Further evaluation using a larger training cohort is required for more accurate and robust performance.Ĭombined PET/MRI has gradually gained ground in routine clinical practice. ConclusionsĮxperimental results demonstrated that a DL approach for whole-body PET AC in PET/MRI is feasible and allows for more accurate results compared with conventional methods. The largest errors were observed in the lung, while the smallest biases were observed in the brain and liver. The regional analysis showed that the average errors and the variability for PET sCT were lower than PET Atlas in all regions. The absolute percentage difference in PET quantification for the entire image was 6.1% for PET sCT and 11.2% for PET Atlas. We found an excellent voxel-by-voxel correlation between PET CT and PET sCT ( R 2 = 0.98). Our DL-based method resulted in better estimates of AC maps with a mean absolute error of 62 HU, compared to 109 HU for the atlas-based method. In addition, region-specific analysis was performed to compare the performances of the methods in brain, lung, liver, spine, pelvic bone, and aorta. The accuracy of the AC maps and reconstructed PET images were assessed by performing a voxel-wise analysis and calculating the quantification error in SUV obtained using DL-based sCT (PET sCT) and a vendor-provided atlas-based method (PET Atlas), with the CT-based reconstruction (PET CT) serving as the reference. The network was pretrained with region-specific images. We performed MRI truncation correction and employed co-registered MRI and CT images for training and leave-one-out cross-validation. Materials and methodsįifteen patients underwent PET/CT followed by PET/MRI with whole-body coverage from skull to feet. The aim of this study is to investigate a deep learning (DL) method to generate voxel-based synthetic CT (sCT) from Dixon MRI and use it as a whole-body solution for PET AC in a PET/MRI system. However, its whole-body implementation is still challenging due to anatomical variations and the limited MRI field of view. Deep convolutional neural networks have demonstrated robust and reliable PET attenuation correction (AC) as an alternative to conventional AC methods in integrated PET/MRI systems.
0 Comments
Leave a Reply. |