https://www.selleckchem.com/ .Low dose X-ray computed tomography (LDCT) is desirable for reduced patient dose. This work develops image reconstruction methods with deep learning (DL) regularization for LDCT. Our methods are based on unrolling of proximal forward-backward splitting (PFBS) framework with data-driven image regularization via deep neural networks. In contrast with PFBS-IR that utilizes standard data fidelity updates via iterative reconstruction (IR) method, PFBS-AIR involves preconditioned data fidelity updates that fuse analytical reconstruction (AR) method and IR in a synergistic way, i.e., fused analytical and iterative reconstruction (AIR). The results suggest that DL-regularized methods (PFBS-IR and PFBSAIR) provided better reconstruction quality from conventional wisdoms (AR or IR). In addition, owing to AIR, PFBS-AIR noticeably outperformed PFBS-IR, and another DL-based postprocessing method FBPConvNet. © 2020 Institute of Physics and Engineering in Medicine.OBJECTIVE Computational current flow models of spinal cord stimulation (SCS) are widely used in device development, clinical trial design, and patient programming. Proprietary models of varied sophistication have been developed. An open-source model with state-of-the-art precision would serve as a standard for SCS simulation. APPROACH We developed a sophisticated SCS modeling platform, named Realistic Anatomically Detailed Open-Source Spinal Cord Stimulation (RADO-SCS) model. This platform consists of realistic and detailed spinal cord and ancillary tissues anatomy derived based on prior imaging and cadaveric studies. In our finite element model of the T9-T11 spine levels, we represented the following tissues vertebrae, intervertebral disc, epidural space, epidural space vasculature, dura mater, dural sac, intraforaminal tissue, cerebrospinal fluid (CSF), whitematter, spinal cord vasculature, Lissauer's tract, gray matter, dorsal and ventral roots and rootlets, dorsal root ganglion (DRG), sym