An algorithm for computed tomography image reconstruction from limited-view projections

With the development of the compressive sensing theory, the image reconstruction from the projections viewed in limited angles is one of the hot problems in the research of computed tomography technology. This paper develops an iterative algorithm for image reconstruction, which can fit the most cases. This method gives an image reconstruction flow with the difference image vector, which is based on the concept that the difference image vector between the reconstructed and the reference image is sparse enough. Then the l1-norm minimization method is used to reconstruct the difference vector to recover the image for flat subjects in limited angles. The algorithm has been tested with a thin planar phantom and a real object in limited-view projection data. Moreover, all the studies showed the satisfactory results in accuracy at a rather high reconstruction speed.

Research on the Application of Super Resolution Reconstruction Algorithm for Underwater Image

Underwater imaging is widely used in ocean,river and lake exploration,but it is affected by properties of water and the optics.In order to solve the lower-resolution underwater image formed by the influence of water and light,the image super-resolution reconstruction technique is applied to the underwater image processing.This paper addresses the problem of generating super-resolution underwater images by convolutional neural network framework technology.We research the degradation model of underwater images,and analyze the lower-resolution factors of underwater images in different situations,and compare different traditional super-resolution image reconstruction algorithms.We further show that the algorithm of super-resolution using deep convolution networks(SRCNN)which applied to super-resolution underwater images achieves good results.

A novel algorithm for transmission image reconstruction of tomographic gamma scaners

It is difficult to develop image reconstruction algorithms for tomographic gamma scanning based on drummed radioactive residues or wastes.In this paper,a novel reconstruction algorithm of transmission image for tomographic gamma scanning is proposed.It is based on the conventional transmission equation and equivalent gamma-ray track length modified by a Monte Carlo method.The algorithm is implemented by simulating the samples on the established platform.For the verification experiments of the algorithm,several cubic voxel samples were designed and manufactured.Experimental tests were conducted.The tomographic gamma scanning of transmission images is compared with the linear attenuation coefficients by the simulated values and experimental data with the algorithm and the reference values.The results show that the absolute relative errors of the reconstructed images are less than 5%.

Elitist Reconstruction Genetic Algorithm Based on Markov Random Field for Magnetic Resonance Image Segmentation

In this paper, elitist reconstruction genetic algorithm （ERGA） based on Markov random field （MRF） is introduced for image segmentation. In this algorithm, a population of possible solutions is maintained at every generation, and for each solution a fitness value is calculated according to a fitness function, which is constructed based on the MRF potential function according to Metropolis function and Bayesian framework. After the improved selection, crossover and mutation, an elitist individual is restructured based on the strategy of restructuring elitist. This procedure is processed to select the location that denotes the largest MRF potential function value in the same location of all individuals. The algorithm is stopped when the change of fitness functions between two sequent generations is less than a specified value. Experiments show that the performance of the hybrid algorithm is better than that of some traditional algorithms.

An Algorithm for the Reconstruction of Entrance Beam Fluence from Virtual Patient Exit Electronic Portal Images

The problem of determining the in vivo dosimetry for patients undergoing radiation treatment has been an area of interest since the development of the field. More recent methods of measurement employ Electronic Portal Image Devices (EPID), or dosimeter arrays, for entrance or exit fluence determination. The more recent methods of in vivo dosimetry make use of detector arrays and reconstruction techniques to determine dose throughout the patient volume. One method uses an array of ion chambers located upstream of the patient. This requires a special hardware device and places an additional attenuator in the beam path, which may not be desirable. An alternative to this approach is to use the existing EPID, which is part of most modern linear accelerators, to image the patient using the treatment beam. Methods exist to deconvolve the detector function of the EPID using a series of weighted exponentials [1]. Additionally, this method has been extended to the deconvolution of the patient scatter in order to determine in vivo dosimetry. The method developed here intends to use EPID images and an iterative deconvolution algorithm to reconstruct the impinging primary fluence on the patient. This primary fluence may then be employed, using treatment time volumetric imaging, to determine dose through the entire patient volume. Presented in this paper is the initial discussion of the algorithm, and a theoretical evaluation of its efficacy using montecarlo derived virtual fluence measurements. The results presented here indicate an agreement of 1% dose difference within 95% the field area receiving 10% of the entrance fluence for a set of sample highly modulated fields. These results warrant continued investigation in applying this algorithm to clinical patient treatments.

Dose reconstruction with Compton camera during proton therapy via subset-driven origin ensemble and double evolutionary algorithm

Compton camera-based prompt gamma(PG) imaging has been proposed for range verification during proton therapy. However, a deviation between the PG and dose distributions, as well as the difference between the reconstructed PG and exact values, limit the effectiveness of the approach in accurate range monitoring during clinical applications. The aim of the study was to realize a PG-based dose reconstruction with a Compton camera, thereby further improving the prediction accuracy of in vivo range verification and providing a novel method for beam monitoring during proton therapy. In this paper, we present an approach based on a subset-driven origin ensemble with resolution recovery and a double evolutionary algorithm to reconstruct the dose depth profile(DDP) from the gamma events obtained by a cadmium-zinc-telluride Compton camera with limited position and energy resolution. Simulations of proton pencil beams with clinical particle rate irradiating phantoms made of different materials and the CT-based thoracic phantom were used to evaluate the feasibility of the proposed method. The results show that for the monoenergetic proton pencil beam irradiating homogeneous-material box phantom,the accuracy of the reconstructed DDP was within 0.3 mm for range prediction and within 5.2% for dose prediction. In particular, for 1.6-Gy irradiation in the therapy simulation of thoracic tumors, the range deviation of the reconstructed spreadout Bragg peak was within 0.8 mm, and the relative dose deviation in the peak area was less than 7% compared to the exact values. The results demonstrate the potential and feasibility of the proposed method in future Compton-based accurate dose reconstruction and range verification during proton therapy.

Super-resolution image reconstruction based on three-step-training neural networks

A new method of super-resolution image reconstruction is proposed, which uses a three-step-training error backpropagation neural network （BPNN） to realize the super-resolution reconstruction （SRR） of satellite image. The method is based on BPNN. First, three groups learning samples with different resolutions are obtained according to image observation model, and then vector mappings are respectively used to those three group learning samples to speed up the convergence of BPNN, at last, three times consecutive training are carried on the BPNN. Training samples used in each step are of higher resolution than those used in the previous steps, so the increasing weights store a great amount of information for SRR, and network performance and generalization ability are improved greatly. Simulation and generalization tests are carried on the well-trained three-step-training NN respectively, and the reconstruction results with higher resolution images verify the effectiveness and validity of this method.

Deep-Learning-Empowered 3D Reconstruction for Dehazed Images in IoT-Enhanced Smart Cities

With increasingly more smart cameras deployed in infrastructure and commercial buildings,3D reconstruction can quickly obtain cities’information and improve the efficiency of government services.Images collected in outdoor hazy environments are prone to color distortion and low contrast;thus,the desired visual effect cannot be achieved and the difficulty of target detection is increased.Artificial intelligence(AI)solutions provide great help for dehazy images,which can automatically identify patterns or monitor the environment.Therefore,we propose a 3D reconstruction method of dehazed images for smart cities based on deep learning.First,we propose a fine transmission image deep convolutional regression network(FT-DCRN)dehazing algorithm that uses fine transmission image and atmospheric light value to compute dehazed image.The DCRN is used to obtain the coarse transmission image,which can not only expand the receptive field of the network but also retain the features to maintain the nonlinearity of the overall network.The fine transmission image is obtained by refining the coarse transmission image using a guided filter.The atmospheric light value is estimated according to the position and brightness of the pixels in the original hazy image.Second,we use the dehazed images generated by the FT-DCRN dehazing algorithm for 3D reconstruction.An advanced relaxed iterative fine matching based on the structure from motion(ARI-SFM)algorithm is proposed.The ARISFM algorithm,which obtains the fine matching corner pairs and reduces the number of iterations,establishes an accurate one-to-one matching corner relationship.The experimental results show that our FT-DCRN dehazing algorithm improves the accuracy compared to other representative algorithms.In addition,the ARI-SFM algorithm guarantees the precision and improves the efficiency.

Randomized Kaczmarz algorithm for CT reconstruction

The order of the projection in the algebraic reconstruction technique(ART)method has great influence on the rate of the convergence.Although many scholars have studied the order of the projection,few theoretical proofs are given.Thomas Strohmer and Roman Vershynin introduced a randomized version of the Kaczmarz method for consistent,and over-determined linear systems and proved whose rate does not depend on the number of equations in the systems in 2009.In this paper,we apply this method to computed tomography(CT)image reconstruction and compared images generated by the sequential Kaczmarz method and the randomized Kaczmarz method.Experiments demonstrates the feasibility of the randomized Kaczmarz algorithm in CT image reconstruction and its exponential curve convergence.

Threshold strategy to improve the images reconstructed by electrical impedance tomography

Because of the illposedness of soft field, the quality of EIT images is not satisfied as expected. This paper puts forward a threshold strategy to decrease the artifacts in the reconstructed images by modifying the solutions of inverse problem. Threshold strategy is a kind of post processing method with merits of easy, direct and efficient. Reconstructed by Gauss-Newton algorithm, the simulation image’s quality is improved evidently. We take two performance targets, image reconstruction error and correlation coefficient, to evaluate the improvement. The images and the data show that threshold strategy is effective and achievable.

A robust tensor watermarking algorithm for diffusion-tensor images

Watermarking algorithms that use convolution neural networks have exhibited good robustness in studies of deep learning networks.However,after embedding watermark signals by convolution,the feature fusion eficiency of convolution is relatively low;this can easily lead to distortion in the embedded image.When distortion occurs in medical images,especially in diffusion tensor images(DTIs),the clinical value of the DTI is lost.To address this issue,a robust watermarking algorithm for DTIs implemented by fusing convolution with a Transformer is proposed to ensure the robustness of the watermark and the consistency of sampling distance,which enhances the quality of the reconstructed image of the watermarked DTIs after embedding the watermark signals.In the watermark-embedding network,Ti-weighted(Tlw)images are used as prior knowledge.The correlation between T1w images and the original DTI is proposed to calculate the most significant features from the T1w images by using the Transformer mechanism.The maximum of the correlation is used as the most significant feature weight to improve the quality of the reconstructed DTI.In the watermark extraction network,the most significant watermark features from the watermarked DTI are adequately learned by the Transformer to robustly extract the watermark signals from the watermark features.Experimental results show that the average peak signal-to-noise ratio of the watermarked DTI reaches 50.47 dB,the diffusion characteristics such as mean diffusivity and fractional anisotropy remain unchanged,and the main axis deflection angleαAc is close to 1.Our proposed algorithm can effectively protect the copyright of the DTI and barely affects the clinical diagnosis.

利用IMAGE卫星观测数据重建地球等离子体层的磁赤道面分布

美国利用IMAGE卫星的极紫外辐射(EUV)探测器对地球等离子体层进行了连续5年的遥感成像观测。由于IMAGE卫星数据是沿观测路径上的积分投影数据,并且存在地球"遮挡"、"阴影"、"数据缺失"等问题,无法直接利用传统的CT方法对等离子体层进行三维重建。本文利用地球磁场模型,基于地球等离子体层的物理性质,建立一个联系地球磁赤道面密度与投影数据的EUV成像模型,实现了从单个角度的EUV观测图像进行地球等离子层三维重构的方法。

Radar Imaging Based on Iterative Algorithms

It has long been realized that the problem of radar imaging is a special case of image reconstruction in which the data are incomplete and noisy. In other fields, iterative reconstruction algorithms have been used successfully to improve the image quality. This paper studies the application of iterative algorithms in radar imaging. A discrete model is first derived, and the iterative algorithms are then adapted to radar imaging. Although such algorithms are usually time consuming, this paper shows that, if the algorithms are appropriately simplified, it is possible to realize them even in real time. The efficiency of iterative algorithms is shown through computer simulations.

Image Reconstruction Using a Genetic Algorithm for Electrical Capacitance Tomography

Electrical capacitance tomography （ECT） has been used for more than a decade for imaging dielectric processes. However, because of its ill-posedness and non-linearity, ECT image reconstruction has always been a challenge. A new genetic algorithm （GA） developed for ECT image reconstruction uses initial results from a linear back-projection, which is widely used for ECT image reconstruction to optimize the threshold and the maximum and minimum gray values for the image. The procedure avoids optimizing the gray values pixel by pixel and significantly reduces the search space dimension. Both simulations and static experimental results show that the method is efficient and capable of reconstructing high quality images. Evaluation criteria show that the GA-based method has smaller image error and greater correlation coefficients. In addition, the GA-based method converges quickly with a small number of iterations.

基于两步迭代收缩法的多稀疏空间图像快速重构方法

由于多稀疏空间图像重构时,像素范围选取过大、峰值信噪比低以及重构时间长,导致图像重构方法存在重构效果差的问题,提出基于两步迭代收缩法的多稀疏空间图像快速重构方法。明确多稀疏空间图像重构存在的问题,在明确问题后,以迭代收缩阈值算法为基础,引入迭代加权收缩算法,结合每一轮迭代结果作为初值,完成图像重构的两步迭代收缩法设计,实现多稀疏空间图像快速重构。实验结果表明:应用该方法后的重构多稀疏空间图像峰值信噪比达到37.9 dB以上,图像重构时间仅为16.0 ms,图像结构相似性达到了0.98以上,并且重构多稀疏空间图像的效果更好,经过实验分析证实了所提方法具备可行性。

AI技术在视频图像超清修复中的应用

随着时代的发展与进步,标清电视逐渐淡出大众视野。为顺应现代社会对于视频图像品质的追求,大量的标清经典影视作品面临着向高清分辨率的转换挑战,但是就转换结果来看,传统的标清在转换为高清后,图像的清晰度并没有得到显著提高。基于此,文章将以人工智能(Artificial Intelligence,AI)技术为核心,以经典标清影视作品1986年版《西游记》和1987年版《红楼梦》为例,结合超清的试验结果,对AI技术在视频图像超清修复中的应用效果进行深入分析。

Reconstruction algorithm of super-resolution infrared image based on human vision processing mechanism

瞄准在红外线的成像解决低分辨率和视觉污迹的问题，用处理机制(HVPM ) 的人的视觉的一个超级决定的红外线的图象重建方法被建议。这个方法联合了视觉的机制有算法设计的侧面的抑制到凸的集合(POCS ) 上重建，改进视觉侧面的抑制网络被利用提高在低分辨率的图象序列的目标和背景之间的对比，然后， POCS 算法被采用重建超级决定的图象。试验性的结果证明建议方法罐头显著地改进图象的视觉效果，其对比和重建的红外线的图象的信息熵分别地与传统的 POCS 重建算法相比到约 5 次和 1.6 次被改进。