High performance X-ray detector with ultra-high spatial and temporal resolution are crucial for biomedical imaging. This study reports a dynamic direct-conversion CMOS X-ray detector assembled with screen-printed CsPbBr₃, whose mobility-lifetime product is 5.2 × 10⁻⁴ cm² V^–1 and X-ray sensitivity is 1.6 × 10⁴ µC Gy_air^–1 cm^–2. Samples larger than 5 cm $$\times$$× 10 cm can be rapidly imaged by scanning this detector at a speed of 300 frames per second along the vertical and horizontal directions. In comparison to traditional indirect-conversion CMOS X-ray detector, this perovskite CMOS detector offers high spatial resolution (5.0 lp mm⁻¹) X-ray radiographic imaging capability at low radiation dose (260 nGy). Moreover, 3D tomographic images of a biological specimen are also successfully reconstructed. These results highlight the perovskite CMOS detector’s potential in high-resolution, large-area, low-dose dynamic biomedical X-ray and CT imaging, as well as in non-destructive X-ray testing and security scanning.

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 nGy_air s⁻¹.

Objective. In this work, a dedicated end-to-end deep convolutional neural network, named as Triple-CBCT, is proposed to demonstrate the feasibility of reconstructing three different material distribution volumes from the dual-energy CBCT projection data. Approach. In Triple-CBCT, the features of the sinogram and the CT image are independently extracted and cascaded via a customized domain transform network module. This Triple-CBCT network was trained by numerically synthesized dual-energy CBCT data, and was tested with experimental dual-energy CBCT data of the Iodine-CaCl ₂ solution and pig leg specimen scanned on an in-house benchtop system. Main results. Results show that the information stored in both the sinogram and CT image domains can be used together to improve the decomposition quality of multiple materials (water, iodine, CaCl ₂ or bone) from the dual-energy projections. In addition, both the numerical and experimental results demonstrate that the Triple-CBCT is able to generate high-fidelity dual-energy CBCT basis images. Significance. An innovative end-to-end network that joints the sinogram and CT image domain information is developed to facilitate high quality automatic decomposition from the dual-energy CBCT scans.

Sparse-view CT is a promising approach for reducing the x-ray radiation dose in clinical CT imaging. However, the CT images reconstructed from the conventional filtered backprojection algorithm suffer from severe streaking artifacts. Iterative reconstruction 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, a model-driven deep learning CT image reconstruction method, which unrolls the iterative optimization procedures into a deep neural network, has shown exciting prospects for improving image quality and shortening the reconstruction time. In this work, we explore a generalized unrolling scheme for such an 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 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.

Positron emission tomography (PET) imaging is a noninvasive technique that makes it possible to probe biological metabolic processes in vivo. However, PET image reconstruction is challenging due to the ill-posedness of the inverse problem. Many image reconstruction methods have been proposed over the past few years to improve diagnostic performance. However, most of these methods can compromise the reconstruction of important high-frequency structural details after aggressive denoising. To address this problem, in this work, we propose a novel deep learning method that reconstructs PET images using a cascading back-projection neural network (bpNet). This network consists of a domain translation operation, which acts as prior knowledge, cascaded with a modified encoder-decoder network. The image reconstruction pipeline ranges from the sinogram to the back-projection image and then to the PET image. Quantitative results from simulation data and Derenzo phantom experiments with the small animal PET prototype system developed in our laboratory clearly demonstrate that our proposed method provides favorable reconstructed image quality, especially for low-count PET image reconstruction.