Abstract
Dedicated brain positron emission tomography (PET) devices can provide higher-resolution images with much lower doses compared to conventional whole-body PET systems, which is important to support PET neuroimaging and particularly useful for the diagnosis of neurodegenerative diseases. However, when a dedicated brain PET scanner does not come with a combined CT or transmission source, there is no direct solution for accurate attenuation and scatter correction, both of which are critical for quantitative PET. To address this problem, we propose joint attenuation and scatter correction (ASC) in image space for non-corrected PET (PET(NC)) using deep convolutional neural networks (DCNNs). This approach is a one-step process, distinct from conventional methods that rely on generating attenuation maps first that are then applied to iterative scatter simulation in sinogram space. For training and validation, time-of-flight PET/MR scans and additional helical CTs were performed for 35 subjects (25/10 split for training and test dataset). A DCNN model was proposed and trained to convert PET(NC) to DCNN-based ASC PET (PET(DCNN)) directly in image space. For quantitative evaluation, uptake differences between PET(DCNN) and reference CT-based ASC PET (PET(CT-ASC)) were computed for 116 automated anatomical labels (AALs) across 10 test subjects (1160 regions in total). MR-based ASC PET (PET(MR-ASC)), a current clinical protocol in PET/MR imaging, was another reference for comparison. Statistical significance was assessed using a paired t test. The performance of PET(DCNN) was comparable to that of PET(MR-ASC), in comparison to reference PET(CT-ASC). The mean SUV differences (mean ± SD) from PET(CT-ASC) were 4.0% ± 15.4% (P < 0.001) and -4.2% ± 4.3% (P < 0.001) for PET(DCNN) and PET(MR-ASC), respectively. The overall larger variation of PET(DCNN) (15.4%) was prone to the subject with the highest mean difference (48.5% ± 10.4%). The mean difference of PET(DCNN) excluding the subject was substantially improved to -0.8% ± 5.2% (P < 0.001), which was lower than that of PET(MR-ASC) (-5.07% ± 3.60%, P < 0.001). In conclusion, we demonstrated the feasibility of directly producing PET images corrected for attenuation and scatter using a DCNN (PET(DCNN)) from PET(NC) in image space without requiring conventional attenuation map generation and time-consuming scatter correction. Additionally, our DCNN-based method provides a possible alternative to MR-ASC for simultaneous PET/MRI.