MR-assisted PET respiratory motion correction using deep-learning based short-scan motion fields

Abstract

Purpose: We evaluated the impact of PET respiratory motion correction (MoCo) in a phantom and patients. Moreover, we proposed and examined a PET MoCo approach using motion vector fields (MVFs) from a deep-learning reconstructed short MRI scan.

Methods: The evaluation of PET MoCo was performed in a respiratory motion phantom study with varying lesion sizes and tumor to background ratios (TBRs) using a static scan as the ground truth. MRI-based MVFs were derived from either 2000 spokes (MoCo₂₀₀₀ , 5-6 min acquisition time) using a Fourier transform reconstruction or 200 spokes (MoCo_P2P200 , 30-40 s acquisition time) using a deep-learning Phase2Phase (P2P) reconstruction and then incorporated into PET MoCo reconstruction. For six patients with hepatic lesions, the performance of PET MoCo was evaluated using quantitative metrics (SUV_max , SUV_peak , SUV_mean , lesion volume) and a blinded radiological review on lesion conspicuity.

Results: MRI-assisted PET MoCo methods provided similar results to static scans across most lesions with varying TBRs in the phantom. Both MoCo₂₀₀₀ and MoCo_P2P200 PET images had significantly higher SUV_max , SUV_peak , SUV_mean and significantly lower lesion volume than non-motion-corrected (non-MoCo) PET images. There was no statistical difference between MoCo₂₀₀₀ and MoCo_P2P200 PET images for SUV_max , SUV_peak , SUV_mean or lesion volume. Both radiological reviewers found that MoCo₂₀₀₀ and MoCo_P2P200 PET significantly improved lesion conspicuity.

Conclusion: An MRI-assisted PET MoCo method was evaluated using the ground truth in a phantom study. In patients with hepatic lesions, PET MoCo images improved quantitative and qualitative metrics based on only 30-40 s of MRI motion modeling data.

Keywords: CAPTURE; P2P; PET/MRI; deep learning; free-breathing; respiratory motion correction.