Background: Recently, the paradigm of computed tomography (CT) reconstruction has shifted as the deep learning technique evolves. In this study, we proposed a new convolutional neural network (called ADAPTIVE-NET) to perform CT image reconstruction directly from a sinogram by integrating the analytical domain transformation knowledge. Methods: In the proposed ADAPTIVE-NET, a specific network layer with constant weights was customized to transform the sinogram onto the CT image domain via analytical back-projection. With this new framework, feature extractions were performed simultaneously on both the sinogram domain and the CT image domain. The Mayo low dose CT (LDCT) data was used to validate the new network.In particular, the new network was compared with the previously proposed residual encoder-decoder (RED)-CNN network. For each network, the mean square error (MSE) loss with and without VGGbased perceptual loss was compared. Furthermore, to evaluate the image quality with certain metrics, the noise correlation was quantified via the noise power spectrum (NPS) on the reconstructed LDCT for each method.Results: CT images that have clinically relevant dimensions of 512×512 can be easily reconstructed from a sinogram on a single graphics processing unit (GPU) with moderate memory size (e.g., 11 GB) by ADAPTIVE-NET. With the same MSE loss function, the new network is able to generate better results than the RED-CNN. Moreover, the new network is able to reconstruct natural looking CT images with enhanced image quality if jointly using the VGG loss. Conclusions:The newly proposed end-to-end supervised ADAPTIVE-NET is able to reconstruct highquality LDCT images directly from a sinogram.

Although perovskite wafers with a scalable size and thickness are suitable for direct X‐ray detection, polycrystalline perovskite wafers have drawbacks such as the high defect density, defective grain boundaries, and low crystallinity. Herein, PbI2‐DMSO powders are introduced into the MAPbI3 wafer to facilitate crystal growth. The PbI2 powders absorb a certain amount of DMSO to form the PbI2‐DMSO powders and PbI2‐DMSO is converted back into PbI2 under heating while releasing DMSO vapor. During isostatic pressing of the MAPbI3 wafer with the PbI2‐DMSO solid additive, the released DMSO vapor facilitates in situ growth in the MAPbI3 wafer with enhanced crystallinity and reduced defect density. A dense and compact MAPbI3 wafer with a high mobility‐lifetime (µτ) product of 8.70 × 10−4 cm2 V−1 is produced. The MAPbI3‐based direct X‐ray detector fabricated for demonstration shows a high sensitivity of 1.58 × 104 µC Gyair−1 cm−2 and a low detection limit of 410 nGyair s−1.

Sparse-view CT is a promising approach in reducing the X-ray radiation dose in clinical CT imaging. However, the CT images reconstructed from the conventional filtered backprojection (FBP) algorithm suffer from severe streaking artifacts. Iterative reconstruction (IR) algorithms have been widely adopted to mitigate these streaking artifacts, but they may prolong the CT imaging time due to the intense data-specific computations. Recently, model-driven deep learning (DL) CT image reconstruction method, which unrolls the iterative optimization procedures into the deep neural network, has shown exciting prospect in improving the image quality and shortening the reconstruction time. In this work, we explore the generalized unrolling scheme for such iterative model to further enhance its performance on sparse-view CT imaging. By using it, the iteration parameters, regularizer term, data-fidelity term and even the mathematical operations are all assumed to be learned and optimized via the network training. Results from the numerical and experimental sparse-view CT imaging demonstrate that the newly proposed network with the maximum generalization provides the best reconstruction performance.