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.     

基于级联卷积神经网络的前列腺磁共振图像分类

针对深度学习训练成本高，以及基于磁共振图像的前列腺癌临床诊断需要大量医学常识且极为耗时的问题，本文提出了一种基于级联卷积神经网络（Convolutional Neural Network，CNN）和磁共振图像的前列腺癌（Prostate Cancer，PCa）自动分类诊断方法，该网络以Faster-RCNN作为前网络，对前列腺区域进行提取分割，用于排除前列腺附近组织器官的干扰；以基于ResNet改进的网络结构CNN40_bottleneck作为后网络，用于对前列腺区域病变进行分类.后网络由瓶颈结构串联组成，其中使用批量标准化（Batch Normalization，BN）、全局平均池化（Global Average Pooling，GAP）进行优化.实验结果证明，本文方法对前列腺癌诊断结果较好，而且缩减了训练时间和参数量，有效降低了训练成本.     

Spiral MRI和图像处理

介绍了在Bruker Biospec 47/30 超导核磁共振成象仪(4.7 T)上实现Spiral快速成像及图像处理系统. 图像处理系统基于PC技术构建而成,主要功能包括：1） 将以Spiral形式采集到的时域磁共振信号转化为适用于快速傅立叶变换的笛卡尔网格(Cartesian)形式（网格化处理）;2）二维快速傅立叶变换(2D-FFT,图像重建);3）由化学位移偏置或磁场不均匀引起得偏共振效应(off-resonance effect)的校正;4）图像分析. 该软件适用于包括以多片多回波在内的各种采样方式得到的Spiral图像的重建和分析,也适用于常规成像数据的重建和分析. 所得到的图像可以以数据方式保存以供再次读入,也能够以TIF、GIF、JPG、BM等格式辅出为图像文件.     

MRISim:磁共振成像仿真实验软件包（英文）

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.     

基于全可编程SoC和LabVIEW的磁共振接收系统设计

本文提出了基于全可编程片上系统（System-on-a-Chip,SoC）和实验室虚拟仪器工程平台（Laboratory Virtual Instrument Engineering Workbench,LabVIEW）的磁共振信号接收系统设计.使用集成了ARM（Advanced RISC Machines）和现场可编程门阵列（Field Programmable Gate Array,FPGA）的全可编程SoC作为接收机的主芯片,利用Xilinx提供的数字信号处理（Digital Signal Processing,DSP）开发工具System Generator设计了数字下变频（Digital Down Converter,DDC）算法,并实现了接收机硬件电路.使用可视化编程平台LabVIEW设计了磁共振上位机软件,完成了磁共振信号的显示、存储和与接收机通信的工作,提高了软件开发效率.实验结果表明,本文设计的接收机能正确接收磁共振回波信号,且具有较高的信噪比.     

基于Gadgetron平台的多GPU分布式磁共振图像重建

为了满足磁共振成像（MRI）临床扫描的需求,磁共振图像重建算法的开发一直在不断进行.目前广泛使用的算法实现方式是利用中央处理器（CPU）对磁共振扫描数据进行数学变换得到图像,随着算法复杂度的提升,计算性能问题逐渐显露.利用CPU在大数据量下执行复杂算法时,计算并行性的缺失以及运算中产生的海量数据的存储负荷会导致计算变得极为缓慢,使得一些算法因为重建时间过长,在临床上面临难以推广的问题,也制约了基础研究中新算法的研发.本文设计并实现了一种新的重建算法执行方式,利用Gadgetron磁共振软件重建平台在多核CPU基础上搭载多块图形处理器（GPU）,将磁共振图像重建以分布式并行计算方式实现,并以重建耗时较长的3D径向数据采集Stack of Star（SOS）的图像重建为实例,展示这种重建的实现方法能以相对低廉的硬件成本极大提升重建的速度.     

基于同时多层激发和并行成像的心脏磁共振电影成像

磁共振成像（MRI）无创无害、对比度多、可以任意剖面成像的特点特别适合用于心脏成像,却因扫描时间长限制了其在临床上的应用.为了解决心脏磁共振电影成像屏气扫描时间过长的问题,该文提出了一种基于同时多层激发的多倍加速心脏磁共振电影成像及其影像重建的方法,该方法将相位调制多层激发（CAIPIRINHA）技术与并行加速（PPA）技术相结合,运用到分段采集心脏电影成像序列中,实现了在相位编码方向和选层方向的四倍加速,并使用改进的SENSE/GRAPPA算法对图像进行重建.分别在水模以及人体上进行了实验,将加速序列图像与不加速序列图像进行对比,结果验证了重建算法的有效性,表明该方法可以在保障图像质量以及准确测量心脏功能的前提下成倍节省扫描时间.     

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.     

基于虚拟线圈和卷积神经网络的多层同时激发图像重建

本文提出一种基于虚拟共轭线圈（Virtual Coil Concept，VCC）技术和k空间插值鲁棒人工神经网络（Robust Artificial-neural-networks for k-space Interpolation，RAKI）的图像重建方法，用于磁共振多层同时激发成像（Simultaneous Multi-Slice imaging，SMS），该方法能够有效提升重建图像的质量，被命名为VIRGINIA（VIRtual conjuGate coIls Neural-networks InterpolAtion）.为了得到更高质量的SMS图像，本文提出的VIRGINIA方法利用磁共振线圈数据的复数共轭对称性质扩展了SMS所获取的多通道数据，并将扩展后的数据用于RAKI网络的训练，利用训练后的网络实现高质量的SMS图像重建.本文将VIRGINIA方法和其他SMS图像重建方法（RAKI和Slice-GRAPPA方法）进行了对比，并采用结构相似指数（Structural Similarity Index，SSIM）、峰值信噪比（Peak Signal-to-Noise Ratio，PSNR）和均方根误差（Root Mean Square Error，RMSE）对不同方法的重建图像进行了量化对比分析.结果显示，在相同的SMS加速倍数下，使用VIRGINIA方法进行重建的图像质量均好于RAKI方法，且远好于传统Slice-GRAPPA方法.     

Raysum reconstruction algorithm in MR cholangiopancreatography

Magnetic resonance cholangiopancreatography (MRCP) is a new, non-invasive imaging technique for the visualization of the biliary ducts. The presence of stones within the choledocus is easily detectable in source images. However, three-dimensional reconstructions using the maximum intensity pixel (or projection) algorithm (MIP) fail to reproduce accurately the eventual presence of filling defects or parietal irregularities due to biliary stones. We used the Raysum algorithm in addition to the MIP in evaluating MRCPs of twelve patients with known choledocolithiasis. A visualization of the stones was obtained in nine (75%) patients by using the Raysum while visualization was obtained in one patient by using MIP. No additional sequences are required, and the post-processing time takes only a few seconds. The Raysum reconstruction can be successfully associated to the MIP in the three-dimensional evaluation of biliary stones in MRCP.     

Multispectral MR images segmentation based on fuzzy knowledge and modified seeded region growing

Magnetic resonance imaging (MRI) is a valuable diagnostic tool in medical science due to its capability for soft-tissue characterization and three-dimensional visualization. One potential application of MRI in clinical practice is brain parenchyma classification and segmentation. Based on fuzzy knowledge and modified seeded region growing, this work proposes a novel image segmentation method, called Fuzzy Knowledge-Based Seeded Region Growing (FKSRG), for multispectral MR images. In this work, fuzzy knowledge includes the fuzzy edge, fuzzy similarity and fuzzy distance, which are obtained from relationships between pixels in multispectral MR images and are applied to the modified seeded regions growing process. In conventional regions merging, the final number of regions is unknown. Therefore, a Target Generation Process is proposed and applied to support conventional regions merging, such that the FKSRG method does not over- or undersegment images. Finally, two image sets, namely, computer-generated phantom images and real MR images, are used in experiments to assess the effectiveness of the proposed FKSRG method. Experimental results demonstrate that the FKSRG method segments multispectral MR images much more effectively than the Functional MRI of the Brain Automated Segmentation Tool, K-means and Support Vector Machine methods.     

Unified Generative Adversarial Networks for Multidomain Fingerprint Presentation Attack Detection

With the rapid growth of fingerprint-based biometric systems, it is essential to ensure the security and reliability of the deployed algorithms. Indeed, the security vulnerability of these systems has been widely recognized. Thus, it is critical to enhance the generalization ability of fingerprint presentation attack detection (PAD) cross-sensor and cross-material settings. In this work, we propose a novel solution for addressing the case of a single source domain (sensor) with large labeled real/fake fingerprint images and multiple target domains (sensors) with only few real images obtained from different sensors. Our aim is to build a model that leverages the limited sample issues in all target domains by transferring knowledge from the source domain. To this end, we train a unified generative adversarial network (UGAN) for multidomain conversion to learn several mappings between all domains. This allows us to generate additional synthetic images for the target domains from the source domain to reduce the distribution shift between fingerprint representations. Then, we train a scale compound network (EfficientNetV2) coupled with multiple head classifiers (one classifier for each domain) using the source domain and the translated images. The outputs of these classifiers are then aggregated using an additional fusion layer with learnable weights. In the experiments, we validate the proposed methodology on the public LivDet2015 dataset. The experimental results show that the proposed method improves the average classification accuracy over twelve classification scenarios from 67.80 to 80.44% after adaptation.     

Recent advances on optic nerve magnetic resonance imaging and post-processing

The optic nerve is known to be one of the largest nerve bundles in the human central nervous system. There have been many studies of optic nerve imaging and post-processing that have provided insights into pathophysiology of optic neuritis related to multiple sclerosis and neuromyelitis optica spectrum disorder, glaucoma, and Leber's hereditary optic neuropathy. There are many challenges in optic nerve imaging, due to the morphology of the nerve through its course to the optic chiasm, its mobility due to eye movements and the high signal from cerebrospinal fluid and orbital fat surrounding the optic nerve. Recently, many advanced and fast imaging sequences have been used with post-processing techniques in attempts to produce higher resolution images of the optic nerve for evaluating various diseases. Magnetic resonance imaging (MRI) is one of the most common imaging methodologies for the optic nerve. This review paper will focus on recent MRI advances in optic nerve imaging and explain several post-processing techniques being used for analysis of optic nerve images. Finally, some challenges and potential for future optic nerve studies will be discussed.     

Intracranial vessel wall imaging framework – Data acquisition,processing, and visualization

ObjectiveAssessment of vessel walls is an integral part in diagnosis and disease monitoring of vascular diseases such as vasculitis. Vessel wall imaging (VWI), in particular of intracranial arteries, is the domain of Magnetic Resonance Imaging (MRI) – but still remains a challenge. The tortuous anatomy of intracranial arteries and the need for high resolution within clinically acceptable scan times require special technical conditions regarding the hardware and software environments.Materials and methodsIn this work a dedicated framework for intracranial VWI is presented offering an optimized, black-blood 3D T1-weighted post-contrast Compressed Sensing (CS)-accelerated MRI sequence prototype combined with dedicated 3D-GUI supported post-processing tool for the CPR visualization of tortuous arbitrary vessel structures.ResultsUsing CS accelerated MRI sequence, the scanning time for high-resolution 3D black-blood CS-space data could be reduced to under 10 min. These data are adequate for a further processing to extract straightened visualizations (curved planar reformats – CPR). First patient data sets could be acquired in clinical environment.ConclusionA highly versatile framework for VWI visualization was demonstrated utilizing a post-processing tool to extract CPR reformats from high-resolution 3D black-blood CS-SPACE data, enabling simplified and optimized assessment of intracranial arteries in intracranial vascular disorders, especially in suspected intracranial vasculitis, by stretching their tortuous course. The processing time from about 15–20 min per patient (data acquisition and further processing) allows the integration into clinical routine.     

基于DSP的全数字低场MRI信号接收算法研究

针对低场磁共振成像（MRI）系统,提出一种实用的基于通用浮点DSP的全数字高精度、高效率信号接收算法. 对经前端调理的回波信号直接采样数字化,在通用浮点DSP上进行数字正交解调, 采用高效的积分梳状滤波器(CIC)、半带滤波器(HB)、FIR滤波器等进行多级滤波抽取,极大的减少了运算量,提高了运算效率,最后得到用于成像的原始数据. 整个数字信号处理过程全部采用单精度浮点数据格式,用软件实现,提高了运算精度,增加了信号检测系统的灵活性. 最后通过CCS2.2软件仿真,验证了本算法的实时性和实用性.     

旋转不变的非局域均值算法在磁共振图像去噪中的应用

磁共振成像（MRI）实验时常采用多次扫描累加平均提高图像信噪比（SNR）,但当扫描过程中运动引起图像变形时,简单地累加平均就无法奏效.为此,本研究组曾提出一种匹配加权平均方法（MWA）提高图像的信噪比.在此基础上,该文提出一种旋转不变的非局域均值算法（RINLM）,即选取圆形邻域区域并将其划分为一系列以中心像素为圆心的等面积圆环,再计算模式的相似性.RINLM算法可以更好地利用图像中旋转的冗余信息、找到更多的相似结构,提高算法的去噪性能.我们把该方法应用于低信噪比图像序列的平均和去噪中,可以更好地处理旋转的局部运动.与非局域均值算法（NLM）相比,RINLM算法可以进一步提高图像的信噪比;与MWA方法相比,其与RINLM算法的结合可以进一步提高磁共振图像序列信噪比,更好的保持图像边缘信息.     

Magnetic resonance imaging segmentation techniques using batch-type learning vector quantization algorithms

In this article, we propose batch-type learning vector quantization (LVQ) segmentation techniques for the magnetic resonance (MR) images. Magnetic resonance imaging (MRI) segmentation is an important technique to differentiate abnormal and normal tissues in MR image data. The proposed LVQ segmentation techniques are compared with the generalized Kohonen's competitive learning (GKCL) methods, which were proposed by Lin et al. [Magn Reson Imaging 21 (2003) 863-870]. Three MRI data sets of real cases are used in this article. The first case is from a 2-year-old girl who was diagnosed with retinoblastoma in her left eye. The second case is from a 55-year-old woman who developed complete left side oculomotor palsy immediately after a motor vehicle accident. The third case is from an 84-year-old man who was diagnosed with Alzheimer disease (AD). Our comparisons are based on sensitivity of algorithm parameters, the quality of MRI segmentation with the contrast-to-noise ratio and the accuracy of the region of interest tissue. Overall, the segmentation results from batch-type LVQ algorithms present good accuracy and quality of the segmentation images, and also flexibility of algorithm parameters in all the comparison consequences. The results support that the proposed batch-type LVQ algorithms are better than the previous GKCL algorithms. Specifically, the proposed fuzzy-soft LVQ algorithm works well in segmenting AD MRI data set to accurately measure the hippocampus volume in AD MR images.     

多通道相位图像的改进型自适应重建算法

自适应重建(Adaptive Reconstruction,AR)算法被广泛应用于磁共振图像的多通道合并问题上.AR算法不需要直接采集各个线圈的灵敏度信息,而是通过通道间信号及噪声相关矩阵,估算出各个通道的灵敏度,从而保证了合并的幅值图像具有较高的信噪比(Signal-to-Noise Ratio,SNR).然而,由于AR算法没有针对相位图像的合并问题进行优化,导致重建出的相位图像具有不确定性.另外,受各通道之间相位偏移及低信噪比相位图像的影响,重建结果可能包含伪影.该文提出了一种改进型AR算法,估算并移除了各通道之间的相位偏移,同时对多通道数据的相位进行质量评估及通道重排,用以进行后续自适应重建.仿体及在体实验表明,该方法可以有效提升AR算法稳定性、消除重建图像中存在的伪影,同时保持合并后幅值图像及相位图像的高信噪比.     

MRI评价药物投递性能方法研究

采用MRI评价自制肝组织特异性非离子型高分子磁共振造影剂在小鼠体内药物投递效果. 分别在注射造影剂后0.1 h、6 h、12 h、24 h及7天采集磁共振T₁加权图像. 所有扫描均在1.5T临床磁共振成像仪上完成, 以固定体线圈为射频发射线圈, 三英寸圆形表面线圈为信号接收线圈. 数据分析前采用线圈非均匀性校正和信号非稳定性校正进行预处理. 实验结果显示,线圈空间敏感性校正使得小鼠组织图像信号强度空间更加均匀,稳定性校正后使得图像数据更加准确可靠,MRI是一种在体评价顺磁性标记高分子化合物药物投递效果的有效方法.