A new imaging mode based on X-ray CT as prior image and sparsely sampled projections for rapid clinical proton CT

Proton computed tomography(CT)has a distinct practical significance in clinical applications.It eliminates 3–5%errors caused by the transformation of Hounsfield unit(HU)to relative stopping power(RSP)values when using X-ray CT for positioning and treatment planning systems(TPSs).Following the development of FLASH proton therapy,there are increased requirements for accurate and rapid positioning in TPSs.Thus,a new rapid proton CT imaging mode is proposed based on sparsely sampled projections.The proton beam was boosted to 350 MeV by a compact proton linear accelerator(LINAC).In this study,the comparisons of the proton scattering with the energy of 350 MeV and 230 MeV are conducted based on GEANT4 simulations.As the sparsely sampled information associated with beam acquisitions at 12 angles is not enough for reconstruction,X-ray CT is used as a prior image.The RSP map generated by converting the X-ray CT was constructed based on Monte Carlo simulations.Considering the estimation of the most likely path(MLP),the prior image-constrained compressed sensing(PICCS)algorithm is used to reconstruct images from two different phantoms using sparse proton projections of 350 MeV parallel proton beam.The results show that it is feasible to realize the proton image reconstruction with the rapid proton CT imaging proposed in this paper.It can produce RSP maps with much higher accuracy for TPSs and fast positioning to achieve ultra-fast imaging for real-time image-guided radiotherapy(IGRT)in clinical proton therapy applications.

Preliminary landscape analysis of deep tomographic imaging patents

Over recent years,the importance of the patent literature has become increasingly more recognized in the aca-demic setting.In the context of artificial intelligence,deep learning,and data sciences,patents are relevant to not only industry but also academe and other communities.In this article,we focus on deep tomographic imaging and perform a preliminary landscape analysis of the related patent literature.Our search tool is PatSeer.Our patent biblio-metric data is summarized in various figures and tables.In particular,we qualitatively analyze key deep tomographic patent literature.

Principle of subtraction ghost imaging in scattering medium

Scattering medium in light path will cause distortion of the light field,resulting in poor signal-to-noise ratio(SNR)of ghost imaging.The disturbance is usually eliminated by the method of pre-compensation.We deduce the intensity fluctuation correlation function of the ghost imaging with the disturbance of the scattering medium,which proves that the ghost image consists of two correlated results:the image of scattering medium and the target object.The effect of the scattering medium can be eliminated by subtracting the correlated result between the light field after the scattering medium and the reference light from ghost image,which verifies the theoretical results.Our research may provide a new idea of ghost imaging in harsh environment.

Compressive near-field millimeter wave imaging algorithm based on Gini index and total variation mixed regularization

A compressive near-field millimeter wave(MMW)imaging algorithm is proposed.From the compressed sensing(CS)theory,the compressive near-field MMW imaging process can be considered to reconstruct an image from the under-sampled sparse data.The Gini index(GI)has been founded that it is the only sparsity measure that has all sparsity attributes that are called Robin Hood,Scaling,Rising Tide,Cloning,Bill Gates,and Babies.By combining the total variation(TV)operator,the GI-TV mixed regularization introduced compressive near-field MMW imaging model is proposed.In addition,the corresponding algorithm based on a primal-dual framework is also proposed.Experimental results demonstrate that the proposed GI-TV mixed regularization algorithm has superior convergence and stability performance compared with the widely used l1-TV mixed regularization algorithm.

Estimation-free spatial-domain image reconstruction of structured illumination microscopy

Structured illumination microscopy(SIM)achieves super-resolution(SR)by modulating the high-frequency information of the sample into the passband of the optical system and subsequent image reconstruction.The traditional Wiener-filtering-based reconstruction algorithm operates in the Fourier domain,it requires prior knowledge of the sinusoidal illumination patterns which makes the time-consuming procedure of parameter estimation to raw datasets necessary,besides,the parameter estimation is sensitive to noise or aberration-induced pattern distortion which leads to reconstruction artifacts.Here,we propose a spatial-domain image reconstruction method that does not require parameter estimation but calculates patterns from raw datasets,and a reconstructed image can be obtained just by calculating the spatial covariance of differential calculated patterns and differential filtered datasets(the notch filtering operation is performed to the raw datasets for attenuating and compensating the optical transfer function(OTF)).Experiments on reconstructing raw datasets including nonbiological,biological,and simulated samples demonstrate that our method has SR capability,high reconstruction speed,and high robustness to aberration and noise.

Simulation and experimental comparison of the performance of four-corner-readout plastic scintillator muon-detector system

Cosmic-ray muons are highly penetrating background-radiation particles found in natural environments.In this study,we develop and test a plastic scintillator muon detector based on machine-learning algorithms.The detector underwent muon position-resolution tests at the Institute of Modern Physics in Lanzhou using a multiwire drift chamber(MWDC)experimental platform.In the simulation,the same structural and performance parameters were maintained to ensure the reliability of the simulation results.The Gaussian process regression(GPR)algorithm was used as the position-reconstruction algorithm owing to its optimal performance.The results of the Time Difference of Arrival algorithm were incorporated as one of the features of the GPR model to reconstruct the muon hit positions.The accuracy of the position reconstruction was evaluated by comparing the experimental results with Geant4 simulation results.In the simulation,large-area plastic scintillator detectors achieved a position resolution better than 20 mm.In the experimental-platform tests,the position resolutions of the test detectors were 27.9 mm.We also analyzed factors affecting the position resolution,including the critical angle of the total internal reflection of the photomultiplier tubes and distribution of muons in the MWDC.Simulations were performed to image both large objects and objects with different atomic numbers.The results showed that the system could image high-and low-Z materials in the constructed model and distinguish objects with significant density differences.This study demonstrates the feasibility of the proposed system,thereby providing a new detector system for muon-imaging applications.

Triple-path feature transform network for ring-array photoacoustic tomography image reconstruction

Photoacoustic imaging(PAI)is a noninvasive emerging imaging method based on the photoacoustic effect,which provides necessary assistance for medical diagnosis.It has the characteristics of large imaging depth and high contrast.However,limited by the equipment cost and reconstruction time requirements,the existing PAI systems distributed with annular array transducers are difficult to take into account both the image quality and the imaging speed.In this paper,a triple-path feature transform network(TFT-Net)for ring-array photoacoustic tomography is proposed to enhance the imaging quality from limited-view and sparse measurement data.Specifically,the network combines the raw photoacoustic pressure signals and conventional linear reconstruction images as input data,and takes the photoacoustic physical model as a prior information to guide the reconstruction process.In addition,to enhance the ability of extracting signal features,the residual block and squeeze and excitation block are introduced into the TFT-Net.For further efficient reconstruction,the final output of photoacoustic signals uses‘filter-then-upsample’operation with a pixel-shuffle multiplexer and a max out module.Experiment results on simulated and in-vivo data demonstrate that the constructed TFT-Net can restore the target boundary clearly,reduce background noise,and realize fast and high-quality photoacoustic image reconstruction of limited view with sparse sampling.

A generalized deep neural network approach for improving resolution of fluorescence microscopy images

Deep learning is capable of greatly promoting the progress of super-resolution imaging technology in terms of imaging and reconstruction speed,imaging resolution,and imagingflux.This paper proposes a deep neural network based on a generative adversarial network(GAN).The generator employs a U-Net-based network,which integrates Dense Net for the downsampling component.The proposed method has excellent properties,for example,the network model is trained with several different datasets of biological structures;the trained model can improve the imaging resolution of different microscopy imaging modalities such as confocal imaging and wide-field imaging;and the model demonstrates a generalized ability to improve the resolution of different biological structures even out of the datasets.In addition,experimental results showed that the method improved the resolution of caveolin-coated pits(CCPs)structures from 264 nm to 138 nm,a 1.91-fold increase,and nearly doubled the resolution of DNA molecules imaged while being transported through microfluidic channels.

Underwater image clarifying based on human visual colour constancy using double-opponency

Underwater images are often with biased colours and reduced contrast because of the absorption and scattering effects when light propagates in water.Such images with degradation cannot meet the needs of underwater operations.The main problem in classic underwater image restoration or enhancement methods is that they consume long calcu-lation time,and often,the colour or contrast of the result images is still unsatisfied.Instead of using the complicated physical model of underwater imaging degradation,we propose a new method to deal with underwater images by imitating the colour constancy mechanism of human vision using double-opponency.Firstly,the original image is converted to the LMS space.Then the signals are linearly combined,and Gaussian convolutions are per-formed to imitate the function of receptive fields(RFs).Next,two RFs with different sizes work together to constitute the double-opponency response.Finally,the underwater light is estimated to correct the colours in the image.Further contrast stretching on the luminance is optional.Experiments show that the proposed method can obtain clarified underwater images with higher quality than before,and it spends significantly less time cost compared to other previously published typical methods.

Multi-scale cross-domain alignment for person image generation

Person image generation aims to generate images that maintain the original human appearance in different target poses.Recent works have revealed that the critical element in achieving this task is the alignment of appearance domain and pose domain.Previous alignment methods,such as appearance flow warping,correspondence learning and cross attention,often encounter challenges when it comes to producing fine texture details.These approaches suffer from limitations in accurately estimating appearance flows due to the lack of global receptive field.Alternatively,they can only perform cross-domain alignment on high-level feature maps with small spatial dimensions since the computational complexity increases quadratically with larger feature sizes.In this article,the significance of multi-scale alignment,in both low-level and high-level domains,for ensuring reliable cross-domain alignment of appearance and pose is demonstrated.To this end,a novel and effective method,named Multi-scale Crossdomain Alignment(MCA)is proposed.Firstly,MCA adopts global context aggregation transformer to model multi-scale interaction between pose and appearance inputs,which employs pair-wise window-based cross attention.Furthermore,leveraging the integrated global source information for each target position,MCA applies flexible flow prediction head and point correlation to effectively conduct warping and fusing for final transformed person image generation.Our proposed MCA achieves superior performance on two popular datasets than other methods,which verifies the effectiveness of our approach.

A novel 4D resolution imaging method for low and medium atomic number objects at the centimeter scale by coincidence detection technique of cosmic-ray muon and its secondary particles

The muon radiography imaging technique for high-atomic-number objects(Z)and large-volume objects via muon transmission imaging and muon multiple scattering imaging remains a popular topic in the field of radiation detection imaging.However,few imaging studies have been reported on low and medium Z objects at the centimeter scale.This paper presents an imaging system that consists of three layers of a position-sensitive detector and four plastic scintillation detectors.It acquires data by coincidence detection technique of cosmic-ray muon and its secondary particles.A 3D imaging algorithm based on the density of the coinciding muon trajectory was developed,and 4D imaging that takes the atomic number dimension into account by considering the secondary particle ratio information was achieved.The resultant reconstructed 3D images could distinguish between a series of cubes with 5-mm-side lengths and 2-mm-intervals.If the imaging time is more than 20 days,this method can distinguish intervals with a width of 1 mm.The 4D images can specify target objects with low,medium,and high Z values.

Parallel Spectral-Domain Optical Coherence Tomography for Non-Scattering Object Imaging

The parallel spectral-domain optical coherence tomography（PSDOCT） is described for highspeed optical coherence tomography（OCT） without lateral scanning. In this setup, the self-elimination of auto-correlation（AC） interference algorithm was used for eradicating the AC interference and ghost images. However, when performed in free space OCT, this algorithm still generated a weak DC component. The algorithm was improved by adding the background intensity part to compensate for the mutual interference between object and reference arms. The results demonstrate that the DC component can be eradicated. Compared with conventional QCT and complex Fourier-domain optical coherence to- mography, the advantages of PSDOCT with the improved algorithm in free space are that it has no moving parts to generate consecutive phase shift, the structure of the object can be reconstructed immediately and automatically, and the speed is approximately 16 times faster than those of the other two in the same case.

Near field 3-D imaging approach for joint high-resolution imaging and phase error correction

This paper combines compressed sensing (CS) imaging theory and range migration algorithm (RMA), and then proposes a near-field three-dimensional (3-D) imaging approach for joint high-resolution imaging and phase error correction. Firstly, a sparse measurement matrix construction method based on a logistic sequence is proposed, which conducts nonlinear transformation for the determined logistic sequence, making it obey uniform distribution, then conducts sign function mapping, and generates the pseudorandom sequence with Bernoulli distribution, thus leading to good signal recovery under down-sampling and easy availability for engineering realization. Secondly, in combination with the RMA imaging approach, the dictionary with all scene information and phase error correction is constructed for CS signal recovery and error correction. Finally, the non-quadratic solution model jointing imaging and phase error correction based on regularization is built, and it is solved by two steps - the separable surrogate functionals (SSF) iterative shrinkage algorithm is adopted to realize target scattering estimate; the iteration mode is adopted for the correction of the dictionary model, so as to achieve the goal of error correction and highly-focused imaging. The proposed approach proves to be effective through numerical simulation and real measurement in anechoic chamber. The results show that, the proposed approach can realize high-resolution imaging in the case of less data; the designed measurement matrix has better non-coherence and easy availability for engineering realization. The proposed approach can effectively correct the phase error, and achieve highly-focused target image. © 2017 Beijing Institute of Aerospace Information.

Autofocus technique for ISAR imaging of uniformly rotating targets based on the ExCoV method

The inverse synthetic aperture radar (ISAR) imaging can be converted into a sparse reconstruction problem and solved by the l1norm minimization algorithm. The basis matrix in sparse ISAR imaging is usually characterized by the unknown rotation rate of a moving target, thus the rotation rate and the sparse signal should be jointly estimated. Especially due to the imperfect coarse motion compensation, we consider the phase error correction problem in the context of the sparse signal reconstruction. To address this issue, we propose an iterative reweighted method, which jointly estimates the rotation rate, corrects the phase error and reconstructs a high resolution ISAR image. The proposed method gives a gradual and interweaved iterative process to refine the unknown parameters to achieve the best sparse representation for the ISAR signals. Particularly, in ISAR image reconstruction, the l1norm minimization algorithm is sensitive to user parameters. Setting these user parameters are not trivial and the reconstruction performance depends significantly on their choices. Then, we consider an expansion-compression variance-component (ExCoV) based method, which is automatic and demands no prior knowledge about signal-sparsity or measurement-noise levels. Both numerical and electromagnetic data experiments are implemented to show the effectiveness of the proposed method. It is shown that the proposed method can estimate the rotation rate and correct the phase errors simultaneously, and its superior performance is proved in terms of high resolution ISAR image. © 2017 Beijing Institute of Aerospace Information.

Handheld diffuse optical breast scanner probe for cross-sectional imaging of breast tissue

Diffuse optical spectroscopy is a relatively new,noninvasive and nonionizing technique for breast cancer diagnosis.In the present study,we have introduced a novel handheld diffuse optical breast scan(DOB-Scan)probe to measure optical properties of the breast in vivo and create functional and compositional images of the tissue.In addition,the probe gives more information about breast tissue's constituents,which helps distinguish a healthy and cancerous tissue.Two symmetrical light sources,each including four different wavelengths,are used to illuminate the breast tissue.A high-resolution linear array detector measures the intensity of the back-scattered photons at different radial destinations from the illumination sources on the surface of the breast tissue,and a unique image reconstruction algorithm is used to create four cross-sectional images for four different wavelengths.Different fromfiber optic-based illumination techniques,the proposed method in this paper integrates multi-wavelength light-emitting diodes to act as pencil beam sources into a scattering medium like breast tissue.This unique design and its compact structure reduce the complexity,size and cost of a potential probe.Although the introduced technique miniaturizes the probe,this study points to the reliability of this technique in the phantom study and clinical breast imaging.We have received ethical approval to test the DOB-Scan probe on patients and we are currently testing the DOB-Scan probe on subjects who are diagnosed with breast cancer.

Deep learning approach to detect seizure using reconstructed phase space images

Epilepsy is a chronic neurological disorder that affects the function of the brain in people of all ages.It manifests in the electroencephalogram(EEG) signal which records the electrical activity of the brain.Various image processing,signal processing,and machine-learning based techniques are employed to analyze epilepsy,using spatial and temporal features.The nervous system that generates the EEG signal is considered nonlinear and the EEG signals exhibit chaotic behavior.In order to capture these nonlinear dynamics,we use reconstructed phase space(RPS) representation of the signal.Earlier studies have primarily addressed seizure detection as a binary classification(normal vs.ictal) problem and rarely as a ternary class(normal vs.interictal vs.ictal)problem.We employ transfer learning on a pre-trained deep neural network model and retrain it using RPS images of the EEG signal.The classification accuracy of the model for the binary classes is(98.5±1.5)% and(95±2)% for the ternary classes.The performance of the convolution neural network(CNN) model is better than the other existing statistical approach for all performance indicators such as accuracy,sensitivity,and specificity.The result of the proposed approach shows the prospect of employing RPS images with CNN for predicting epileptic seizures.

Image Reconstruction of Ghost Imaging Based on Improved Generative Adversarial Networks

In this paper, we improve traditional generative adversarial networks (GAN) with reference to residual networks and convolutional neural networks to facilitate the reconstruction of complex objects that cannot be reconstructed by traditional associative imaging methods. Unlike traditional ghost imaging to reconstruct objects from bucket signals, our proposed method can use simple objects (such as EMNIST) as a training set for GAN, and then recognize objects (such as faces) of completely different complexity than the training set. We use traditional ghost imaging and neural network to reconstruct target objects respectively. According to the research results in this paper, the method based on neural network can reconstruct complex objects very well, but the method based on traditional ghost imaging cannot reconstruct complex objects. The research scheme in this paper is of great significance for the reconstruction of complex object-related imaging under low sampling conditions.

SAR imaging method for sea scene target based on improved phase retrieval algorithm

Due to the influence of the platform random motion and electromagnetic propagation in turbulent media, the synthetic aperture radar (SAR) high resolution imaging for the sea scenes where there are large amounts of water returns with some target (land) returns is very difficult. To solve this problem, a SAR imaging method based on the improved phase retrieval (PR) algorithm is proposed. First, a filter is added to the conventional PR algorithm which can reduce the influence of water returns on the reconstruction of the targets and improve the reconstruction result of the targets. Then, the corrupted phase of the Fourier transform of the intensity image in the iterative process, which can improve the stability of the iterative algorithm, is used to reduce the recovery errors, and a better recovery performance is achieved. Finally, several experiments are performed to demonstrate the advantages of the proposed method. © 2016 Beijing Institute of Aerospace Information.

IMAGE RECONSTRUCTION AND OBJECT CLASSIFICATION IN CT IMAGING SYSTEM

By obtaining a feasible filter function,reconstructed images can be got with linear interpolation and liftered backprojection techniques.Considering the gray and spstial correlation neighbour informations of each pixel,a new supervised classification method is put forward for the reconstructed images,and an experiment with noise image is done,the result shows that the method is feasible and accurate compared with ideal phantoms.

Linearized Proximal Alternating Direction Method of Multipliers for Parallel Magnetic Resonance Imaging

In this study, we propose a linearized proximal alternating direction method with variable stepsize for solving total variation image reconstruction problems. Our method uses a linearized technique and the proximal function such that the closed form solutions of the subproblem can be easily derived.In the subproblem, we apply a variable stepsize, that is like Barzilai-Borwein stepsize, to accelerate the algorithm. Numerical results with parallel magnetic resonance imaging demonstrate the efficiency of the proposed algorithm.