基于PCAU-Net的快速多通道磁共振成像方法

多通道磁共振成像方法采用多个接收线圈同时欠采样k空间以加快成像速度,并基于后处理算法重建图像,但在较高加速因子时,其图像重建质量仍然较差．本文提出了一种基于PCAU-Net的快速多通道磁共振成像方法,将单通道实数U型卷积神经网络拓展到多通道复数卷积神经网络,设计了一种结构不对称的U型网络结构,通过在解码部分减小网络规模以降低模型的复杂度．PCAU-Net网络在跳跃连接前增加了1×1卷积,以实现跨通道信息交互．输入和输出之间利用残差连接为误差的反向传播提供捷径．实验结果表明,使用规则和随机采样模板,在不同加速因子时,相比常规的GRAPPA重建算法和SPIRiT重建方法,本文提出的PCAU-Net方法可高质量重建出磁共振复数图像,并且相比于PCU-Net方法,PCAU-Net减少了模型参数、缩短了训练时间．     

MRISim:磁共振成像仿真实验软件包

本文基于数值计算模拟技术,开发了模拟磁共振成像（MRI）数据采集与图像重建的仿真软件包——MRISim.虚拟数据采集部分通过对设备硬件、样品（标样或人体部位）进行物理数学建模后,构建原始模拟信号,并填充k空间,然后再基于k空间数据实现磁共振图像重建.该软件可以通过参数的任意调节对影响磁共振图像质量的因素进行可视化分析,包括11种常见伪影的特征和成因分析.我们的研究表明应用该仿真软件可以弥补台式MRI扫描仪价格昂贵、实验时间长等不足之处,实现对相关科技人员的批量化、规模化的实践操作培训.     

一种结合并行成像和压缩感知的快速磁共振成像新方法

压缩感知（CS）技术和并行成像技术（主要是SENSE技术、GRAPPA技术等）都能通过减少k空间数据的采集量来加快磁共振成像速度,目前已有一些将两种方法相结合进一步加速磁共振成像速度的方法（例如CS-GRAPPA）.本文针对数据采集和重建这两方面对现有CS-GRAPPA方法进行了改进,采集方式上采用了局部等间隔采集模板以满足GRAPPA重建的要求,并对采集模板进行随机放置以满足CS重建的要求;数据重建时,根据自动校正数据估算GRAPPA算法中欠采行的重建误差,并利用误差的大小确定在CS算法中保真的程度.不同磁共振图像重建实验的结果表明：与现有方法相比,本文方法能够更好地保留原有图像细节并有效减少伪影.     

用于SAR估计的基于U-Net网络的快速膝关节模型重建

膝关节高场磁共振成像（MRI）时,射频功率沉积（SAR）是一个关键的安全指标.目前对于局部SAR的准确估计只能通过电磁仿真实现,这就要求得到每一个个体的膝关节模型.本文提出一种针对低场磁共振图像的基于卷积神经网络的分割方法,以实现膝关节磁共振图像的快速重建.数据集来自于矢位T₁加权自旋回波图像,将膝关节组织按照"肌肉-脂肪-骨骼"模型进行简化,除脂肪与骨骼之外的其他组织归类为肌肉.采用一种全卷积的神经网络,即U-Net进行逐层的图像分割,卷积层数为4,训练采用交叉熵函数.本文对图像的自动分割结果与手动标注结果进行了定量的比较.此外,采用3 T正交鸟笼线圈进行了SAR仿真,结果验证了组织简化对于SAR估计的可行性,并且所提方法构建的模型可以得到较为精准的局部SAR分布.     

基于支撑先验与深度图像先验的无预训练磁共振图像重建方法

基于深度学习的磁共振成像(magnetic resonance imaging, MRI)方法需要大规模、高质量的病患数据样本集进行预训练.然而,由于病患隐私及设备等因素限制,获取大规模、高质量的磁共振数据集在实际临床应用中面临挑战.本文提出一种新的基于深度学习的欠采样磁共振图像重建方法,该方法无需预训练、不依赖训练数据集,而是充分利用待重建的目标MR图像的结构先验和支撑先验,并将其引入深度图像先验(deep image prior, DIP)框架,从而削减对训练数据集的依赖,提升学习效率.基于参考图像与目标图像的相似性,采用高分辨率参考图像作为深度网络输入,将结构先验信息引入网络;将参考图像在小波域中幅值大的系数索引集作为目标图像的已知支撑集,构造正则化约束项,将网络训练转化为网络参数的最优化求解过程.实验结果表明,本文方法可由欠采样k空间数据重建得到更精确的磁共振图像,且在保留组织特征、细节纹理方面具有明显优势.     

儿童发育性髋关节脱位的磁共振形态学定量

发育性髋关节脱位（developmental dysplasia of the hip,DDH）作为一类常见的、严重威胁儿童健康成长的髋关节疾病会严重影响到儿童的肢体发育和生活质量,其早诊断、早治疗非常重要.磁共振成像（magnetic resonance imaging,MRI）技术可提供丰富的有关髋关节发育情况的形态学信息.目前,基于磁共振图像的DDH临床诊断主要凭借医生的肉眼观测,对医生要求甚高,而且无法定量判断DDH病情.本文提出了一种针对儿童DDH磁共振图像的形态学定量评估方法,通过对DDH病理改变密切相关的形态学参数的自动测定,完成形态学参数的定量评估,为临床提供辅助的量化参考.该方法包括磁共振图像预处理、股骨及盆骨分割、髋关节三维模型重建,以及结合了厚度搜索、三维霍夫变换和最小二乘拟合等算法实现的中心边缘角（center-edge angle,CEA）、髋臼角（acetabular index,AI）和股骨颈前倾角（femoral neck anteversion,FNA）等重要指标的自动测量.儿童DDH形态学定量评估方法的建立对儿童DDH的筛查、诊断和确诊患儿手术方案的制定,以及术后的动态随访,都具有重要参考价值.     

基于同伦l0范数最小化重建的三维动态磁共振成像

高欠采倍数的动态磁共振图像重建具有重要意义,是同时实现高时间分辨率和高空间分辨率动态对比度增强成像的重要环节.本研究提出一种结合黄金角变密度螺旋采样、并行成像和基于同伦l₀范数最小化的压缩感知的图像重建的三维动态磁共振成像方法.黄金角变密度螺旋采样轨迹被用来连续获取k空间数据,具有数据采集效率高、对运动不敏感等优点.在重建算法中,将多线圈稀疏约束应用于时间总变分域,使用基于l₀范数最小化的非线性重建算法代替传统的l₁范数最小化算法,进一步提高了欠采样率.仿真实验和在体实验表明本文所提的方法在保持图像质量的同时,也可以实现较高的空间分辨率和时间分辨率,初步验证了基于同伦l₀范数最小化重建在三维动态磁共振成像上的优势和临床价值.     

双树小波变换与小波树稀疏联合的低场CS-MRI算法

压缩感知理论常用在磁共振快速成像上,仅采样少量的K空间数据即可重建出高质量的磁共振图像.压缩感知磁共振成像技术的原理是将磁共振图像重建问题建模成一个包含数据保真项、稀疏先验项和全变分项的线性组合最小化问题,显著减少磁共振扫描时间.稀疏表示是压缩感知理论的一个关键假设,重建结果很大程度上依赖于稀疏变换.本文将双树复小波变换和小波树稀疏联合作为压缩感知磁共振成像中的稀疏变换,提出了基于双树小波变换和小波树稀疏的压缩感知低场磁共振图像重建算法.实验表明,本文所提算法可以在某些磁共振图像客观评价指标中表现出一定的优势.     

基于深度递归级联卷积神经网络的并行磁共振成像方法

快速磁共振成像是磁共振研究领域重要的课题之一.随着大数据和深度学习的兴起,神经网络成为快速磁共振技术的重要方法.然而网络性能表现和网络参数量之间较难取得平衡,且对于多通道数据重建的并行成像问题,相关研究较少.本文构建了一种深度递归级联卷积神经网络结构,用于处理并行成像问题.这种网络结构在减少网络参数量的同时,能够尽可能地提高网络的表达能力,提高网络重建的精确度.实验结果表明,相较于传统并行成像方法,通过训练好的神经网络对欠采样磁共振数据进行重建,可以得到更准确的重建结果,且重建时间大大缩短.     

基于神经网络拟合的腹部化学交换饱和转移成像

磁共振成像（Magnetic Resonance Imaging，MRI）化学交换饱和转移（Chemical Exchange Saturation Transfer，CEST）技术在临床诊断中展现了巨大的潜力，但在腹部成像中受到主磁场偏移量大的挑战，而且利用传统的非对称性分析法得到的酰胺质子转移（Amide Proton Transfer，APT）成像对比度受到核奥氏增强（Nuclear Overhauser Enhancement，NOE）效应的干扰.本文提出了一种基于神经网络拟合的CEST后处理方法，对每个像素采集得到的Z谱特征进行识别，不需要额外序列扫描即可得到背景参考Z谱与主磁场偏移量，用以校正和获得理想的Z谱，并进一步分离得到源自APT效应与NOE效应的信号.鸡蛋清和健康志愿者腹部成像结果显示，本文提出的基于神经网络的CEST后处理方法效果较好.     

Optimization of hyperparameters for SMS reconstruction

PurposeSimultaneous multi-slice (SMS) imaging accelerates MRI data acquisition by exciting multiple image slices with a single radiofrequency pulse. Overlapping slices encoded in acquired signal are separated using a mathematical model, which requires estimation of image reconstruction kernels using calibration data. Several parameters used in SMS reconstruction impact the quality and fidelity of final images. Therefore, finding an optimal set of reconstruction parameters is critical to ensure that accelerated acquisition does not significantly degrade resulting image quality.MethodsGradient-echo echo planar imaging data were acquired with a range of SMS acceleration factors from a cohort of five volunteers with no known neurological pathology. Images were collected using two available phased-array head coils (a 48-channel array and a reduced diameter 32-channel array) that support SMS. Data from these coils were identically reconstructed offline using a range of coil compression factors and reconstruction kernel parameters. A hybrid space (k-x), externally-calibrated coil-by-coil slice unaliasing approach was used for image reconstruction. The image quality of the resulting reconstructed SMS images was assessed by evaluating correlations with identical echo-planar reference data acquired without SMS. A finger tapping functional MRI (fMRI) experiment was also performed and group analysis results were compared between data sets reconstructed with different coil compression levels.ResultsBetween the two RF coils tested in this study, the 32-channel coil with smaller dimensions clearly outperformed the larger 48-channel coil in our experiments. Generally, a large calibration region (144–192 samples) and small kernel sizes (2–4 samples) in k_y direction improved image quality. Use of regularization in the kernel fitting procedure had a notable impact on the fidelity of reconstructed images and a regularization value 0.0001 provided good image quality. With optimal selection of other hyperparameters in the hybrid space SMS unaliasing algorithm, coil compression caused small reduction in correlation between single-band and SMS unaliased images. Similarly, group analysis of fMRI results did not show a significant influence of coil compression on resulting image quality.ConclusionsThis study demonstrated that the hyperparameters used in SMS reconstruction need to be fine-tuned once the experimental factors such as the RF receive coil and SMS factor have been determined. A cursory evaluation of SMS reconstruction hyperparameter values is therefore recommended before conducting a full-scale quantitative study using SMS technologies.     

Deep learning for radial SMS myocardial perfusion reconstruction using the 3D residual booster U-net

PurposeTo develop an end-to-end deep learning solution for quickly reconstructing radial simultaneous multi-slice (SMS) myocardial perfusion datasets with comparable quality to the pixel tracking spatiotemporal constrained reconstruction (PT-STCR) method.MethodsDynamic contrast enhanced (DCE) radial SMS myocardial perfusion data were obtained from 20 subjects who were scanned at rest and/or stress with or without ECG gating using a saturation recovery radial CAIPI turboFLASH sequence. Input to the networks consisted of complex coil combined images reconstructed using the inverse Fourier transform of undersampled radial SMS k-space data. Ground truth images were reconstructed using the PT-STCR pipeline. The performance of the residual booster 3D U-Net was tested by comparing it to state-of-the-art network architectures including MoDL, CRNN-MRI, and other U-Net variants.ResultsResults demonstrate significant improvements in speed requiring approximately 8 seconds to reconstruct one radial SMS dataset which is approximately 200 times faster than the PT-STCR method. Images reconstructed with the residual booster 3D U-Net retain quality of ground truth PT-STCR images (0.963 SSIM/40.238 PSNR/0.147 NRMSE). The residual booster 3D U-Net has superior performance compared to existing network architectures in terms of image quality, temporal dynamics, and reconstruction time.ConclusionResidual and booster learning combined with the 3D U-Net architecture was shown to be an effective network for reconstructing high-quality images from undersampled radial SMS datasets while bypassing the reconstruction time of the PT-STCR method.     

Coil-combined split slice-GRAPPA for simultaneous multi-slice diffusion MRI

Objective: To develop a kernel optimization method called coil-combined split slice-GRAPPA (CC-SSG) to improve the accuracy of the reconstructed coil-combined images for simultaneous multi-slice (SMS) diffusion weighted imaging (DWI) data.Methods: The CC-SSG method optimizes the tuning parameters in the k-space SSG kernels to achieve an optimal trade-off between the intra-slice artifact and inter-slice leakage after the root-sum-of-squares (rSOS) coil combining of the de-aliased SMS DWI data. A detailed analysis is conducted to evaluate the contributions of the intra-slice artifact and inter-slice leakage to the total reconstruction error after coil combining.Results: Comparisons of the proposed CC-SSG method with the slice-GRAPPA (SG) and split slice-GRAPPA (SSG) methods are provided using two in-vivo readout-segmented (RS) EPI datasets collected from stroke patients. The CC-SSG method demonstrates improved accuracy of the reconstructed coil-combined images and the estimated diffusion tensor imaging (DTI) maps.Conclusion: CC-SSG strikes a good balance between the intra-slice artifact and inter-slice leakage for rSOS coil combining, and so can yield better reconstruction performance compared to SG and SSG for rSOS reconstruction. The optimal trade-off between the two artifacts is robust to the contrast of SMS data and the choice of the coil combining method.     

光泵抽运3He极化程度监控系统的设计与实现

极化³He的一项重要应用是中子的极化.中国绵阳研究堆（CMRR）已建立国内首个自旋交换光学泵浦（SEOP）极化³He中子极化系统.为了监测³He的极化率随时间的相对变化情况,本文首先设计了基于核磁共振（NMR）技术的³He相对极化率测量系统,通过Matlab控制程序实现了对³He相对极化率的定时检测.然后对拾波线圈的构形和信噪比（SNR）进行了优化.结果表明当绕线长度一样时,Brooks构形的线圈有利于提高SNR;当线圈的平均半径为（a₀+d）/√2（a₀为³He气室的半径,d为拾波线圈与气室之间的距离）时,其SNR最高.最后对该系统的本底噪声进行了测量,发现其主要来源于环境噪声（0.27 μV/√Hz）和数据采集（DAQ）卡的噪声（0.40 μV/√Hz）,系统的总噪声功率谱密度约为√0.16+0.073G² μV/√Hz（G为放大器的增益倍数）.     

基于博奇编码离轴全息方法的研究

研究了一种计算全息编码过程中使原始像与共轭像分离的方法。通过对傅里叶变换计算全息图再现过程的分析,采用将原物抽样点镶嵌到比原物大的全零矩阵中的方法代替载频参数的计算,来实现原始像与共轭像的分离。对新矩阵进行离散傅里叶变换,利用博奇编码方式制作出计算全息图,并在图像重构时利用高通滤波器消除背景光干扰对重构视觉效果的影响。采用该方法制作的计算全息图可通过控制全零矩阵的大小来控制再现时原始像与共轭像的分离程度,全零矩阵越大,其分离程度越大。实验结果表明,全零矩阵为原物大小的4倍时可使原始像与共轭像刚好分离。但是为了方便滤除零级光斑,全零矩阵需稍大于原物大小的4倍。     

用改进的Fienup迭代算法进行数字全息重建

数字全息成像中往往包括再现像、共轭像和零级项,再现像的分离是常见而又难以彻底解决的问题。提出一种新的全息图重建算法,即利用相干衍射成像（CDI）中的迭代方法处理数字全息图,实现仅有一个实像的再现结果,从而彻底解决该问题。该方法包括两个步骤：首先通过CCD分别测量样品单独存在、样品和参考光同时存在以及参考光的远场衍射分布;然后通过计算机进行迭代运算。由于干涉光的存在,该算法比传统的CDI算法有更快的收敛速度和重建质量。同时进行了数值模拟验证并对生物切片进行了物像重建。     

用于压缩感知磁共振成像的分割字典学习算法

字典学习算法可以根据数据本身的特点构建稀疏域中的基,从而使数据的表示更加稀疏.该文在传统的字典学习算法基础上提出了分割字典学习算法,由于部分磁共振图像组织结构简单、可以进行图像分割,因此可根据此特点来优化字典中基函数的构建,使磁共振图像的表达更为稀疏,从而获得更高的重建图像质量.该文利用模拟数据和真实数据进行了重建实验,结果表明与传统的字典学习算法相比,分割字典学习算法能进一步改善重建图像质量.     

基于AI+MRI的影像诊断的样本增广与批量标注方法

训练样本是所有领域人工智能（AI）研发的关键因素.目前，基于人工智能+磁共振成像（AI+MRI）的影像诊断存在着训练样本的有效标注数量和类型无法满足研发需求的瓶颈问题.本文利用临床MRI设备对志愿者或阳性病例进行正常或重点病灶区的定量扫描，获取高分辨率各向同性的纵向弛豫时间（T₁）、横向弛豫时间（T₂）、质子密度（Pd）和表观扩散系数（ADC）等物理信息的多维数据矩阵，作为原始数据.开发虚拟MRI技术平台，对原始数据（相当于数字人体样本）进行虚拟扫描，实现不同序列不同参数下的多种类磁共振图像输出.选择感兴趣组织具有最好边界区分度的图像种类，经有经验的影像医生对其进行手动勾画并轨迹跟踪形成三维MASK标注矩阵，作为其他种类图像的图像勾画标注模板，从而实现低成本、高效率的MRI样本增广和批量标注.该平台以临床少量阳性病例作为输入，进行样本增广和标注，极大地减少AI对实际扫描样本的要求，降低了影像医生的精力和时间投入，极大地节省了成本，并输出了数量足够的磁共振图像，为基于AI+MRI的影像诊断研发提供低成本的训练数据解决方案.     

Joint Reconstruction of Multi-contrast Images and Multi-channel Coil Sensitivities

Magnetic resonance imaging (MRI) has an important feature that it provides multiple images with different contrasts for complementary diagnostic information. However, a large amount of data is needed for multi-contrast images depiction, and thus, the scan is time-consuming. Many methods based on parallel magnetic resonance imaging (pMRI) and compressed sensing (CS) are applied to accelerate multi-contrast MR imaging. Nevertheless, the image reconstructed by sophisticated pMRI methods contains residual aliasing artifact that degrades the quality of the image when the acceleration factor is high. Other methods based on CS always suffer the regularization parameter-selecting problem. To address these issues, a new method is presented for joint multi-contrast image reconstruction and coil sensitivity estimation. The coil sensitivities can be shared during the reconstruction due to the identity of coil sensitivity profiles of different contrast images for imaging stationary tissues. The proposed method uses the coil sensitivities as sharable information during the reconstruction to improve the reconstruction quality. As a result, the residual aliasing artifact can be effectively removed in the reconstructed multi-contrast images even if the acceleration factor is high. Besides, as there is no regularization term in the proposed method, the troublesome regularization parameter selection in the CS can also be avoided. Results from multi-contrast in vivo experiments demonstrated that multi-contrast images can be jointly reconstructed by the proposed method with effective removal of the residual aliasing artifact at a high acceleration factor.