DeepPVC: Prediction of A Partial Volume-Corrected Map for Brain Positron Emission Tomography Studies Via a Deep Convolutional Neural Network

Abstract Background Partial volume correction with anatomical magnetic resonance (MR) images (MR-PVC) is useful for accurately quantifying tracer uptake on brain positron emission tomography (PET) images. However, MR segmentation processes for MR-PVC are time-consuming and prevent the widespread clinical use of MR-PVC. Here we aimed to develop a deep learning model to directly predict PV-corrected maps from PET and MR images, ultimately improving the MR-PVC throughput. Methods We used MR T1-weighted and [11C]PiB PET images as training input data from 156 participants from the Alzheimer’s Disease Neuroimaging Initiative database using the U-Net model. We calculated PV-corrected maps as the training target using the region-based voxel-wise PVC method. The trained deepPVC model was validated by six-fold cross-validation and then tested using MR T1-weighted and [11C]PiB PET images from 36 participants acquired at sites other than the training dataset. We calculated the structural similarity index (SSIM) of the PV-corrected maps and intraclass correlation (ICC) of the PV-corrected standardized uptake value (SUV) between the RBV PVC and deepPVC as indicators for validation and testing. Results A high SSIM (0.810 ± 0.042) and ICC (0.867 ± 0.086) were observed in the validation and test data (SSIM, 0.828 ± 0.032; ICC, 0.910 ± 0.053). The computation time required to predict a PV-corrected map for a participant (48 s without a graphics processing unit) was much shorter than that for the RBV PVC and MR segmentation processes. Conclusion These results suggest that the deepPVC model directly predicts PV-corrected maps from MR and PET images and improves the throughput of MR-PVC by skipping the MR segmentation processes.