Torso synthetic CT generation by integrating deep learning and segmentation for FDG-PET/MR attenuation correction

<i>Introduction.</i>Positron Emission Tomography/Magnetic Resonance (<b>PET/MR</b>) offers benefits over PET/CT including simultaneous PET and MR acquisition, intrinsic spatial registration accuracy, MR-based functional information, and superior soft tissue contrast. However, accurate attenuation correction (<b>AC</b>) for PET remains challenging as MR signals do not directly correspond to attenuation. Using deep learning algorithms that learn complex relationships, we generate synthetic CT (<b>sCT</b>) from MR for AC. Our novel method for AC, merges deep learning with threshold-based segmentation, to produce an AC map for the entire torso from Dixon MR images, which heretofore has not been demonstrated.<i>Method</i>. Twenty-nine prospectively collected, paired FDG-PET/CT and MR datasets were used for training and validation using the U-net Residual Network conditional Generative Adversarial Network integrated with tissue segmentation (<b>URcGAN</b>_<b>mod</b>) from Dixon MR data. Our application focused on torso (base of the skull to mid-thigh) AC, a common but challenging field of view (FOV). Performance was compared to that of 4 previously published methods.<i>Results</i>. Using 15 paired datasets for training and 14 independent datasets for testing, the URcGAN_modgenerates an accurate torso sCT with a mean absolute difference of 32 ± 4 HU per voxel. When applied for AC for FDG images, and considering evaluable (SUV ≥ 0.1 g/ml) voxels across all regions of interest, absolute values of the differences were within 4.4% from those determined using the measured CT for AC. Reproducibility was excellent with less than 3.5% standard deviation. The results demonstrate the accuracy and precision of URcGAN_modmethod for torso sCT generation for quantitatively accurate MR-based AC (<b>MRAC</b>), exceeding the comparison methods.<i>Conclusion</i>. Combining deep learning and segmentation enhances MRAC accuracy in torso FDG-PET/MR, improves SUV accuracy throughout the torso, achieves less than 4.4% SUV error, and outperforms comparison methods. Given the excellent sCT and SUV accuracy and precision, our proposed method warrants further studies for quantitative longitudinal multicenter trials.