融合ResNet结构的U-Net眼底视盘分割方法

由于亮度的相似性,带病灶眼底图像的视盘分割通常会受到亮病灶干扰.现有的视盘分割方法对正常的视网膜眼底图像具有较好的分割效果,但是在带病灶的眼底图像中表现不佳.在医学图像数据样本有限的情况下,U-Net网络能实现少样本训练生成较好的分割结果.提出一种将残差结构与U-Net网络融合的视盘分割方法.残差模块的跳跃连接能将浅层...     

基于ITK和VTK的三维成像实现

介绍了Fast Marching快速行进图像分割和Marching Cubes步进立方体2种算法的原理,利用ITK的图像读取与处理功能及VTK在可视化方面的突出能力,将二者有机地集成起来,通过ITK和VTK实现这2种算法,最终生成三维立体医学图像。实验结果验证了该方法可以得到病理部位的详细特征,在医学图像三维成像方面有良好的性能。     

基于VTK三维可视化编程

介绍了VTK特点、体系结构、对象模型等,着重描述图形对象、可视化对象、流水线和图像处理。针对医学图像需要,使用VTK开发了一个小型医学三维可视化软件。实验结果表明,与使用OpenGL相比,使用VTK可以节约大量时间,开发出的软件更加标准和规范。     

基于正交矩的纹理分割

在识别一幅图像中的界面或物体时，一般先要进行纹理分割．本提出了基于勒让得矩的纹理分割方法．首先在图像的小窗口中计算矩值，然后用一个非线性转换器把它转化成纹理特征．再用这些特征组成特征向量作为输入数据．接着采用RBF人工神经网络对提取的特征进行分割．用k均值算法训练RBF人工神经网络的隐层．输出层的训练是采用基于LMS的监督式数学模型．该算法成功地分割了许多灰度级图像．和基于几何矩的纹理分割相比，用正交矩可以降低分割错误率．     

SVM for density estimation and application to medical image segmentation

A method of medical image segmentation based on support vector machine （SVM） for density estimation is presented. We used this estimator to construct a prior model of the image intensity and curvature profile of the structure from training images. When segmenting a novel image similar to the training images, the technique of narrow level set method is used. The higher dimensional surface evolution metric is defined by the prior model instead of by energy minimization function. This method offers several advantages. First, SVM for density estimation is consistent and its solution is sparse. Second, compared to the traditional level set methods, this method incorporates shape information on the object to be segmented into the segmentation process. Segmentation results are demonstrated on synthetic images, MR images and ultrasonic images.     

模态命题逻辑系统K、D、T、S4、S5、B之比较

模态命题逻辑系统K、D、T、S4、S5、B所依据的公理有一定的差异,导致它们之间的定理有一定的差异,推理能力的大小也有所不同.由于定理集的不同导致S4、S5可进行叠置模态词的归约,而K、D、T、B不能;S5可进行嵌套模态词的归约,K、D、T、S4、B没有这种归约能力.     

Graphic processing unit-accelerated mutual information-based 3D image rigid registration

Mutual information (MI)-based image registration is effective in registering medical images, but it is computationally expensive. This paper accelerates MI-based image registration by dividing computation of mutual information into spatial transformation and histogram-based calculation, and performing 3D spatial transformation and trilinear interpolation on graphic processing unit (GPU). The 3D floating image is downloaded to GPU as flat 3D texture, and then fetched and interpolated for each new voxel location in fragment shader. The transformed results are rendered to textures by using frame buffer object (FBO) extension, and then read to the main memory used for the remaining computation on CPU. Experimental results show that GPU-accelerated method can achieve speedup about an order of magnitude with better registration result compared with the software implementation on a single-core CPU.     

树映射的稠密混沌

设T是树,f:T→T是连续映射.在本文我们显示下列性质等价:(1)f是通用混沌,(2)对某个δ＞0,f是通用δ-混沌,(3)对某个δ＞0,f是稠密δ-混沌,(4)或者存在唯一的传递的非退化的连通闭集,或者存在k(k≥2)个有公共端站的传递的非退化的连通闭集;且如果J是非退化的连通集合,则f(J)是非退化的,且存在传递的连通集合I0和整数n使得fn(J)∩Int(I0)≠0.     

一种小波域K-Means遥感图像分类标注算法

由于合成孔径雷达图像（遥感）的相干斑噪声数据丰富,导致传统的遥感图像分割方法分割效果不佳,采用学习理论和神经网络改善图像处理性能。根据图像统计特征,采取神经网络语义提出一种高效的图像纹理特征分割方法。首先,利用K-means聚类提取遥感图像的纹理特征,然后根据遥感图像在小波域中的分布特征对其进行滤波,最后利用语义对滤波后的遥感图像纹理特征和灰度组成的矢量进行分割归类,在遥感图像分割中快速标注分类以便于视觉分析。利用区域一致性分割分类,由聚类样本特征匹配进行图像分类标注,对变化检测进行统计分析,过分割或欠分割误差聚类样本不做标注,选取最佳样本聚类k值标注分类结果。     

A new algorithm of brain volume contours segmentation

This paper explores brain CT slices segmentation technique and some related problems, including contours segmentation algorithms, edge detector, algorithm evaluation and experimental results. This article describes a method for contour-based segmentation of anatomical structures in 3D medical data sets. With this method, the user manually traces one or more 2D contours of an anatomical structure of interest on parallel planes arbitrarily cutting the data set. The experimental results showed the segmentation based on 3D brain volume and 2D CT slices. The main creative contributions in this paper are: (1) contours segmentation algorithm; (2) edge detector; (3) algorithm evaluation. Project (No.69931010) supported by the National Natural Science Foundation of China     

基于改进UNet的人造板表面缺陷的图像分割方法

为满足人造板表面缺陷图像分割的精度要求,提出了一种改进的UNet语义分割网络模型。在传统的UNet网络结构上将编码部分改进为残差网络ResNet50并去掉连接层与平均池化层,网络通过残差块堆叠获取更多特征的底层信息;同时在跳跃连接中嵌入聚焦注意力机制的模块,抑制干扰信息,保留有效位置信息,聚焦缺陷区域并加强学习。对4种UNet网络模型的人造板表面缺陷图像分割进行仿真比较,结果表明,融合聚焦注意力机制的残差UNet网络模型在像素准确率和平均交并比等指标上有较大提升,分割精度较高。     

A new algorithm of brain volume contours segmentation

INTRODUCTIONSegmentation ,acentralissueofcomputervision ,isafundamentalprocessingstepinmostsystemsthatsupportmedicaldiagnosisorplan ningofsurgicaloperationsandradiationtreat ments (Wyattetal.,2 0 0 0 ;Wintereretal.,2 0 0 2 ;Baoetal.,1998) .Contour basedse…     

图像分割技术在医学图像分割中的应用

图像分割是图像分析和处理的关键步骤,医学图像分割是图像分割的一个重要应用领域。本文讨论了医学图像分割的目的和意义,对医学图像分割的常用技术进行了研究。     

Take away body parts! An investigation into the use of 3D‐printed anatomical models in undergraduate anatomy education

Understanding the three‐dimensional (3D) nature of the human form is imperative for effective medical practice and the emergence of 3D printing creates numerous opportunities to enhance aspects of medical and healthcare training. A recently deceased, un‐embalmed donor was scanned through high‐resolution computed tomography. The scan data underwent segmentation and post‐processing and a range of 3D‐printed anatomical models were produced. A four‐stage mixed‐methods study was conducted to evaluate the educational value of the models in a medical program. (1) A quantitative pre/post‐test to assess change in learner knowledge following 3D‐printed model usage in a small group tutorial; (2) student focus group (3) a qualitative student questionnaire regarding personal student model usage (4) teaching faculty evaluation. The use of 3D‐printed models in small‐group anatomy teaching session resulted in a significant increase in knowledge (P = 0.0001) when compared to didactic 2D‐image based teaching methods. Student focus groups yielded six key themes regarding the use of 3D‐printed anatomical models: model properties, teaching integration, resource integration, assessment, clinical imaging, and pathology and anatomical variation. Questionnaires detailed how students used the models in the home environment and integrated them with anatomical learning resources such as textbooks and anatomy lectures. In conclusion, 3D‐printed anatomical models can be successfully produced from the CT data set of a recently deceased donor. These models can be used in anatomy education as a teaching tool in their own right, as well as a method for augmenting the curriculum and complementing established learning modalities, such as dissection‐based teaching. Anat Sci Educ 11: 44–53. © 2017 American Association of Anatomists.     

基于并行粒子群算法的Otsu双阈值医学图像分割

医学图像分割一直是医学影像分析领域的研究热点。由于粒子群优化(PSO)容易陷入局部极小,因此该算法用于搜索某些函数极值时精确度较低且稳定性较差。针对该问题,结合Otsu分割技术,提出了一种基于并行粒子群优化算法的Otsu双阈值医学图像分割算法。在该算法中,将粒子群体分成若干个子群体,进化在多个不同的子群中并行进行,避免单种群进化过程中出现的过早收敛现象,提高整个算法的收敛速度。实验结果表明,提出的分割算法与传统粒子群算法相比,不仅能够对图像进行准确的分割,而且具有更强的精确性和稳定性,其收敛速度明显优于基于单种群的粒子群算法的Otsu双阈值医学图像分割。     

蜂窝网络覆盖下的D2D通信研究

随着物联网与大数据时代的到来,频谱资源日益紧缺。为缓解频谱资源紧张,提高频谱资源利用率,将D2D通信技术引入蜂窝网络,同时与NONA、EH、Relay等技术结合,通过合理的资源分配与功率控制,改善蜂窝通信网络服务性能,降低通信时延,提高频谱资源利用率。与传统蜂窝通信网络比,D2D通信技术加入蜂窝网络可扩大蜂窝网络覆盖范围,提高边缘用户吞吐量与蜂窝用户和D2D用户的吞吐量,具有广阔的应用前景。     

3D Reconstruction technique for tomographic PIV

Tomographic particle image velocimetry(Tomo-PIV) is a state-of-the-art experimental technique based on a method of optical tomography to achieve the three-dimensional(3D) reconstruction for threedimensional three-component(3D-3C) flow velocity measurements. 3D reconstruction for Tomo-PIV is carried out herein. Meanwhile, a 3D simplified tomographic reconstruction model reduced from a 3D volume light intensity field with 2D projection images into a 2D Tomo-slice plane with 1D projecting lines, i.e., simplifying this 3D reconstruction into a problem of 2D Tomo-slice plane reconstruction, is applied thereafter. Two kinds of the most well-known algebraic reconstruction techniques, algebraic reconstruction technique(ART) and multiple algebraic reconstruction technique(MART), are compared as well. The principles of the two reconstruction algorithms are discussed in detail, which has been performed by a series of simulation images, yielding the corresponding reconstruction images that show different features between the ART and MART algorithm, and then their advantages and disadvantages are discussed. Further discussions are made for the standard particle image reconstruction when the background noise of the pre-initial particle image has been removed. Results show that the particle image reconstruction has been greatly improved. The MART algorithm is much better than the ART. Furthermore, the computational analyses of two parameters(the particle density and the number of cameras), are performed to study their effects on the reconstruction. Lastly, the 3D volume particle field is reconstructed by using the improved algorithm based on the simplified 3D tomographic reconstruction model, which proves that the algorithm simplification is feasible and it can be applied to the reconstruction of 3D volume particle field in a Tomo-PIV system.     

基于深度学习的杂草识别系统

田间除草技术在农业生产中具有重要意义。针对复杂背景下农作物与杂草识别率低、算法鲁棒性差等问题,提出一种图像分割网络 Res-Unet。该网络为 unet 网络的改进版本,采用 resnet50 网络代替 unet 主干网络,解决复杂背景下农作物与杂草区域提取困难、小植株检测效果差、分割边缘震荡、变形问题。将图像的平均交并比、准确率、训练时长作为评价指标进行实验。结果表明：使用 Res-Unet 模型的平均交并比为 82.25%,平均像素准确率为 98.67%。改进的 Res-Unet 模型相对于 Unet 平均交并比高出 4.74%,相较于 segnet 平均交并比高出 10.68%,训练时间减少 3 小时。该方法对复杂背景下甜菜杂草检测效果良好,可为机器人精确除草提供参考。     

基于计算机的三维医学图像处理方法——图像分割技术

图像分割技术就是把图像中具有特殊涵义（如医学图像中的病变部位）的不同区域分开来,使每一个区域都满足特定区域的一致性的图像处理技术。基于当前医学图像分割方法研究,分割的速度和稳定性无法同时提高的问题,引入一种被称为“live-wire”的半自动的交互式范例,并对其在三雏空间上的实现建立了理论模型;同时自定义了与本文模型相关的MATLAB实现函数。     

远程临床医学技能培训的实现

目前医学教育中的临床技能培养存在要求高、难度大、实践机会少等问题。虚拟现实、视音频、多媒体及计算机网络等技术的发展,为临床医学技能培养提供了一条新的途径。基于新疆生产建设兵团医疗现状和发展规划构建的远程医学临床技能培训平台,就远程教育与医学教育的结合进行探索,依托优质医学资源,利用卫星网络、互联网络和VPN专网以及现代信息技术,实现远程医学教育、协同诊断、手术观摩、三维虚拟手术实验等功能,缩短了医学院学生、各类医务人员从理论学习到临床具体操作的时间,提升了整体的临床技能综合水平。