基于加权压缩感知的MR图像重建方法

背景：压缩感知理论已广泛应用于MR图像的快速重建中。在对K空间数据进行随机欠采样后,通过非线性优化算法求解带约束的范数最小化问题,可恢复出在变换域具有稀疏性的MR图像。 目的：为了增强图像在变换域中的稀疏性,改善MR图像重建质量,提出了对待重建图像的稀疏表示进行加权的方法。 方法：采用非线性共轭梯度下降算法求解该加权范数最小化问题,在迭代过程中,根据所求取的图像稀疏表示来更新权值矩阵,增强MR图像的稀疏性。 结果与结论：通过比较带加权矩阵和不带加权矩阵的压缩感知图像重建方法,结果表明带加权矩阵改进的算法提高了图像重建能力。     

基于压缩感知算法的基因表达谱数据分析

目的 基因表达谱数据分析是生物信息学领域最重要的研究内容之一.其可实现对不同病理分型的肿瘤的正确分类,对肿瘤诊断和治疗具有重大意义.方法 本文应用压缩感知算法实现对胃癌基因表达谱数据的分类,运用训练数据构造冗余字典,采用随机分布的规范行矢量高斯矩阵构造感知矩阵,对训练数据和测试数据进行感知,利用正交l2-范数算法对基因表达谱数据进行重建,在变换域中采用近邻法测试判断数据类别,与样本的实际类别相比较.结果 实验结果表明,压缩感知算法与K均值聚类、SVM等其他分类算法相比有较高的分类正确率,且分类速度快,能避免特征选取的问题.结论 本文方法对疾病的临床诊断和生物信息学研究有重要的参考和借鉴作用.     

压缩感知磁共振成像脉冲序列的设计与实现

为了进一步减少数据扫描时间,提高磁共振成像速度,我们对压缩感知MRI脉冲序列进行了研究。采用相位编码方向变密度欠采集的方式,设计了基于自旋回波的压缩感知序列;并采用PPL语言编程,在永磁和超导MR扫描仪上实现了该序列,对压缩感知欠采集与自旋回波全采集的数据进行了图象重建和分析。结果表明:该序列达到了压缩感知的要求,采集的头部和膝盖数据的最佳欠采样加速因子分别为2和4,大大节省了数据采集时间。该序列的实现使得低场强MR扫描仪在不提高梯度性能的情况下,便可实现快速成像,为提高我国在MR扫描仪上的研发水平奠定了基础。     

基于压缩感知的CT重建算法的研究现状

压缩感知理论是一种新兴的信号获取与处理理论,通过减少信号重建所需的数据以缩短信号采样时间,减少计算量,并在一定程度上保持原有图像的重建质量,由此可以解决在CT重建中还普遍存在的清晰度不够高、线性度不够好和有噪声伪影干扰等问题。由于该理论的这些显著优点,使其在CT成像领域引起了广泛关注,取得了很大进展。本文对近几年压缩感知应用于CT重建的研究方法和成果进行归纳和分析,其中包括传统统计迭代算法与压缩感知理论相结合方法的分析,先验图像约束与压缩感知理论相结合方法的分析以及字典学习的发展历程分析。最后,对该研究领域的发展进行了展望。     

基于压缩感知的磁共振图像重建算法的VC实现

我们对压缩感知重建算法在MRI中的应用进行了研究,并在VC6.0平台下对其进行工程实现。该程序主要由以下几部分组成：（1）建立图像模型及引入仪器采集数据;（2）设计采样方法模拟压缩感知的稀疏采集;（3）选择图像稀疏变换方法;（4）选用压缩感知算法重建得到图像。结果表明：使用该方法可以成功重建出高质量的图像,为压缩感知算法在MRI扫描仪器上的使用提供了重要参考。     

基于Bandlet的压缩感知算法及其在智能乳腺全容积超声系统中的应用

目的在智能乳腺全容积超声系统中需扫描很多个切面同时进行成像和保存,数据量庞大。为此,本文提出基于Bandlet变换的压缩感知方法并应用于该系统,以降低存储和传输的数据量。方法首先利用超声图像的Bandlet变换域能够根据图像的"几何正则性"来自适应改变得到稀疏表示的特点,将所得图像进行Bandlet变换。然后选择与Bandlet基矩阵不相干的随机测量来降低图像压缩的数据量,之后利用匹配追踪算法由压缩数据重建超声图像。最后以智能乳腺全容积超声系统的图像数据为例进行压缩效率和重建有效性的验证。结果压缩后的数据大小为原数据的30%,降低了传输和存储的数据量,同时可得到高质量的重建图像。结论基于Bandlet的压缩感知算法可降低智能乳腺全容积超声系统图像的传输带宽和数据量,并保证了图像重建的质量,适用于智能乳腺全容积超声系统。     

基于参考图像的压缩感知磁共振扩散张量成像

基于参考图像的压缩感知磁共振扩散张量成像方法,利用相邻方向的扩散加权图像差异较小的特点,采用压缩感知理论实现快速扩散张量成像,回顾性选取扩散张量图像数据进行实验研究,在采样率为50%的均匀分布辐射线欠采样方式下进行基于参考图像的压缩感知扩散张量图像重建,结果表明重建后的扩散加权图的平均结构相似性（MSSIM）和峰值信噪比（PSNR）分别为0.904±0.044、（37.92±3.89） dB,各向异性分数图的MSSIM和PSNR分别为0.992、41.64 dB。因此,该方法在保证重建图像质量的前提下,可显著缩短数据采集时间,减少由于时间过长引起的图像伪影等问题。     

一种基于人类感知的医学图象压缩方法

作者详细地介绍了一种基于人类感知的医学图象压缩算法，它利用人类视觉的运动特性，空间频率特性及时间频率特性对静止灰度图象进行有限失真压缩，该方法能大大压缩图象数据提高压缩比，对医学图象的压缩是一种比较有效的方法。     

采用径向压缩的超声弹性成像逆问题求解

超声弹性成像在前列腺的应用以及血管弹性成像中,组织压缩的方向是沿径向的.本文利用极坐标下的应力-应变关系,提出一种有限元迭代的方法,进行组织弹性模量分布的重建,即弹性成像逆问题的求解.采用扇形组织模型和环形组织模型两种模型进行了计算机仿真,分别用来模拟超声弹性成像在前列腺中的应用情形和血管弹性成像的情形.仿真结果表明了该方法的可行性.     

基于压缩感知理论的医学图像重构算法研究现状

压缩感知理论的提出促进了医学成像技术的发展。压缩感知是通过直接采集压缩后的数据,利用重构算法高精度恢复原信号,避免了传统的先采样再压缩造成的资源浪费。基于压缩感知的CT、MRI、US成像的重构算法对其应用于医学成像起着至关重要的作用。因此,对重构算法进行了着重介绍,并进行比较分析。     

Accelerated three‐dimensional cine phase contrast imaging using randomly undersampled echo planar imaging with compressed sensing reconstruction

The aim of this study was to implement and evaluate an accelerated three‐dimensional (3D) cine phase contrast MRI sequence by combining a randomly sampled 3D k‐space acquisition sequence with an echo planar imaging (EPI) readout. An accelerated 3D cine phase contrast MRI sequence was implemented by combining EPI readout with randomly undersampled 3D k‐space data suitable for compressed sensing (CS) reconstruction. The undersampled data were then reconstructed using low‐dimensional structural self‐learning and thresholding (LOST). 3D phase contrast MRI was acquired in 11 healthy adults using an overall acceleration of 7 (EPI factor of 3 and CS rate of 3). For comparison, a single two‐dimensional (2D) cine phase contrast scan was also performed with sensitivity encoding (SENSE) rate 2 and approximately at the level of the pulmonary artery bifurcation. The stroke volume and mean velocity in both the ascending and descending aorta were measured and compared between two sequences using Bland–Altman plots. An average scan time of 3 min and 30 s, corresponding to an acceleration rate of 7, was achieved for 3D cine phase contrast scan with one direction flow encoding, voxel size of 2 × 2 × 3 mm³, foot–head coverage of 6 cm and temporal resolution of 30 ms. The mean velocity and stroke volume in both the ascending and descending aorta were statistically equivalent between the proposed 3D sequence and the standard 2D cine phase contrast sequence. The combination of EPI with a randomly undersampled 3D k‐space sampling sequence using LOST reconstruction allows a seven‐fold reduction in scan time of 3D cine phase contrast MRI without compromising blood flow quantification. Copyright © 2014 John Wiley & Sons, Ltd.     

Non‐uniformly under‐sampled multi‐dimensional spectroscopic imaging in vivo: maximum entropy versus compressed sensing reconstruction

The four‐dimensional (4D) echo‐planar correlated spectroscopic imaging (EP‐COSI) sequence allows for the simultaneous acquisition of two spatial (k_y, k_x) and two spectral (t₂, t₁) dimensions in vivo in a single recording. However, its scan time is directly proportional to the number of increments in the k_y and t₁ dimensions, and a single scan can take 20–40 min using typical parameters, which is too long to be used for a routine clinical protocol. The present work describes efforts to accelerate EP‐COSI data acquisition by application of non‐uniform under‐sampling (NUS) to the k_y–t₁ plane of simulated and in vivo EP‐COSI datasets then reconstructing missing samples using maximum entropy (MaxEnt) and compressed sensing (CS). Both reconstruction problems were solved using the Cambridge algorithm, which offers many workflow improvements over other l₁‐norm solvers. Reconstructions of retrospectively under‐sampled simulated data demonstrate that the MaxEnt and CS reconstructions successfully restore data fidelity at signal‐to‐noise ratios (SNRs) from 4 to 20 and 5× to 1.25× NUS. Retrospectively and prospectively 4× under‐sampled 4D EP‐COSI in vivo datasets show that both reconstruction methods successfully remove NUS artifacts; however, MaxEnt provides reconstructions equal to or better than CS. Our results show that NUS combined with iterative reconstruction can reduce 4D EP‐COSI scan times by 75% to a clinically viable 5 min in vivo, with MaxEnt being the preferred method. Copyright © 2013 John Wiley & Sons, Ltd.     

Temporal differences (TED) compressed sensing: a method for fast MRgHIFU temperature imaging

This work proposes the Temporal Differences (TED) Compressed Sensing (CS) method for accelerating thermal monitoring in MR‐guided High‐Intensity Focused Ultrasound (MRgHIFU) treatments. TED combines k‐space subsampling, parallel imaging, and a unique CS recovery of the temporal differences between pre‐heating and post‐heating multi‐coil data. TED was validated through retrospective experiments with (i) two phantom datasets acquired with 1.5 T and 3 T MRgHIFU systems from different vendors, (ii) data from an in vivo animal model experiment, and (iii) four datasets from clinical in vivo MRgHIFU treatments of prostate cancer in humans. TED produced highly accurate temperature change maps from subsampled k‐space data for all datasets. For the clinical in vivo data, an analysis of 105 time frames showed that the average TED reconstruction error is 1.06‐1.67 °C. Furthermore, TED consistently outperforms two state‐of‐the‐art methods, l₁‐SPIRiT and the K‐space Hybrid Method, and offers errors that are significantly lower, by 29% or more. Moreover, TED offers robust performance over a range of its tunable parameters, stability across MRgHIFU systems from different vendors, and a short runtime of 1.7 s. In summary, TED enables k‐space subsampling while retaining high‐temperature mapping accuracy.     

Comparison of basis functions and q‐space sampling schemes for robust compressed sensing reconstruction accelerating diffusion spectrum imaging

Time constraints placed on magnetic resonance imaging often restrict the application of advanced diffusion MRI (dMRI) protocols in clinical practice and in high throughput research studies. Therefore, acquisition strategies for accelerated dMRI have been investigated to allow for the collection of versatile and high quality imaging data, even if stringent scan time limits are imposed. Diffusion spectrum imaging (DSI), an advanced acquisition strategy that allows for a high resolution of intra‐voxel microstructure, can be sufficiently accelerated by means of compressed sensing (CS) theory. CS theory describes a framework for the efficient collection of fewer samples of a data set than conventionally required followed by robust reconstruction to recover the full data set from sparse measurements. For an accurate recovery of DSI data, a suitable acquisition scheme for sparse q‐space sampling and the sensing and sparsifying bases for CS reconstruction need to be selected. In this work we explore three different types of q‐space undersampling schemes and two frameworks for CS reconstruction based on either Fourier or SHORE basis functions. After CS recovery, diffusion and microstructural parameters and orientational information are estimated from the reconstructed data by means of state‐of‐the‐art processing techniques for dMRI analysis. By means of simulation, diffusion phantom and in vivo DSI data, an isotropic distribution of q‐space samples was found to be optimal for sparse DSI. The CS reconstruction results indicate superior performance of Fourier‐based CS‐DSI compared to the SHORE‐based approach. Based on these findings we outline an experimental design for accelerated DSI and robust CS reconstruction of the sparse measurements that is suitable for the application within time‐limited studies.     

Accelerated high‐frame‐rate mouse heart cine‐MRI using compressed sensing reconstruction

We introduce a new protocol to obtain very high‐frame‐rate cinematographic (Cine) MRI movies of the beating mouse heart within a reasonable measurement time. The method is based on a self‐gated accelerated fast low‐angle shot (FLASH) acquisition and compressed sensing reconstruction. Key to our approach is that we exploit the stochastic nature of the retrospective triggering acquisition scheme to produce an undersampled and random k–t space filling that allows for compressed sensing reconstruction and acceleration. As a standard, a self‐gated FLASH sequence with a total acquisition time of 10 min was used to produce single‐slice Cine movies of seven mouse hearts with 90 frames per cardiac cycle. Two times (2×) and three times (3×) k–t space undersampled Cine movies were produced from 2.5‐ and 1.5‐min data acquisitions, respectively. The accelerated 90‐frame Cine movies of mouse hearts were successfully reconstructed with a compressed sensing algorithm. The movies had high image quality and the undersampling artifacts were effectively removed. Left ventricular functional parameters, i.e. end‐systolic and end‐diastolic lumen surface areas and early‐to‐late filling rate ratio as a parameter to evaluate diastolic function, derived from the standard and accelerated Cine movies, were nearly identical. Copyright © 2012 John Wiley & Sons, Ltd.