Development of fast deep learning quantification for magnetic resonance fingerprinting in vivo

PurposeA deep neural network was developed for magnetic resonance fingerprinting (MRF) quantification. This study aimed at extending previous studies of deep learning MRF to in vivo applications, allowing sub-second computation time for large-scale data.MethodsWe applied the deep learning methodology based on our previously published multi-layer perceptron. The number of layers was four, which was optimized to balance the model capacity and noise robustness. The training sets were obtained from MRF dictionaries with 9000 to 28,000 atoms, depending on the desired T1 and T2 ranges. The simulated MRF undersampling artifact based on the k-space acquisition scheme and noise were both added to the training data to reduce the error in estimates.ResultsThe neural network achieved high fidelity (R2 _ 0.98) as compared to the T1 and T2 values of the ISMRM standardized phantom. In brain MRF experiment, the model trained with simulated artifacts and noise showed less error compared to that without. The in vivo application of our neural network for liver and prostate were also demonstrated. For an MRF slice with 256 _ 256 image resolution, the computation time of our neural network was 0.12 s, compared with the _ 28 s-pre-slice for the conventional dictionary matching method.ConclusionOur neural network achieved fast computation speed for MRF quantification. The model trained with simulated artifacts and noise showed less error and achieved optimal performance for phantom experiment and in vivo normal brain and liver, and prostate cancer patient.     

K-SVD和OMP算法在超声信号去噪中的应用

针对在线采集时超声波检测信号中存在大量噪声,降低了材料内部缺陷诊断准确性的问题,提出了一种基于广义K+奇异值分解算法(K-SVD)和正交匹配追踪算法(OMP)相结合的超声回波信号去噪算法。该算法利用K-SVD算法将Gabor字典训练成能够最有效反映信号结构特征的超完备字典,然后基于训练完成的超完备字典,用OMP算法把一定数量的字典原子进行线性组合来构成原始信号,从而实现信号的去噪。通过仿真实验将本文方法与传统的小波阈值去噪方法进行了对比研究。实验结果表明,该方法对超声回波信号的去噪效果优于小波阈值去噪方法,且噪声越大对比越明显,不仅可更有效地滤除信号中的高斯白噪声,提高信噪比,且尽可能保留了原始信号有用信息。     

MR fingerprinting reconstruction with Kalman filter

Magnetic resonance fingerprinting (MR fingerprinting or MRF) is a newly introduced quantitative magnetic resonance imaging technique, which enables simultaneous multi-parameter mapping in a single acquisition with improved time efficiency. The current MRF reconstruction method is based on dictionary matching, which may be limited by the discrete and finite nature of the dictionary and the computational cost associated with dictionary construction, storage and matching.In this paper, we describe a reconstruction method based on Kalman filter for MRF, which avoids the use of dictionary to obtain continuous MR parameter measurements. With this Kalman filter framework, the Bloch equation of inversion-recovery balanced steady state free-precession (IR-bSSFP) MRF sequence was derived to predict signal evolution, and acquired signal was entered to update the prediction. The algorithm can gradually estimate the accurate MR parameters during the recursive calculation. Single pixel and numeric brain phantom simulation were implemented with Kalman filter and the results were compared with those from dictionary matching reconstruction algorithm to demonstrate the feasibility and assess the performance of Kalman filter algorithm.The results demonstrated that Kalman filter algorithm is applicable for MRF reconstruction, eliminating the need for a pre-define dictionary and obtaining continuous MR parameter in contrast to the dictionary matching algorithm.     

snapMRF: GPU-accelerated magnetic resonance fingerprinting dictionary generation and matching using extended phase graphs

Purpose:Magnetic resonance fingerprinting (MRF) is a state-of-the-art quantitative MRI technique with a computationally demanding reconstruction process, the accuracy of which depends on the accuracy of the signal model employed. Having a fast, validated, open-source MRF reconstruction would improve the dependability and accuracy of clinical applications of MRF.Methods:We parallelized both dictionary generation and signal matching on the GPU by splitting the simulation and matching of dictionary atoms across threads. Signal generation was modeled using both Bloch equation simulation and the extended phase graph (EPG) formalism. Unit tests were implemented to ensure correctness. The new package, snapMRF, was tested with a calibration phantom and an in vivo brain.Results:Compared with other online open-source packages, dictionary generation was accelerated by 10–1000× and signal matching by 10–100×. On a calibration phantom, T₁ and T₂ values were measured with relative errors that were nearly identical to those from existing packages when using the same sequence and dictionary configuration, but errors were much lower when using variable sequences that snapMRF supports but that competitors do not.Conclusion:Our open-source package snapMRF was significantly faster and retrieved accurate parameters, possibly enabling real-time parameter map generation for small dictionaries. Further refinements to the acquisition scheme and dictionary setup could improve quantitative accuracy.     

近似零伪范数约束的水声信号压缩与重构

提出近似零伪范数约束的稀疏压缩与重构方法。该方法首先采用稀疏二进制矩阵作为测量矩阵,对信号进行压缩和传输;在接收端仅给定测量矩阵和压缩信号的条件下,采用小波滤波器设计字典,利用最陡梯度法寻优和投影方法求得信号的稀疏表达,最终结合稀疏表达值与字典用于水声数据重建,海试实验结合扫频以及单载频信号进行处理,采用NMSE、SNR以及算法运行时间作为算法的评估指标,以验证本文方法相对于传统算法在恢复精度上的提高。      

基于Karhunen-Loève变换和小波谱特征矢量量化的三维谱像数据压缩

提出了基于Karhunen Lo埁ｖｅ变换的小波谱特征矢量量化三维谱像数据压缩方法耍幔颍瑁酰睿澹?Lo埁ｖｅ变换 /小波变换 /小波谱特征矢量量化方法应用了Karhunen Lo埁ｖｅ变换的消除谱相关性优良性能 ,应用二维小波变换消除空间相关性 ,在小波变换域内应用二维集分割嵌入块编码和一维谱特征矢量量化对三维谱像数据压缩 ,获得较高的压缩性能。实验结果表明 :Karhunen Lo埁ｖｅ变换 /小波变换 /小波谱特征矢量量化编码比Karhunen Lo埁ｖｅ变换 /小波变换 /改进对块零树编码和Karhunen Lo埁ｖｅ变换 /小波变换 /快速矢量量化编码方法在同样压缩比条件下 ,峰值信噪比提高 2dB和 1dB以上 ,而速度提高了 1.5和 8倍 ,整体压缩性能有较大的提高     

一种消除测速模糊的梳状谱信号设计方法

相比于传统信号,梳状谱具有更好的混响抑制能力,但其容易产生多普勒测速模糊。为了解决这一问题,设计了一种新的几何梳状谱信号,通过分析测速模糊产生的原因,在传统频点计算方法的基础上,利用在信号频点计算中加入一组抗多普勒频率间隔的方法,以降低频点的重合。仿真分析证明,提出的梳状谱信号设计方法有效的减少了速度搜索时频谱重叠的程度,无论在噪声还是混响限制条件下均可以获得一个明显的输出峰值,避免了测速模糊的问题,可以获得比传统信号更好的检测性能。     

基于结构字典学习的图像复原方法

本文提出一种新的结构字典学习方法,并利用它进行图像复原。首先给出结构字典学习的基本内容和方法,然后将傅里叶正则化方法和结构字典学习方法有效整合到图像复原算法中。结构字典学习方法是先将原图像进行结构分解,再分别学习出每个结构图像中的字典,最后利用这些字典对原图像进行稀疏的表示。结合傅里叶正则化,提出了一种有效的迭代图像复原算法:第一步在傅里叶域利用正则化反卷积方法得到图像的初步估计;第二步采用结构字典学习的方法对遗留的噪声进行去噪处理。实验结果表明,提出的方法在改进信噪比和视觉质量上都要优于6种先进的图像复原方法,改进的信噪比平均提升0.5 d B以上。     

分块稀疏信号1-bit压缩感知重建方法

1-bit压缩感知理论指出:对稀疏信号进行少量线性投影并对投影信号进行1-bit量化,该1-bit信号包含足够的信息,从而能对原始信号进行高精度重建.然而,当信号难以进行稀疏表达时,传统1-bit压缩感知算法无法精确重建原始信号.前期研究表明,分块稀疏模型作为一种特殊的结构型稀疏模型,对于难以用传统稀疏模型进行表达的信号具有较好的表达作用.本文提出了一种针对分块稀疏信号的1-bit压缩感知重建方法,该方法利用分块稀疏的统计特性对信号进行数学建模,通过变分贝叶斯推断方法进行信号重建并在光电容积脉搏波(photoplethysmography)信号上进行了实验验证.实验结果表明,与现有1-bit压缩感知重建方法相比,本文方法重建精度更高,且收敛速度更快.     

Simultaneous quantification of SPIO and gadolinium contrast agents using MR fingerprinting

PurposeDevelop a magnetic resonance fingerprinting (MRF) methodology with R₂¹ quantification, intended for use with simultaneous contrast agent concentration mapping, particularly gadolinium (Gd) and iron labelled CD8+ T cells.MethodsVariable-density spiral SSFP MRF was used, modified to allow variable TE, and with an exp.(−TE·R₂¹) dictionary modulation. In vitro phantoms containing SPIO labelled cells and/or gadolinium were used to validate parameter maps, probe undersampling capacity, and verify dual quantification capabilities. A C57BL/6 mouse was imaged using MRF to demonstrate acceptable in vivo resolution and signal at 8× undersampling necessary for a 25-min scan.ResultsStrong agreement was found between conventional and MRF-derived values for R₁, R₂, and R₂¹. Expanded MRF allowed quantification of iron-loaded CD8+ T cells. Results were robust to 8× undersampling and enabled recreation of relaxation profiles for both a Gd agent and iron labelled cells simultaneously. In vivo data demonstrated sufficient SNR in undersampled data for parameter mapping to visualise key features.ConclusionMRF can be expanded to include R₁, R₂, and R₂¹ mapping required for simultaneous quantification of gadolinium and SPIO in vitro, allowing for potential implementation of a variety of future in vivo studies using dual MR contrast agents, including molecular imaging of labelled cells.     

AIR-MRF: Accelerated iterative reconstruction for magnetic resonance fingerprinting

Existing approaches for reconstruction of multiparametric maps with magnetic resonance fingerprinting (MRF) are currently limited by their estimation accuracy and reconstruction time. We aimed to address these issues with a novel combination of iterative reconstruction, fingerprint compression, additional regularization, and accelerated dictionary search methods. The pipeline described here, accelerated iterative reconstruction for magnetic resonance fingerprinting (AIR-MRF), was evaluated with simulations as well as phantom and in vivo scans. We found that the AIR-MRF pipeline provided reduced parameter estimation errors compared to non-iterative and other iterative methods, particularly at shorter sequence lengths. Accelerated dictionary search methods incorporated into the iterative pipeline reduced the reconstruction time at little cost of quality.     

一种快速的分形图像压缩编码方法

针对分形压缩编码存在耗时过长的问题 ,提出一种快速分形编码算法 :即利用快速卷积来计算图像块之间的互相关 ,从而对编码过程进行无损加速。经仿真实验表明 :与经典的分割迭代函数系统 (PIFS)方法相比 ,在信噪比可接受的前题下 ,该算法的压缩比和编码速度均有显著提高。     

基于最小二乘法的动态光谱补偿拟合提取

高信噪比的动态光谱(dynamic spectrum, DS)提取是实现高精度动态光谱血液成分无创检测的一个关键。为了进一步提高提取的精度和速度,从原理上分析了各单波长光电容积脉搏波(photoelectric plethysmography,PPG)的线性相似性,并基于此性质提出了补偿拟合法：首先按照PPG单周期采样点数进行滑动平均得到漂移基线进行补偿,除去基线漂移;其次用各波长对数PPG与全波长叠加平均模板PPG进行最小二乘拟合,提取一次项系数构成DS。利用拟合提取法对近红外和可见光波段各25组PPG数据样本进行DS提取实验验证,并将结果与单沿提取法进行平滑性指标的对比,结果表明：近红外和可见光波段补偿拟合法获取DS的平均方差分别为单沿提取法的77.9%和59.5%,稳定提高了DS的平滑性;近红外和可见光波段补偿拟合法处理时间分别可以达到单沿提取法的10%和20%,处理速度得到显著改善。补偿拟合法在单沿提取法的基础上稳定提高了DS的信噪比,改善了DS提取质量,缩减了提取时间,并简化了处理步骤,有望推动DS无创血液成分检测的发展。     

一种强噪声背景下微弱超声信号提取方法研究

为解决在强噪声背景下获取超声信号的难题,基于粒子群优化算法和稀疏分解理论提出一种强噪声背景下微弱超声信号提取方法.该方法将降噪问题转换为在无穷大参数集上对函数进行优化的问题,首先以稀疏分解理论和超声信号的结构特点为依据构建了粒子群优化算法运行所需要的目标函数及去噪后信号的重构函数,从而将粒子群优化算法和超声信号降噪联系在一起;然后根据粒子群优化算法可以在连续参数空间寻优的特点建立了用于匹配超声信号的连续超完备字典,并采用改进的自适应粒子群优化算法在该字典中对目标函数进行优化;最后根据对目标函数在字典上的优化结果确定最优原子,并利用最优原子按照重构函数重构出降噪后的超声信号.通过对仿真超声信号和实测超声信号的处理,结果表明本文提出的方法可以有效提取信噪比低至-4 dB的强噪声背景下的微弱超声信号,且和基于自适应阈值的小波方法相比本文方法表现出更好的降噪性能.     

数字照片图像来源检测中的传感器模式噪声预处理方法

针对传感器模式噪声易受CFA插值噪声和JPEG压缩噪声污染,提出一种基于空域平滑滤波的传感器模式噪声预处理方法,去除干扰噪声,从而提高数字照片图像来源检测准确率.假设传感器模式噪声是一种类似高斯白噪声的随机信号,其在频域具有与高斯白噪声相似的平坦频谱;基于此,在空域采用高斯白噪声对传感器模式噪声进行引导滤波,其空域平滑效果使传感器模式噪声在保持自身性质的同时,拥有与高斯白噪声相似的特性.手机相机照片图像库的评估实验结果表明,与现有预处理方法相比,所提算法在图像来源检测准确度上Kappa统计系数提高了0.026以上,同时算法对JPEG压缩的鲁棒性也明显优于其他算法.     

Towards predicting the encoding capability of MR fingerprinting sequences

Sequence optimization and appropriate sequence selection is still an unmet need in magnetic resonance fingerprinting (MRF). The main challenge in MRF sequence design is the lack of an appropriate measure of the sequence's encoding capability. To find such a measure, three different candidates for judging the encoding capability have been investigated: local and global dot-product-based measures judging dictionary entry similarity as well as a Monte Carlo method that evaluates the noise propagation properties of an MRF sequence. Consistency of these measures for different sequence lengths as well as the capability to predict actual sequence performance in both phantom and in vivo measurements was analyzed. While the dot-product-based measures yielded inconsistent results for different sequence lengths, the Monte Carlo method was in a good agreement with phantom experiments. In particular, the Monte Carlo method could accurately predict the performance of different flip angle patterns in actual measurements. The proposed Monte Carlo method provides an appropriate measure of MRF sequence encoding capability and may be used for sequence optimization.     

Shadow regions detection algorithm by adaptive narrowband two-phase Chan-Vese model

An adaptive narrowband two-phase Chan-Vese(ANBCV) model is proposed for im?proving the shadow regions detection performance of sonar images. In the first noise smoothing step, the anisotropic second-order neighborhood MRF(Markov Random Field, MRF) is used to describe the image texture feature parameters. Then, initial two-class segmentation is processed with the block mode /c-means clustering algorithm, to estimate the approximate position of the shadow regions. On this basis, the zero level set function is adaptively initialized by the approximate position of shadow regions. ANBCV model is provided to complete local op?timization for eliminating the image global interference and obtaining more accurate results.Experimental results show that the new algorithm can efficiently remove partial noise, increase detection speed and accuracy, and with less human intervention.     

Chan-Vese模型两相自适应窄带的阴影区检测方法

为得到快速高精度的声呐图像阴影区检测效果,提出Chan-Vese模型两相自适应窄带检测方法。利用各向异性二阶邻域马尔可夫模型估计声呐图像的纹理特征参数,实现原始图像平滑去噪;由块方式的k-均值聚类算法确定图像的初始两类分割,初步确定阴影区大致位置,并根据此大致位置,自适应初始化零水平集函数,来减少人为干预,提高检测速度;在此基础上,提出建立Chan-Vese模型两相窄带水平集进行声呐图像检测,完成局部寻优,排除全局图像中孤立区对检测的影响,使阴影区检测结果更加精确。通过对真实声呐图像的检测实验结果分析,验证提出的检测方法能够去除原始图像的部分噪声,提高检测精度和速度,有一定的自动性和适应性。      

基于稀疏分解的大功率半导体激光器1/f噪声参数估计的新方法

本文结合1/f噪声信号功率谱随频率成反比变化的关系, 以及稀疏分解可以根据信号灵活构造原子库的特点, 提出一种基于稀疏分解估计大功率半导体激光器1/f噪声的新方法, 构造了具备1/f噪声特点的过完备库. 在该过完备库中通过Matching Pursuit(MP)算法完成了白噪声与1/f噪声混叠信号的稀疏分解. 实验结果显示:该方法估计出淹没在白噪声环境中1/f噪声的γ 参数, 与频谱分析仪的测量结果有较好的一致性, 通过对比不同的过完备库证明了所构造的过完备库的优越性.     

基于字典学习和稀疏表示的单通道语音增强算法综述*

如何从带噪语音信号中恢复出干净的语音信号一直都是信号处理领域的热点问题。近年来研究者相继提出了一些基于字典学习和稀疏表示的单通道语音增强算法,这些算法利用语音信号在时频域上的稀疏特性,通过学习训练数据样本的结构特征和规律来构造相应的字典,再对带噪语音信号进行投影以估计出干净语音信号。针对训练样本与测试数据不匹配的情况,有监督类的非负矩阵分解方法与基于统计模型的传统语音增强方法相结合,在增强阶段对语音字典和噪声字典进行更新,从而估计出干净语音信号。本文首先介绍了单通道情况下语音增强的信号模型,然后对4种典型的增强方法进行了阐述,最后对未来可能的研究热点进行了展望。