Manual corrections from two experienced operators served as ground truth, and data augmentation using simulated vectors enhanced training robustness. The study compared the DL approach to both manual and standard non-AI automatic MC methods, assessing agreement and diagnostic accuracy using minimal segmental stress MBF and MFR. RESULTS: The area under the receiver operating characteristic curves (AUC) for significant CAD were comparable between DL-MC stress MBF, manual-MC stress MBF from Operators (AUC = 0.897, 0.892 and 0.889, respectively; p > 0.05), standard non-AI automatic MC (AUC = 0.877; p > 0.05) and significantly higher than No-MC (AUC = 0.835; p < 0.05). Similar findings were observed with MFR. The 95% confidence limits for agreement with the operator were ± 0.49 (mean difference = 0.00) for MFR and ± 0.24 ml/g/min (mean difference = 0.00) for stress MBF. CONCLUSION: DL-MC is significantly faster but diagnostically comparable to manual-MC. The quantitative results obtained with DL-MC for stress MBF and MFR are in excellent agreement with those manually corrected by experienced operators compared to standard non-AI automatic MC in patients undergoing (18)F-flurpiridaz PET-MPI.