Pseudo CT Image Synthesis and Bone Segmentation From MR Images Using Adversarial Networks With Residual Blocks for MR-Based Attenuation Correction of Brain PET Data
Li Tao, Jonathan Fisher, Emily Anaya, Xin Li, Craig S. Levin
Abstract
For photon attenuation correction, current positron emission tomography systems combined with magnetic resonance imaging (PET/MR) imaging systems typically use methods based on MR image segmentation with subsequent assignment of empirical attenuation coefficients in PET image reconstruction. Delineation of bone in MR images has been challenging, especially in the head and neck areas, due to the difficulty of separating bone from air. In this article, we study deep learning techniques that assist the MR-based attenuation correction (MRAC) process for PET/MR systems, with focus on the brain region. We use a generative adversarial network (GAN) with residual blocks in a conditional setting for this task. We studied the performance of the designed network on image translation and segmentation tasks, which are essential for MRAC. For both tasks, the network generates pseudo CT images that resemble real CT images with normalized pixel value difference of around 5% and structural similarity (SSIM) index of around 0.8.