运动模糊图象中运动方向的自动检测算法

匀速直线运动模糊图象中运动方向的检测是图象恢复过程的重要步骤之一。对运动模糊图象实施方向微分 ,根据方向微分图像灰度值 (绝对值 )分布的特点 ,首先给出了计算任意角度的方向微分的公式 ,然后将微分图象灰度值 (绝对值 )通过灰度线性变换 ,求取和值中的极大值来自动且有效地识别出运动方向 ,并通过实验验证     

基于形态学重构运算的医学CT图像滤波方法

提出一种基于数学形态学开-闭重构的医学CT图像滤波方法。该方法合理选取不同尺度的结构元素和标记图像,利用数学形态学开-闭重构运算对图像进行滤波,解决了传统滤波方法处理医学CT图像时滤波效果差及模糊图像边缘信息的问题。仿真结果表明该方法在复杂噪声情况下能够有效滤除噪声并且边缘保持效果较好。     

基于边缘形态变换的彩色织物图像分割算法

新疆民间织物图像具有鲜明的民族特色,为了生成和创新民族民间织物图像,如何自动分割织物基元是一个关键问题.论文以问题为驱动,提出了一种基于边缘形态变换的彩色织物图像分割算法.首先,对彩色图像进行颜色空间的变换,然后根据图像特征提出调整图像大小的前处理标准,再利用Canny算子检测边缘,对检测边缘进行形态变换后处理,最后标...     

基于邻域信息的图像模糊映射及其应用

模糊映射是图像模糊处理的基础,目前主要是基于图像象素值的映射,没有充分利用图像的邻域相关信息。本文提出基于邻域信息的模糊映射思想,解决较复杂图像的模糊处理问题。文中给出该方法在边缘检测、区域分割中的应用实例,均取得令人满意的结果。     

灰度图像序列中基于二次帧差的分割算法

视频对象的分割在基于内容的视频编码及视频检索中占有重要的地位。在快速准确的原则上,利用视频序列中的时域及空域信息,提出了一种分割运动对象的仿真方法。首先利用二次帧差求交集的方法求出图像帧的运动区域,然后利用形态梯度算子得到图像帧的边缘信息,最后时空结合并填充就可以分割出运动对象。实验证明分割效果较好并节省了处理时间。     

基于模糊连接度的FCM分割方法在医学图像分析中的应用

图像分割的一个重要应用领域是医学图像的分割.我们针对医学图像的模糊特点和实际应用的要求,结合模糊连接度阈值分割和模糊C均值聚类两种分割方法的优点,提出一种新的交互式医学图像分割方法.首先计算整幅图像的模糊连接度,通过闽值分割提取出感兴趣的对象,并将模糊连接度作为图像的冗余特征;然后在由冗余特征和原图像特征构成的二维聚类空间中,利用模糊C-均值聚类方法优化上一步骤的分割结果,提高分割准确度.我们以CT和MR图像为实验对象进行了验证,实验结果表明这是一个有效的方法.     

基于点云辐射场的新视角图像生成网络

新视角图像生成是指使用同一场景、多个位置和角度拍摄的一组图像，生成新颖视角位置处的场景图像，在真实拍摄的城市建筑场景图像中存在移动的瞬态对象，对静态建筑造成遮挡，导致生成的新视角图像模糊、存在伪影甚至建筑物生成错误。针对于此，本文提出了一种基于点云辐射场的新视角图像生成方法。首先，通过瞬态对象过滤模块得到静态建筑图像；然后，分别经过2D CNN和3D CNN网络获取图像特征和图像点云信息，二者结合构建神经点云；最后，输入多层感知机网络获取场景采样点位置的体积密度和颜色信息，并指导体渲染模块生成新视角位置的图像。在Photo Tourism数据集与最新的几种方法进行比较，实验结果和可视化结果表明，所提方法在数据集上有较好的效果表现，有效地解决了生成图像中存在伪影和建筑物生成错误的问题。     

Photoshop图像处理软件在放疗中射野验证的应用探讨

目的 探讨利用Adobe公司Photoshop图像处理软件验证放疗位置的临床价值.方法 利用扫描仪将加速器拍摄的验证片、定位片或数字重建图像输入计算机中,调整图像大小、灰度、对比度后进行图像配准与测量.结果 通过射野验证图像与参考图像的对比发现,在左右方向、上下方向和前后方向头颈部摆位误差分别为(1.11±1.37)、(1.33±1.25)、(0.83±0.79)mm,胸部的分别为(1.44±1.03)、(1.6±1.52)、(1.34±1.17)mm;腹部的分别为(1.53±0.86)、(1.83±1.19)、(1.67±0.68)mm,盆腔部的分别为(1.93±1.83)、(1.59±1.07)、(0.85±0.72)mm.结论 利用Adobe公司Photoshop图像处理软件可以进行射野和摆位位置的准确测量且操作简单、安全可靠.     

基于双边滤波的POCS超分辨率图像序列重建算法

针对传统凸集投影(POCS)超分辨率图像序列重建算法使用高斯滤波器来估计点扩散函数(PSF)导致边缘模糊的现象,本文采用双边滤波器来估计PSF,双边滤波方法是将高斯函数和图像亮度信息相乘,优化后的权系数再与图像作卷积,使重建后的图像边缘得到很好保持。运动估计是POCS超分辨率图像序列重建算法的关键技术,本文选择结合图像金字塔的光流估计对图像序列进行配准,得到更加精确的估计结果。实验表明,可以使重建图像取得良好的视觉效果。     

基于三维投影的视频序列静态全景合成算法

视频序列静态全景合成技术是视频图像分析的关键技术。本文提出了一种基于三维投影的视频序列静态全景合成算法,该算法通过引入三维投影原理,将视频序列中各帧图像依次投影到全景图像平面,推导出在同一三维坐标下各帧图像与全景图像之间的变换关系,并采用各帧图像间的运动参数联合生成全景图像。实验结果表明,该方法能够生成较高质量的全景图。     

一种基于小波变换的图像复原方法

本文描述了一个基于小波的图像复原方法,该方法首先将图像和运算用小波表示,得到退化模型的多分辨率稀疏矩阵表示法,使用该法我们得到一个多级正则化图像复原算法,并可有效地进行平滑约束。最后,我们对所提算法进行了验证,取得了较好的结果。     

Resolution improvement in positron emission tomography using anatomical Magnetic Resonance Imaging

An ideal imaging system should provide information with high-sensitivity, high spatial, and temporal resolution. Unfortunately, it is not possible to satisfy all of these desired features in a single modality. In this paper, we discuss methods to improve the spatial resolution in positron emission imaging (PET) using a priori information from Magnetic Resonance Imaging (MRI). Our approach uses an image restoration algorithm based on the maximization of mutual information (MMI), which has found significant success for optimizing multimodal image registration. The MMI criterion is used to estimate the parameters in the Sharpness-Constrained Wiener filter. The generated filter is then applied to restore PET images of a realistic digital brain phantom. The resulting restored images show improved resolution and better signal-to-noise ratio compared to the interpolated PET images. We conclude that a Sharpness-Constrained Wiener filter having parameters optimized from a MMI criterion may be useful for restoring spatial resolution in PET based on a priori information from correlated MRI.     

Photoshop简易定位法切除颅内浅表小病灶(附18例报告)

背景与目的:颅内小病灶手术的关键在于术中的精确定位。本研究主要总结和分析Photoshop简易定位法切除颅内占位病灶的经验。方法:应用Photoshop简易定位法确定肿瘤的位置,经影像资料再次比较定位标记物与肿瘤的实际位置的关系,确定手术切口,切除颅内病灶。其中脑脓肿1例,脑转移瘤2例,脑膜瘤15例。结果:标记物与肿瘤误差为0.8~1.0cm,经验证后重新确定肿瘤中心,术中验证其误差为0.2~0.5cm,均于显微镜下行全切术,术后患者均康复出院。结论:Photoshop简易定位法手术治疗颅内位置表浅小病灶准确、安全。     

一种新的基于彩色双边滤波的彩色图像增强方法

本文提出一种新的基于彩色双边滤波的彩色图像增强方法。该方法将彩色图像增强分为三部分：全局亮度调节、对比度增强和颜色恢复。全局亮度调节主要是对图像的整体亮度信息进行非线性调整,压缩图像的亮度动态范围 局部对比度增强主要是利用彩色双边滤波获得像素点所在邻域的背景亮度,由当前像素点的亮度与背景亮度之间的关系,通过非线性的方法增强图像局部对比度 最后通过颜色恢复算法恢复图像色彩。相关实验表明,本文所提方法可以获得很好的彩色图像增强效果。     

Improving soft-tissue contrast in four-dimensional computed tomography images of liver cancer patients using a deformable image registration method

PURPOSE: To investigate a deformable image registration method to improve soft-tissue contrast in four-dimensional (4D) computed tomography (CT) images of the liver. METHODS AND MATERIALS: Ten patients with hepatocellular carcinoma underwent 4D CT scan for radiotherapy treatment planning on a positron emission tomography/CT scanner. Four-dimensional CT images were binned into 10 equispaced phases. The exhale phase served as the reference phase, and images from the other nine phases were coregistered to the reference phase image using an intensity-based, automatic deformable image registration method. Then the coregistered images were combined to create a single, high-quality reconstructed CT image at exhale phase as the new reference for target delineation. The extent of image quality enhancement was quantified relative to the original CT by calculating the signal-to-noise ratio and the contrast-to-noise ratio. RESULTS: The soft tissue image contrast was noticeably better after deformable image registration than in the original scans. Signal-to-noise ratios inside the liver region of interest increased for all patients by a factor of 3.0 (range, 2.3-3.7). The improvement in image quality was not linearly proportionate to the number of images averaged. Using only 6 phases can achieve at least 85% of the contrast enhancement that can be achieved using all 10 phases. We also found that contrast enhancement was inversely proportional to the original image quality (p = 0.006), and the contrast enhancement is attained with little loss of spatial resolution. CONCLUSIONS: This deformable image registration method is feasible to improve soft-tissue image quality in 4D CT images.     

Incorporation of local dependent reliability information into the Prior Image Constrained Compressed Sensing (PICCS) reconstruction algorithm

PurposeThe reduction of dose in cone beam computer tomography (CBCT) arises from the decrease of the tube current for each projection as well as from the reduction of the number of projections. In order to maintain good image quality, sophisticated image reconstruction techniques are required. The Prior Image Constrained Compressed Sensing (PICCS) incorporates prior images into the reconstruction algorithm and outperforms the widespread used Feldkamp-Davis-Kress-algorithm (FDK) when the number of projections is reduced. However, prior images that contain major variations are not appropriately considered so far in PICCS. We therefore propose the partial-PICCS (pPICCS) algorithm. This framework is a problem-specific extension of PICCS and enables the incorporation of the reliability of the prior images additionally.Material and MethodsWe assumed that the prior images are composed of areas with large and small deviations. Accordingly, a weighting matrix considered the assigned areas in the objective function. We applied our algorithm to the problem of image reconstruction from few views by simulations with a computer phantom as well as on clinical CBCT projections from a head-and-neck case. All prior images contained large local variations. The reconstructed images were compared to the reconstruction results by the FDK-algorithm, by Compressed Sensing (CS) and by PICCS. To show the gain of image quality we compared image details with the reference image and used quantitative metrics (root-mean-square error (RMSE), contrast-to-noise-ratio (CNR)).ResultsThe pPICCS reconstruction framework yield images with substantially improved quality even when the number of projections was very small. The images contained less streaking, blurring and inaccurately reconstructed structures compared to the images reconstructed by FDK, CS and conventional PICCS. The increased image quality is also reflected in large RMSE differences.ConclusionsWe proposed a modification of the original PICCS algorithm. The pPICCS algorithm incorporates prior images as well as information about location dependent uncertainties of the prior images into the algorithm. The computer phantom and experimental data studies indicate the potential to lowering the radiation dose to the patient due to imaging while maintaining good image quality.     

ABAS软件勾画OAR临床前测试重要性研究

目的 对基于模板自动分区(ABAS)算法的图像勾画软件进行临床前测试,评估鼻咽癌放疗计划OAR勾画精度,为确定临床应用条件提供依据。方法 以放疗医师在22例鼻咽癌患者放疗计划CT图像上手工勾画的OAR结构为评价标准,分别对ABAS软件两种算法(General和Head/Neck)自动勾画的OAR进行以下测试:(1)每1例患者均拷贝1套图像,以原图像上手工勾画的轮廓为模板在拷贝图像上自动勾画,考察自动勾画对模板的还原能力;(2)以1例患者图像上手工勾画的轮廓为模板,对其余患者图像进行自动勾画,考察采用单一模板对不同患者图像自动勾画的准确度。评价指标包括各OAR的DSC、V_diff、DSC与勾画体积相关性,以及自动勾画加手工修改与单纯手工勾画的耗时差别。Wilcoxon符号秩检验,Spearman相关性分析。结果 Head/Neck算法对模板还原能力优于或相当于General算法,自动勾画DSC与所勾画结构体积大小呈正相关(r_s=0.879、0.939)。还原测试中体积>1 cm³器官自动勾画的DSC>0.8。使用Head/Neck算法基于单一模板的自动勾画中,脑干、颞叶、腮腺、下颌骨的DSC和V_diff平均值分别为0.81~0.90和2.73%~16.02%,颞颌关节和视交叉DSC为0.45~0.49。应用自动勾画加手工修改比单纯手工勾画可以节省68%时间。结论 临床前测试可以确定ABAS算法在特定临床应用条件的准确度和适用范围,所测试软件可帮助提高鼻咽癌放疗计划OAR勾画效率,但不适用于较小体积器官的勾画。     

The role of high-energy imaging in a radiotherapy service and its incorporation in a network]

To directly compare the clinical efficacy of electronic to film portal images and the advantages of comparing directly on the monitor the simulation image and the portal image. MATERIAL AND METHODS: This study was designed to compare clinical efficacy of electronic to film portal images acquired using a liquid matrix ion-chamber electronic portal imaging device (EPID) and a conventional film system. Two radiation oncologists served as observers and evaluated a total of 30 sets of images for three different treatment sites: lung, pelvis, and head/neck. Each set of images included a simulation image, a portal film, a video paper print of electronic portal images, and a video prints of electronic portal images. Four to six anatomical landmarks were selected from each treatment site. Each observer was asked to rate each landmark in terms of its clinical visibility and to rate the ease of making the pertinent verification decision in the corresponding electronic and film portal images with the aid of the simulation image. The time needed to obtain and analyse a conventional portal image and an EPID would be analysed for the radiotherapist and the medical technicians. RESULTS: Ratings for the visibility of landmarks and for the verification decision of treatment ports were similar for electronic and film images for most landmarks. However, vertebral bodies and several landmarks in the pelvis such as the acetabulum and pubic symphysis were more visible in the electronic portal images than in the portal film images. For the medical technicians, the EPID is more comfortable, and they do not need to develop any images. CONCLUSION: The visibility of landmarks in electronic portal images is comparable to that in film portal images. Verification of treatment ports based only on electronic portal images acquired using an electronic portal imaging device is generally achievable. Thus the integration of the EPID and simulation image in a network provides more flexibility in the daily work of a medical radiotherapy team.