Search

Mesoscale volumetric imaging is of great importance for the study of bio-organisms. Among others, optical projection tomography provides unprecedented structural details of specimens, but it requires fluorescence label for chemical targeting. Raman spectroscopic imaging is able to identify chemical components in a label-free manner but lacks microstructure. Here, we present a dual-modality optical-Raman projection tomography (ORPT) technology, which enables label-free three-dimensional imaging of microstructures and components of millimeter-sized samples with a micron-level spatial resolution on the same device. We validate the feasibility of our ORPT system using images of polystyrene beads in a volume, followed by detecting biomolecules of zebrafish and Arabidopsis , demonstrating that fused three-dimensional images of the microstructure and molecular components of bio-samples could be achieved. Last, we observe the fat body of Drosophila melanogaster at different developmental stages. Our proposed technology enables bimodal label-free volumetric imaging of the structure and function of biomolecules in a large sample.

Recently, image-based diagnostic technology has made encouraging and astonishing development. Modern medical care and imaging technology are increasingly inseparable. However, the current diagnosis pattern of Signal-to-Image-to-Knowledge inevitably leads to information distortion and noise introduction in the procedure of image reconstruction (Signal-to-Image). Artificial intelligence (AI) technologies that can mine knowledge from vast amounts of data offer opportunities to disrupt established workflows. In this prospective study, for the first time, we developed an AI-based Signal-to-Knowledge diagnostic scheme for lung nodule classification directly from the CT rawdata (the signal). We found that the rawdata achieved almost comparable performance with CT indicating that we can diagnose diseases without reconstructing images. Meanwhile, the introduction of rawdata could greatly promote the performance of CT, demonstrating that rawdata contains some diagnostic information that CT does not have. Our results break new ground and demonstrate the potential for direct Signal-to-Knowledge domain analysis.

BACKGROUND: Projection tomography (PT) is a very important and valuable method for fast volumetric imaging with isotropic spatial resolution. Sparse-view or limited-angle reconstruction-based PT can greatly reduce data acquisition time, lower radiation doses, and simplify sample fixation modes. However, few techniques can currently achieve image reconstruction based on few-view projection data, which is especially important for in vivo PT in living organisms. METHODS: A 2-stage deep learning network (TSDLN)-based framework was proposed for parallel-beam PT reconstructions using few-view projections. The framework is composed of a reconstruction network (R-net) and a correction network (C-net). The R-net is a generative adversarial network (GAN) used to complete image information with direct back-projection (BP) of a sparse signal, bringing the reconstructed image close to reconstruction results obtained from fully projected data. The C-net is a U-net array that denoises the compensation result to obtain a high-quality reconstructed image. RESULTS: The accuracy and feasibility of the proposed TSDLN-based framework in few-view projection-based reconstruction were first evaluated with simulations, using images from the DeepLesion public dataset. The framework exhibited better reconstruction performance than traditional analytic reconstruction algorithms and iterative algorithms, especially in cases using sparse-view projection images. For example, with as few as two projections, the TSDLN-based framework reconstructed high-quality images very close to the original image, with structural similarities greater than 0.8. By using previously acquired optical PT (OPT) data in the TSDLN-based framework trained on computed tomography (CT) data, we further exemplified the migration capabilities of the TSDLN-based framework. The results showed that when the number of projections was reduced to 5, the contours and distribution information of the samples in question could still be seen in the reconstructed images. CONCLUSIONS: The simulations and experimental results showed that the TSDLN-based framework has strong reconstruction abilities using few-view projection images, and has great potential in the application of in vivo PT.

Objective. To develop a simultaneous positron emission tomography-Optical (OPET) breast imaging dual-head PET subsystem, called DH-Mammo PET, for accurate, early diagnosis and efficacy assessment of breast cancer with high resolution and sensitivity. Approach. We developed a breast-dedicated PET based on LYSO crystal, silicon photomultiplier array and multi-voltage threshold sampling technique. It consists of two detector heads, each with a detection area of 216 mm × 145.5 mm. The distance between the detector heads is fixed at 120 mm. In order to extract coincidences and correct data, GPU-based software coincidence processing, random, scatter, normalization, gap-filling and attenuation corrections were applied in turn. The images were reconstructed using maximum likelihood expectation maximization with depth of interaction (DOI) modeling. The performance of DH-Mammo PET was evaluated referring to NEMA NU 4–2008, NU 2–2007 and Chinese industry recommended standard YY/T 1835–2022. Besides, several clinical patient images of DH-Mammo PET were compared with those of a whole-body PET/CT. Main results. The energy resolution was 14.5%, and time resolution was 22Na point source imaging, its spatial resolution was 2.60 mm (5.40 mm), 1.00 mm (1.04 mm), and 0.96 mm (0.93 mm) in the X, Y and Z directions, respectively, using the system response matrix with (without) DOI modeling. Indicated by the Derenzo phantom imaging, the spatial resolution was ∼3.0 mm, X, Y and Z directions. The system sensitivity was 6.87%, 4.89% and 3.37% with an energy window of 100–800, 250–750 and 350–650 keV, respectively. The scatter fraction was 26.43%, and the peak NECR was 162.6 kcps at 24.1 MBq for the modified rat-like phantom. As for the recovery coefficients, they ranged from 0.15 to 1.04 for rods between 1 and 5 mm obtained with a NEMA image quality phantom. The spill-over ratio for the air-filled and water-filled chamber was 0.05 and 0.11, respectively. DH-Mammo PET can provide more image details in clinical experiments and fulfil a fast scan with 60–120 s acquisition time. Significance. Good spatial resolution and high sensitivity of DH-Mammo PET would enable fast and accurate PET imaging of the breast. Besides, combining the DH-Mammo PET with the diffuse optical tomography would make full use of tumor metabolic imaging and tissue endogenous optical imaging, which would improve the accuracy of early clinical diagnosis of small lesions of breast cancers.

Optical strategies like Cerenkov luminescence imaging (CLI) or radioluminescence imaging (RLI) to image clinically available positron emission tomography and single photon emission computed tomography probes still suffer from low sensitivity or resolution. This study investigated a painted radioluminescence imaging (PRLI) approach that employed a painted scintillator to improve signal and resolution for imaging clinical used 18F-fluorinated deoxyribose (18F-FDG). Results of phantom and in vivo experiments revealed that PRLI could achieve ∼100 times higher signal intensity than CLI and higher resolution compared to Flexible radioluminescence imaging (FRLI), a flexible scintillation-based RLI. PRLI increased signal-to-background ratio in the pseudotumor model by 81.8% (compared to CLI) and 73.9% (compared to FRLI) as well as in the tumor model by 60.0% (compared to CLI) and 33.3% (compared to FRLI). As a conclusion, PRLI is a more effective optical approach for detecting tumors using 18F-FDG.

Scattering can seriously affect the highly sensitive detection and quantitative analysis of chemical substances in scattering media and becomes a significant challenge for in vivo application of Raman spectroscopy. In this study, we demonstrated a proof of concept for using the self-reconstructing Bessel beam for Raman spectroscopic sensing of the chemicals in the handmade scattering media and biological tissue slices. The homebuilt Bessel beam Raman spectroscopy (BRS) was capable of accurately detecting the Raman spectra of the chemicals buried in the scattering media, and had a superiority in quantitative analysis. The feasibility of the developed technique was verified by detecting the Raman spectra of pure samples in air. Compared with the spectra acquired by the Gaussian beam Raman spectroscope, the performance of the BRS system in terms of Raman spectrum detection and Raman peak recognition was confirmed. Subsequently, by employing the technique for the detection of acetaminophen buried in the scattering media, the application of the new technology in detecting and quantitating the chemicals in the scattering media were underlined, offering greater detection depth and better linear quantification capability than the conventional Gaussian beam Raman spectroscopy. Finally, we explored the potential of the BRS system for chemical sensing of acetaminophen in biological tissue slices, indicating a significant development towards the evaluation of drug in vivo.

Objective: Stimulated Raman projection tomography (SRPT), a recently developed label-free volumetric chemical imaging technology, has been reported to quantitatively reconstruct the distribution of chemicals in a three-dimensional (3D) complex system. The current image reconstruction scheme used in SRPT is based on a filtered back projection (FBP) algorithm that requires at least 180 angular-dependent projections to rebuild a reasonable SRPT image, resulting in a long total acquisition time. This is a big limitation for longitudinal studies on live systems. Methods: We present a sparse-view data-based sparse reconstruction scheme, in which sparsely sampled projections at 180 degrees were used to reconstruct the volumetric information. In the scheme, the simultaneous algebra reconstruction technique (SART), combined with total variation regularization, was used for iterative reconstruction. To better describe the projection process, a pixel vertex driven model (PVDM) was developed to act as projectors, whose performance was compared with those of the distance driven model (DDM). Results: We evaluated our scheme with numerical simulations and validated it for SRPT by mapping lipid contents in adipose cells. Simulation results showed that the PVDM performed better than the DDM in the case of using sparse-view data. Our scheme could maintain the quality of the reconstructed images even when the projection number was reduced to 15. The cell-based experimental results demonstrated that the proposed scheme can improve the imaging speed of the current FBP-based SRPT scheme by a factor of 9–12 without sacrificing discernible imaging details. Conclusion: Our proposed scheme significantly reduces the total acquisition time required for SRPT at a speed of one order of magnitude faster than the currently used scheme. This significant improvement in imaging speed would potentially promote the applicability of SRPT for imaging living organisms.

The dual-head positron emission tomography (PET) systems have an importance role in the preclinical and clinical applications. This paper focuses on developing a simplified model based on distance-driven (DD) and solid angle method to calculate the system response matrix (SRM) for the dual-head PET system. The subsampling schemes, including the subvoxel scheme and multi-DD scheme were introduced. The full width at half maximum (FWHM), coefficient of variation (COV), and contrast were computed and compared with that of using the Monte Carlo (MC)-based and multiray methods. In this paper, the dual-head PET system is configured with a 5 cm separation and $52 \times 104$ mm3 detection area of each head. The size of each crystal is $13\times 1.89\times 1.89$ mm3. The results indicate that the rods with 1.0 mm diameter are resolved basically with the 100th iteration when the voxel is virtually divided into $2\times 2\times 2$ and $4\times 4\times 4$ subvoxels, which is comparable to that with the MC-based SRM. When the voxel is divided into four cuboid-shaped subvoxels, the rods with 1.0 mm diameter are resolved with the 80th iteration and the COV performs well in the simulation experiment. Overall, the proposed SRM model achieves a good compromise between image quality and calculation time.

Confocal laser scanning microscopy (CLSM) is expected to exhibit a better imaging performance in the second near-infrared (NIR-II) windows with weak tissue scattering and autofluorescence. However, the indium gallium arsenide (InGaAs) detectors currently used for imaging in the NIR-II region are prohibitively expensive, hampering its extensive biomedical applications. In this study, a novel NIR-II CLSM system is developed by using the inexpensive silicon photomultiplier (SiPM) that can perform the multicolor biological imaging in vivo. Using IR-780 iodide as the contrast agent, the NIR-II imaging capability of constructed CLSM is inspected, demonstrating a spatial resolution of 1.68 µm (close to the diffraction limit) and a fluorophore detection sensitivity as low as 100 nm. In particular, it is discovered that the multicolor imaging performance in both NIR-I and NIR-II windows is comparable to those from multialkali and InGaAs photomultiplier tubes. In addition, 3D NIR-II CLSM is also conducted for in vivo imaging of the vascular structure in mouse ear and subcutaneous tumors. To the best of authors' knowledge, this is the first time that a low-cost detector based on a SiPM has been used for microscopic imaging of trailing fluorescence signals in the NIR-II region of an NIR fluorescent probe.

Multispectral Photoacoustic Tomography (MSPAT) is capable of visualizing the concentration distribution of various chromophores in biological tissues, where the unmixing process is usually performed with the spectral fitting method that requires the absorption spectral signatures of all chromophores in the tissue to be known. However, due to the changes of spectral signatures of some exogenous contrast agents in vitro and in vivo, the conventional fitting method will be hindered. Although the blind unmixing algorithms do not require the exact absorption spectrum of each chromophore in advance, it is often sensitive to noise, which may lead to low quantitative results. Considering that the non-negativity of concentration distribution and absorption spectra of the chromophores as well as the sparsity of concentration image of exogenous contrast agent in the gradient domain, we herein propose a modified MSPAT implementation that utilizes a non-negative matrix factorization iterative reconstruction framework with the support of a priori information of spectral signature of oxy-/deoxy-hemoglobin and valid sparsity regularization during the iteration. Consequently, the spectral signature of the exogenous contrast agent and the concentration distribution of each chromophore can be recovered simultaneously. The proposed approach has been validated by simulation and in vivo experiments, exhibiting promising performances in image fidelity even when the multi-wavelength photoacoustic tomographic images used for spectral unmixing are affected by noise or reconstruction artifacts.

To meet the diversity needs of diagnosis, treatment or prevention of diseases, different pharmaceutical dosage forms are designed and manufactured. The main role of each dosage form is drug carrier. However, changing forms might have some other different effects in clinical usages. For example, the capsule and tablets are absorbed by the intestine and stomach respectively, solutions and patches can act directly on the surface of skin etc. The quantity and quality analysis of the main drug in different form is a key issue in quality control. Therefore, it is a meaningful research of developing a facility method to detect the drug in different dosage forms. The traditional drug detection methods principally analyze and evaluate the performance through chemical reactions, photo-electricity or electrophoresis. However, these methods will cause damage to the samples. Owing to the non-invasive, non-destructive and label-free characteristics, Raman spectroscopy (RS) technique plays an important role in different fields. The current RS setup uses Gaussian beam as the excitation light, which can provide higher signal-to-noise in the thin or transparent sample. However, the Gaussian beam dispersed rapidly in the scattering medium, it is not conducive to in vivo or deep imaging. The Bessel beam having long focusing characteristics and self-reconstructing properties may provide solution to this problem. We here presented a new scheme for RS, which used a Bessel beam as the excitation light. The feasibility and effectiveness of the proposed scheme for detecting the drug in different pharmaceutical dosage forms were verified by series experiments.

Purpose: Dual-head positron emission tomography (PET) scanners have increasingly attracted the attention of many researchers. However, with the compact geometry, the depth-of-interaction blurring will reduce the image resolution considerably. Monte Carlo (MC)-based system response matrix (SRM) is able to describe the physical process of PET imaging accurately and improve reconstruction quality significantly. The MC-based SRM is large and precomputed, which leads to a longer image reconstruction time with indexing and retrieving precomputed system matrix elements. In this study, we proposed a GPU acceleration algorithm to accelerate the iterative reconstruction. Methods: It has been demonstrated that the line-of-response (LOR)-based symmetry and the Graphics Processing Unit (GPU) technology can accelerate the reconstruction tremendously. LOR-based symmetry is suitable for the forward projection calculation, but not for the backprojection. In this study, we proposed a GPU acceleration algorithm that combined the LOR-based symmetry and voxel-based symmetry together, in which the LOR-based symmetry is responsible for the forward projection, and the voxel-based symmetry is used for the backprojection. Results: Simulation and real experiments verify the efficiency of the algorithm. Compared with the CPU-based calculation, the acceleration ratios of the forward projection and the backprojection operation are 130 and 110, respectively. The total acceleration ratio is 113x. In order to compare the acceleration effect of the different symmetries, we realized the reconstruction with the voxel-based symmetry and the LOR-based symmetry strategies. Compared with the LOR-based GPU reconstruction, the acceleration ratio is 3.5x. Compared with the voxel-based GPU reconstruction, the acceleration ratio is 12x. Conclusion: We have proposed a new acceleration algorithm for the dual-head PET system, in which both the forward and backprojection operations are accelerated by GPU. (c) 2019 The Authors. Medical Physics published by Wiley Periodicals, Inc. on behalf of American Association of Physicists in Medicine.

Optical projection tomography (OPT) is a novel three-dimensional imaging technique, which provides an approach to recreating the three-dimensional images of biological specimens ranging from millimeters to centimeters. In the current OPT setup, the specimen was immersed in the index-matching fluid. In this case, the specimen could not survive or the survival time was too short for longitudinal imaging. In this paper, we first designed a new type of sample fixation method for in vivo OPT imaging. The specimen was embedded into a transparent gel in a petri dish, and the dish was affixed to the rotational stage of our homemade OPT system. As the specimen does not need to be immersed in the index-matching fluid, this method can reduce the damage to the specimen and it is more conducive to longitudinal observation for in vivo OPT. However, this fixation method induces a problem of insufficient measurements. The angles parallel to or nearly parallel to the surface of the dish cannot be acquired. To address this problem, we, then, used a limited-angle reconstruction framework for the novel sample fixation-based OPT, which combines the algebraic reconstruction technique (ART) algorithm with prior information to solve the inverse reconstruction problem. The feasibility and effectiveness of the proposed sample fixation method and the limited-angle reconstruction framework were verified by the simulations and experiments.

Generally, luminescence quenching at high doping concentrations typically limits the concentration of doped ions in the lanthanide material to less than 0.05-20 mol %, and this is still a major hindrance in designing nanoplatforms with improved brightness. In this research, a nanoplatform capable of dual-modal imaging and synergetic antitumor cells therapy was designed. NaYF4: x%Er@NaXF4 ( x = 5, 25, 50, and 100; X = Lu and Y) core@shell nanoparticles with Er3+ ion concentration up to 100 mol % were synthesized, and the luminescence properties under near-infrared (NIR) excitation were detected. The results show the strong coupled of surface and concentration quenching effects in upconversion nanoparticles (UCNP). Upconversion luminescence (UCL) and NIR-II emission intensity increased with negligible concentration quenching effect under 980 and 800 nm NIR lasers because of the growth of epitaxial shells. Therefore, the enhanced red luminescence transfers energy to photosensitizer ZnPc as the photodynamic therapy (PDT) agent for tumor inhibition efficacy.

When using quantitative photoacoustic tomography (q-PAT) reconstruction to recover the optical absorption coefficients of tissue, the commonly used diffusion equation has several limitations in the case of the objects that have small geometries and high-absorption or low-scattering areas. Furthermore, the conventional perturbation reconstruction strategy is unsatisfactory when the target tissue containing large heterogeneous features. We herein present a modified q-PAT implementation that employs the higher-order photon migration model achieving the tradeoff between mathematical rigidity and computational efficiency. Besides, a nonlinear iterative method is proposed to obtain the perturbations of optical absorption considering the updating of the sensitivity matrix in calculating the fluence perturbations. Consequently, the distribution of tissue optical properties can be recovered in a robust way even if the targets with high absorption are included. The proposed approach has been validated by simulation, phantom and in vivo experiments, exhibiting promising performances in image fidelity and quantitative feasibility for practical applications.

When using quantitative photoacoustic tomography (q-PAT) reconstruction to recover the optical absorption coefficients of tissue, the commonly used diffusion equation has several limitations in the case of the objects that have small geometries and high-absorption or low-scattering areas. Furthermore, the conventional perturbation reconstruction strategy is unsatisfactory when the target tissue containing large heterogeneous features. We herein present a modified q-PAT implementation that employs the higher-order photon migration model achieving the tradeoff between mathematical rigidity and computational efficiency. Besides, a nonlinear iterative method is proposed to obtain the perturbations of optical absorption considering the updating of the sensitivity matrix in calculating the fluence perturbations. Consequently, the distribution of tissue optical properties can be recovered in a robust way even if the targets with high absorption are included. The proposed approach has been validated by simulation, phantom and in vivo experiments, exhibiting promising performances in image fidelity and quantitative feasibility for practical applications.

To facilitate the clinical applicability of the diffuse optical inspection device, a compact multi-wavelength diffuse optical tomography system for breast imaging (compact-DOTB) with a fiber-free parallel-plane structure was designed and fabricated for acquiring three-dimensional optical properties of the breast in continuous-wave mode. The source array consists of 56 surface-mounted micro light-emitting diodes (LEDs), each integrating three wavelengths (660, 750, and 840 nm). The detector array is arranged with 56 miniaturized surface-mounted optical sensors, each encapsulating a high-sensitivity photodiode (PD) and a low-noise current amplifier with a gain of 24×. The system provides 3,136 pairs of source-detector measurements at each wavelength, and the fiber-free design largely ensures consistency between source/detection channels while effectively reducing the complexity of system operation and maintenance. We have evaluated the compact-DOTB system’s characteristics and demonstrated its performance in terms of reconstruction positioning accuracy and recovery contrast with breast-sized phantom experiments. Furthermore, the breast cancer patient studies have been carried out, and the quantitative results indicate that the compact-DOTB system is able to observe the changes in the functional tissue components of the breast after receiving the neoadjuvant chemotherapy (NAC), demonstrating the great potential of the proposed compact system for clinical applications, while its cost and ease of operation are competitive with the existing breast-DOT devices.

The construction of photon propagation has a close relationship with the quality of reconstructed images. The classical Monte Carlo (MC) based method can model the photon propagation precisely, but it is time-consuming. The analytical method can often quickly construct a model, but its precision is a problem. How to fully exploit the advantages of the MC simulation and analytical model is an open problem. Inspired by the characteristics of the depth of interaction (DOI) detectors, which can help confirm the deposited position of a photon with DOI-encoding technology, we virtually discretize each crystal into several subcrystals to obtain the statistical distribution by MC-based simulation. Then, the statistical distribution is combined with a spatially variant solid-angle model. This combination strategy provides a hybrid model to describe photon propagation with relatively high accuracy and low computational cost. Three discretization schemes are compared to optimize the constructed photon propagation model. Several experiments are carried out to evaluate the performance of the proposed hybrid method. The metrics of full width at half maximum (FWHM), contrast recovery (CR), and coefficient of variation (COV) are adopted to quantitate the imaging results. The classical MC-based method is compared as a gold-standard reference. When a crystal is divided into two discretized positions, the convergent tendencies of CRs and COVs are consistent with that based on MC simulation method, respectively. In terms of FWHMs, the resolutions of using the MC-based model and the proposed hybrid model are 0.71 mm and 0.68 mm in the direction parallel to the detector head, respectively. This indicates the potential of the proposed method in positron emission tomography imaging.

Fluorescence planar imaging (FPI) is failure to capture high resolution images of deep fluorochromes due to photon diffusion. This paper presents an image restoration method to deal with this kind of blurring. The scheme of this method is conceived based on a reconstruction method in fluorescence molecular tomography (FMT) with diffusion model. A new unknown parameter is defined through introducing the first mean value theorem for definite integrals. System matrix converting this unknown parameter to the blurry image is constructed with the elements of depth conversion matrices related to a chosen plane named focal plane. Results of phantom and mouse experiments show that the proposed method is capable of reducing the blurring of FPI image caused by photon diffusion when the depth of focal plane is chosen within a proper interval around the true depth of fluorochrome. This method will be helpful to the estimation of the size of deep fluorochrome.

BACKGROUND The CT image reconstruction algorithm based compressed sensing (CS) can be formulated as an optimization problem that minimizes the total-variation (TV) term constrained by the data fidelity and image nonnegativity. There are a lot of solutions to this problem, but the computational efficiency and reconstructed image quality of these methods still need to be improved. OBJECTIVE To investigate a faster and more accurate mathematical algorithm to settle TV term minimization problem of CT image reconstruction. METHOD A Nesterov's algorithm (NESTA) is a fast and accurate algorithm for solving TV minimization problem, which can be ascribed to the use of most notably Nesterov's smoothing technique and a subtle averaging of sequences of iterates, which has been shown to improve the convergence properties of standard gradient-descent algorithms. In order to demonstrate the superior performance of NESTA on computational efficiency and image quality, a comparison with Simultaneous Algebraic Reconstruction Technique-TV (SART-TV) and Split-Bregman (SpBr) algorithm is made using a digital phantom study and two physical phantom studies from highly undersampled projection measurements. RESULTS With only 25% of conventional full-scan dose and, NESTA method reduces the average CT number error from 51.76HU to 9.98HU on Shepp-Logan phantom and reduces the average CT number error from 50.13HU to 0.32HU on Catphan 600 phantom. On an anthropomorphic head phantom, the average CT number error is reduced from 84.21HU to 1.01HU in the central uniform area. CONCLUSIONS To the best of our knowledge this is the first work that apply the NESTA method into CT reconstruction based CS. Research shows that this method is of great potential, further studies and optimization are necessary.

Back projection filtering (BPF) and filtered back projection (FBP) are classic CT reconstruction analytic methods. However, when dealing with the reconstruction of incomplete datasets, analytic methods may suffer from artifacts due to the global nature of filtering. The iterative algorithm is another CT reconstruction method. Although the iterative algorithm can get excellent results, it requires high computation cost. In this work, inspired by the idea of BPF, we propose a CT image reconstruction strategy based on a new convolutional neural network that can capture features with different levels. The proposed method can learn the mapping between the direct back projection and the ideal CT images and then realize accurate image reconstruction. It is suitable for not only complete projection data but also transverse truncated projection data with different regions of interest (ROIs) sizes. The experiment results show that the proposed method outperforms the conventional FBP and other state-of-the-art deep learning methods in the truncated reconstruction. At the same time, the proposed method requires a lower computation cost which is helpful for fast reconstruction in the clinical research.