基于各向异性扩散的B超图像去噪

提出了一种基于各向异性扩散方程的B超图像斑点噪声抑制的算法.斑点噪声是由超声成像机制引起的固有噪声形态,它对B超图像的特征提取、识别和分析带来极大困难.特别是对于边缘提取,斑点噪声使得传统的提取算法几乎都无法取得理想的效果.各向异性扩散方程是一种能有效抑制斑点噪声的算法,本文针对原始算法中扩散系数过饱和的问题以及斑点尺度系数选择的不足,提出了改进的方法,从而在抑制斑点噪声的同时保留甚至增强B超图像中的边缘细节信息,为下一步的边缘提取提供了有效保障.     

基于比率距离的自适应超声图像去噪方法

针对超声图像噪声的瑞利分布特性,使用一种新的自适应超声图像去噪方法,改进固定窗口包含边缘时无法做到沿边缘方向滤波的不足。采用可自由伸缩的自适应滤波窗口,首先针对瑞利分布的噪声引入比率距离,得到超声图像像素间的相似度距离,然后考虑像素的邻域图像块均值,解决相似度距离之间比较的问题,最后像素根据新的相似度距离进行八方向伸展,得到不规则形状的滤波窗口进行去噪。用仿真超声图像和临床超声图像进行实验,图像评价指标结果表明该算法优于经典算法,更适用于去除超声图像的斑点噪声,在去除噪声的同时能够较好地保留细节边缘。     

基于盲解卷积的医学超声图像复原算法研究进展

医学超声成像受其成像机制的限制,会导致系统分辨率不高.为了获得诊断学上的重要信息,通常需要进行图像复原.在实际情况中,医学超声成像系统的退化过程难以精确地描述出来,故当点扩散函数未知或先验知识较少时,采用盲图像复原算法从退化图像中进行原始图像估计.主要针对基于盲解卷积的医学超声图像复原算法进行综述,并根据辨识方法分为先验辨识法和联合辨识法,分析讨论各种盲复原方法的基本理论和改进方法,最后提出了医学超声图像盲复原算法的发展方向.     

基于图像对比度分析的自适应超声声速优化

本文提出一种基于图像对比度分析的自适应声速优化技术,从而实时得到对比度增强、组织结构清晰可见的超声影像。论文首先描述超声系统动态延迟聚焦的波束形成过程,并引入系统声速以及组织真实声速等概念,进而讨论其两者不匹配对图像品质的影响。介绍图像灰度值表示的对比度之后,论文阐述了准确估计与组织声速一致的系统声速的基本原理。最后,论文通过已知声速的仿人体组织体模和真实人体组织超声影像来验证,并与已有声速优化方法进行比较。实验结果不仅表明本研究所估计的声速是准确的,而且算法运算速度亦适用于超声系统的实时应用。     

基于超声图像的乳腺钙化点自动检测技术

当前乳腺钙化点检测方法多基于X光片,难以应用于超声图像,本研究提出基于超声图像的乳腺钙化点自动检测技术,首先将乳腺超声图像中的肿瘤区域通过勾画模板提取出来,基于简单线性迭代聚类算法进行超像素分割;然后提取表征各超像素的特征量来计算显著性图,基于钙化区域显著性进行粗钙化点分割;最终对分割后的粗钙化点进行形态学检测,达到对超声图像中的细钙化点自动检测。该方法取得了较好的分割效果,具有较强的鲁棒性,为形成具有普适性的肿瘤自动诊断方案奠定了研究基础。     

基于深度学习的颈动脉超声图像内中膜厚度测量

目的 颈动脉血管内中膜厚度(IMT)是衡量动脉粥样硬化程度的重要标准.一般采用人工标定进行测量,该过程耗时且繁琐,由此提出一种总体性能较好的全自动分割(AS)算法.方法 该算法首先利用卷积神经网络(CNN)识别出颈动脉血管远端,进而提取包含颈动脉内膜、中膜部分的感兴趣区域(ROI).采用基于堆栈式自编码器(SAE)构造的模式分类器将ROI中的像素进行分类.最后利用分类区域的面积信息和位置信息对分类结果进行甄别,运用曲线拟合提取边界完成测量任务.结果 针对本研究所用图像库中的84幅颈动脉超声图像进行实验,金标准(GT)由两名专家4次测量的平均值产生,其与AS之间的绝对误差和标准差为(13.3±20.5) μm,协方差系数为0.990 7.结论 实验结果表明,此算法总体性能较好,能够实现超声颈动脉血管内中膜全自动、快速、准确分割,从而满足临床需要.     

A fast inverse consistent deformable image registration method based on symmetric optical flow computation

Deformable image registration is widely used in various radiation therapy applications including daily treatment planning adaptation to map planned tissue or dose to changing anatomy. In this work, a simple and efficient inverse consistency deformable registration method is proposed with aims of higher registration accuracy and faster convergence speed. Instead of registering image I to a second image J, the two images are symmetrically deformed toward one another in multiple passes, until both deformed images are matched and correct registration is therefore achieved. In each pass, a delta motion field is computed by minimizing a symmetric optical flow system cost function using modified optical flow algorithms. The images are then further deformed with the delta motion field in the positive and negative directions respectively, and then used for the next pass. The magnitude of the delta motion field is forced to be less than 0.4 voxel for every pass in order to guarantee smoothness and invertibility for the two overall motion fields that are accumulating the delta motion fields in both positive and negative directions, respectively. The final motion fields to register the original images I and J, in either direction, are calculated by inverting one overall motion field and combining the inversion result with the other overall motion field. The final motion fields are inversely consistent and this is ensured by the symmetric way that registration is carried out. The proposed method is demonstrated with phantom images, artificially deformed patient images and 4D-CT images. Our results suggest that the proposed method is able to improve the overall accuracy (reducing registration error by 30% or more, compared to the original and inversely inconsistent optical flow algorithms), reduce the inverse consistency error (by 95% or more) and increase the convergence rate (by 100% or more). The overall computation speed may slightly decrease, or increase in most cases because the new method converges faster. Compared to previously reported inverse consistency algorithms, the proposed method is simpler, easier to implement and more efficient.     

基于双目红外相机定位的自由式三维超声图像重建系统

目的:设计并实现自由式三维超声图像重建系统,该系统能对自由式采集的二维超声图像阵列进行三维重建与显示交互。方法:系统使用双目红外相机及其配套测量器件,在超声探头上固定定位小球,双目红外相机可以实时追踪探头的空间位置,从而获取超声图像阵列的相对关系。软件部分根据实时探头位置并计算转换矩阵,获取超声图像阵列的数据并填充三维体数据网格,使用光线投射法绘制图像。结果:该系统可以实现超声图像阵列的采集与存储、超声图像感兴趣区域勾画、三维重建与可视化功能。结论:该研究提出的基于双目红外相机定位的自由式三维超声图像重建系统对未来的临床使用以及科学研究奠定了良好基础。     

Spectral image reconstruction for transcranial ultrasound measurement

An approach aimed at improved ultrasound resolution and signal strength through highly attenuating media is presented. The method delivers a series of multiple-cycle bursts in order to construct a discrete spectral (frequency domain) response in one dimension. Cross-correlation of this ultrasound A-mode response with its transmitted signal results in time-localized peaks that correspond to scattering locations. The approach is particularly relevant to the problem of transcranial ultrasound imaging, as it combines numerous smaller signals into a single signal whose net power may exceed that which could be achieved using a single burst. Tests are performed with human skull fragments and nylon-wire targets embedded in a tissue phantom. Skulls are oriented to produce both lateral and shear modes of transcranial propagation. A total of nine locations distributed over three ex vivo human skull samples are studied. Compared with pulsed and chirped signals, results indicate more localized peaks when using the multi-cycle approach, with more accurate positioning when combined with the transcranial shear mode.     

基于全变分模型的CT不完全角度重建算法研究进展

在计算机断层扫描成像领域,不完全角度重建算法可以在不完备的投影数据中重建出质量较好的图像,而其中比较突出的一类算法是基于全变分模型的重建算法。研究者们在此模型的基础上提出了许多相关的算法,重建出了质量更好的图像。本文首先简要介绍了全变分模型重建算法,然后在模型改进和求解算法两个方面对此模型的重建算法进行研究。在模型改进方面主要介绍了根据全变分模型的局限性以及图像的内涵信息引入相关的先验（方向信息、非局部信息、高阶梯度信息等）来改善图像的重建性能。在求解算法方面主要介绍了经典的梯度下降算法以及基于稀疏优化理论的交替方向最小化算法。最后分析总结了目前存在的问题以及提出模型改进和求解算法两方面相结合依旧是未来发展的趋势。     

基于边缘监督的肝部超声图像包膜分割网络

肝纤维化、肝硬化的早期发现对临床治疗和预后评估具有重要意义。而肝包膜的形态和纹理特征是计算机辅助肝硬化诊断的重要依据。本文提出一种基于边缘监督的肝部超声图像包膜分割网络。该网络以常用的分割模型UNet为基础，引入空洞卷积，扩大感受野；同时，添加了边缘监督模块，从而将特征学习主要聚焦在图像梯度较大的部分；此外，还设计了混合加权损失函数，来缓解肝包膜部分与其他区域之间的极度不平衡情况。实验结果表明，本文提出的ES-UNet网络结构平均Dice系数相比原始UNet提高了0.171 5，平均交并比（MIoU）提高了0.021 5，其他指标也有较明显的提高，可见，本文算法的各个组件对模型分割性能的优化都有一定的贡献，改进后的模型可以实现肝包膜的精确分割。     

医学超声图像分析的研究进展

超声成像是四大医学影像技术之一,由于其特有的实时性、无损性、廉价性被广泛应用于医疗和诊断,因此,有必要对医学超声图像的计算机分析进行研究。从图像分割、图像配准及组织定征和生物测量三个医学超声图像分析的主要方面对国内外近年来的主要研究情况进行综述和评价,并在此基础上探讨其发展前景。     

Proposal for an allele nomenclature system based on the evolutionary divergence of haplotypes

The classical view of what constitutes an "allele" has been challenged by recent findings of a great deal of human genetic variability, i.e., we can expect, on average, one variant site every 100-250 bases of our haploid genome. The haplotype is defined as "the patterns of co-occurrence of variant sites on the same chromosome" (and therefore within each particular gene). Sufficient evidence exists for the divergence of haplotypes during evolution of Homo sapiens sapiens, and the total number of haplotypes per gene will reflect the amount of time any particular ethnic group has existed on the planet, e.g., greatest in Africans, fewer in East Asians, and still fewer in Caucasians. If the average gene spans 30 kb, we can expect approximately 170 polymorphic variant sites per gene in the world population. We do not see 2(170) haplotypes, however; we might find only 10 to 200 haplotypes (depending on the gene's size and degree of conservation of the gene product). This finite number allows for a reasonable haplotype nomenclature system for each gene, based on evolutionary divergence. For polymorphic variants (i.e., frequency > or = 0.01), I propose using Arabic numerals for the major clades (e.g., *1, *2, em leader *20, *21), capital letters for sublineages (e.g., *2A, *2B, *2C), and Arabic numerals for sub-sublineages (e.g., *22G12, *22G13); additional subcategories may be added, in an alternating number/letter/number/letter sequence, depending on the complexity of present-day haplotypes of a particular gene. Web sites with a web master and external advisory committee should be set up for each gene superfamily, family, or individual gene (depending on complexity), and an international haplotype nomenclature committee, perhaps comprised of several dozen of these web masters, should oversee haplotype nomenclature for the entire human genome. The higher heterozygosity and multiallelic nature makes haplotypes more informative than biallelic SNPs. Ultimately, our knowledge of haplotype patterns, rather than single variant sites, of perhaps several hundred genes will likely be helpful in finding associations between genotype and any multiplex phenotype (e.g., complex diseases including cancer, and/or toxicity of pharmaceutical agents or environmental pollutants).     

A new prediction method for the total pollen counts of Cryptomeria japonica based on variation in annual summertime temperature]

In order to predict the total pollen counts of Cryptomeria japonica, we examined the difference of summertime temperature between the previous year and the year before the previous. Correlation coefficients of nine points throughout Japan exceeded more than r = 0.84 when compared the total pollen counts obtained from prediction and those from observation. The best correlation at four out of nine places was obtained with mean temperature of July, however, mean temperature of August or maximum temperature of August (or July) exceeded at some places. The differences, between observed values and predicted values are within 1000 grains/cm2 in 101 cases out of 135 cases (75%). Prediction errors at the year of bumper crop of male flower were less than 40% and the average is 17.5%. It is considered that our new method is useful enough for prediction, especially, the year of bumper crop of male flower.     

Higher order total variation regularization for EIT reconstruction

Electrical impedance tomography (EIT) attempts to reveal the conductivity distribution of a domain based on the electrical boundary condition. This is an ill-posed inverse problem; its solution is very unstable. Total variation (TV) regularization is one of the techniques commonly employed to stabilize reconstructions. However, it is well known that TV regularization induces staircase effects, which are not realistic in clinical applications. To reduce such artifacts, modified TV regularization terms considering a higher order differential operator were developed in several previous studies. One of them is called total generalized variation (TGV) regularization. TGV regularization has been successively applied in image processing in a regular grid context. In this study, we adapted TGV regularization to the finite element model (FEM) framework for EIT reconstruction. Reconstructions using simulation and clinical data were performed. First results indicate that, in comparison to TV regularization, TGV regularization promotes more realistic images.

Open image in new window

Graphical abstract Reconstructed conductivity changes located on selected vertical lines. For each of the reconstructed images as well as the ground truth image, conductivity changes located along the selected left and right vertical lines are plotted. In these plots, the notation GT in the legend stands for ground truth, TV stands for total variation method, and TGV stands for total generalized variation method. Reconstructed conductivity distributions from the GREIT algorithm are also demonstrated.