Iron Oxide‐Labeled Collagen Scaffolds for Non‐Invasive MR Imaging in Tissue Engineering

Non‐invasive imaging holds significant potential for implementation in tissue engineering. It can be used to monitor the localization and function of tissue‐engineered implants, as well as their resorption and remodelling. Thus far, however, the vast majority of effort in this area of research have focused on the use of ultrasmall super‐paramagnetic iron oxide (USPIO) nanoparticle‐labeled cells, colonizing the scaffolds, to indirectly image the implant material. Reasoning that directly labeling scaffold materials might be more beneficial (enabling imaging also in the case of non‐cellularized implants), more informative (enabling the non‐invasive visualization and quantification of scaffold degradation), and easier to translate into the clinic (cell‐free materials are less complex from a regulatory point‐of‐view), three different types of USPIO nanoparticles are prepared and incorporated both passively and actively (via chemical conjugation; during collagen crosslinking) into collagen‐based scaffold materials. The amount of USPIO incorporated into the scaffolds is optimized, and correlated with MR signal intensity, showing that the labeled scaffolds are highly biocompatible, and that scaffold degradation can be visualized using MRI. This provides an initial proof‐of‐principle for the in vivo visualization of the scaffolds. Consequently, USPIO‐labeled scaffold materials seem to be highly suitable for image‐guided tissue engineering applications.     

基于光谱注意力图卷积网络的高光谱图像分类

近年来,图卷积网络因其特征聚合的机制,能够同时对单个节点以及近邻节点的特征进行表示,被广泛应用于高光谱图像的分类任务。然而,高光谱图像(HSI)中常存在波段冗余、同物异谱等问题,使得直接利用原始光谱特征构建的初始图可靠性不足,从而导致高光谱图像的分类精度低。为此,该文提出一种基于光谱注意力图卷积网络(SAGCN)的高光谱图像半监督分类方法。首先,利用注意力模块对光谱的局部与全局信息进行交互,以增加重要光谱的权重、减小冗余波段以及噪声波段的权重,从而实现光谱的自适应加权;然后,针对光谱加权处理后的高光谱图像,通过空间-光谱相似性度量构建更为准确的近邻矩阵;最后,通过图卷积对标记和无标记样本进行有效的特征聚合,并使用标记样本的聚合特征训练网络。在Indian Pines, Kennedy Space Center和Botswana 3个真实高光谱图像数据集上的实验结果验证了所提方法的有效性。     

Web and personal image annotation by mining label correlation with relaxed visual graph embedding

The number of digital images rapidly increases, and it becomes an important challenge to organize these resources effectively. As a way to facilitate image categorization and retrieval, automatic image annotation has received much research attention. Considering that there are a great number of unlabeled images available, it is beneficial to develop an effective mechanism to leverage unlabeled images for large-scale image annotation. Meanwhile, a single image is usually associated with multiple labels, which are inherently correlated to each other. A straightforward method of image annotation is to decompose the problem into multiple independent single-label problems, but this ignores the underlying correlations among different labels. In this paper, we propose a new inductive algorithm for image annotation by integrating label correlation mining and visual similarity mining into a joint framework. We first construct a graph model according to image visual features. A multilabel classifier is then trained by simultaneously uncovering the shared structure common to different labels and the visual graph embedded label prediction matrix for image annotation. We show that the globally optimal solution of the proposed framework can be obtained by performing generalized eigen-decomposition. We apply the proposed framework to both web image annotation and personal album labeling using the NUS-WIDE, MSRA MM 2.0, and Kodak image data sets, and the AUC evaluation metric. Extensive experiments on large-scale image databases collected from the web and personal album show that the proposed algorithm is capable of utilizing both labeled and unlabeled data for image annotation and outperforms other algorithms.     

一种改进的图谱阈值分割算法

针对图像分割是典型的结构不良问题,将图谱划分理论作为一种新型的模式分析工具应用到图像分割并引起广大学者关注。考虑到现有的图谱阈值法中图权计算方法采用基于欧氏距离的幂指数函数导致其计算量过大的不足,首先采用基于欧氏距离的分式型柯西函数代替基于欧氏距离的幂指数函数提出图权计算的新方法,其次将其应用基于图谱划分测度的图像阈值分割算法中并得到一种改进的图谱阈值分割方法。实验结果表明,该方法的计算量小且对目标和背景相差比例较大的图像能获得满意的结果。     

基于邻域最小生成树的半监督极化SAR图像分类方法

该文针对极化SAR图像分类中只有少量标记样本的问题,提出了一种基于邻域最小生成树的半监督极化SAR图像分类方法。该方法针对极化SAR图像以像素为分类对象的特点,结合自训练方法的思想,利用极化SAR图像像素点的空间信息,提出了基于邻域最小生成树辅助学习的样本选择策略,增加自训练过程中被选择无标记样本的可靠性,扩充标记样本数量,训练更好的分类器。最终用训练好的分类器对极化SAR图像进行测试。对3组真实的极化SAR图像进行测试,实验结果表明,该方法在只有少量标记样本的情况下能获得满意的分类结果,且分类正确率明显优于传统的分类算法。      

Adaptive image coding using spectral classification

We present a new classification scheme, dubbed spectral classification, which uses the spectral characteristics of the image blocks to classify them into one of a finite number of classes. A vector quantizer with an appropriate distortion measure is designed to perform the classification operation. The application of the proposed spectral classification scheme is then demonstrated in the context of adaptive image coding. It is shown that the spectral classifier outperforms gain-based classifiers while requiring a lower computational complexity.     

基于分等级对象语义图模型的复杂目标自动识别方法研究

目标自动识别是图像处理领域的研究热点。针对现有方法的不足,该文提出一种新的基于分等级对象语义图模型的复杂目标自动识别方法。该方法通过构建分等级对象语义图模型增强对目标与背景间、目标部件间语义约束的利用,引入置信对象网络统计局部特性,利用消息机制传递对象间相互影响,实现概率语义分析。训练中还将产生式和判别式方法结合,提高了目标识别的准确度。在自然和遥感部分目标类别数据集上的测试结果表明,该方法能完成对多种类型和复杂结构目标的识别和提取,具有一定的实用价值。     

Support vector machine active learning by Hessian regularization

It is time-consuming and expensive to gather and label the growing multimedia data that is easily accessible with the prodigious development of Internet technology and digital sensors. Hence, it is essential to develop a technique that can efficiently be utilized for the large-scale multimedia data especially when labeled data is rare. Active learning is showing to be one useful approach that greedily chooses queries from unlabeled data to be labeled for further learning and then minimizes the estimated expected learning error. However, most active learning methods only take into account the labeled data in the training of the classifier. In this paper, we introduce a semi-supervised algorithm to learn the classifier and then perform active learning scheme on top of the semi-supervised scheme. Particularly, we employ Hessian regularization into support vector machine to boost the classifier. Hessian regularization exploits the potential geometry structure of data space (including labeled and unlabeled data) and then significantly leverages the performance in each round. To evaluate the proposed algorithm, we carefully conduct extensive experiments including image segmentation and human activity recognition on popular datasets respectively. The experimental results demonstrate that our method can achieve a better performance than the traditional active learning methods.     

Image registration

In order to demonstrate the growth of the medical image registration field over the past decades, this paper presents the number of journal publications on this topic since 1988 until 2002. In a similar manner, trends in topics within the field of medical image registration are detected. Publications on computed tomography (CT) and magnetic resonance imaging (MRI) are rather constant through the years. Positron emission tomography (PET) and single photon emission computed tomography (SPECT), on the other hand, seem to loose ground to newly emerging functional imaging techniques, such as functional MRI (fMRI) whereas an increase in interest in registration of ultrasound (US) images was observed. Two topics in image registration that are currently considered hot are intraoperative and elastic registration. Although the interest in intraoperative registration strongly increased in the late 1990s, there seems to be a slight relative decrease in recent years. On the other hand, elastic registration has become a popular topic, reaching the highest numbers so far in 2002.     

Knowledge-based segmentation of Landsat images

A knowledge-based approach for Landsat image segmentation is proposed. The image segmentation problem is solved by extracting kernel information from the input image to provide an initial interpretation of the image and by using a knowledge-based hierarchical classifier to discriminate between major land-cover types in the study area. The proposed method is designed in such a way that a Landsat image can be segmented and interpreted without any prior image-dependent information. The general spectral land-cover knowledge is constructed from the training land-cover data, and the road information of an image is obtained through a road-detection program     

基于局部平滑加权图割方法的SAR图像分割

针对合成孔径雷达(SAR)图像分割,提出了一种 局部平滑加权图割(LSWGC,local smoothing weighted graph cut)模型。首先,在加权图割(WGCut)的目标函数中加入局部平滑罚项,提高了基于谱 聚类的SAR 图像分割方法对斑点噪声的稳健性,抑制了SAR图像分割中孤立点的产生;其次,利用WGCut 与加权核 K均值(WKKM)的等价性,LSWGC以不同于参数核 图割(PKGC)方法的核化方式将核映射引入目标函数中,用图 割最优化算法求解标号函数,避免了基于谱聚类的SAR图像分割方法中图谱的求解问题,同 时改善了PKGC方法二类划分易丢失目标的不足。模拟和真实SAR图像的实验结果证实 了本文方案的有效性。     

Imaging the distribution of magnetic nanoparticles with ultrasound

Magnetic nanoparticles can be caused to oscillate under the influence of an incident ultrasonic wave. If the particles are momentarily aligned with a magnetizing pulse creating a macroscopic magnetization, this oscillation will result in a time-varying magnetic moment which should be detectable as an induced voltage in a nearby pickup coil. In this way, focused ultrasound can be used to map, or image, the spatial distribution of the magnetic particles after these particles have been introduced into the body. The magnetic particles could be antibody-labeled to target tumor cells or used as a cardiovascular contrast agent, among other applications. The magnitude of the induced signal is estimated for one micron particles with a Fe/tissue volume fraction of 10(-6), which is about the limit of detectability for MRI superparamagnetic contrast agents consisting of single domain iron-oxide particles. One advantage of this method compared to conventional MRI is potentially greater sensitivity due to the absence of a large background signal.     

原位心脏移植心内膜活检组织的电镜观察及排异监测

心脏移植在我国起步较晚，近年只有少数几家医院实施了这种手术，但术后长期存活病人不多，其中多死于排异反应。同种异体心脏移植早期，急性排异较为多见，是移植器官不能长期存活的主要原因之一。     

一种改进的图割目标分割算法

为了减少图像目标在分割过程中受到噪声、复杂背景等因素的影响,将图像的多特征信息引入到图割算法中,提出了一种结合图像的多特征信息图割目标分割方法。该方法先选取像素点的多种图像特征组成特征向量,并对已做好标记的目标和背景种子点的特征向量分别进行FCM聚类,然后分别计算各像素点与这两类种子点的各聚类中心的最短欧式距离,并据此信息完成对能量函数的构造,最终运用最大流/最小割的方法得到图像分割的结果。其与传统图割算法相比,分割结果有了明显改善。实验结果表明,该算法具有有效性。     

Multiscale image segmentation using wavelet-domain hidden Markovmodels

We introduce a new image texture segmentation algorithm, HMTseg, based on wavelets and the hidden Markov tree (HMT) model. The HMT is a tree-structured probabilistic graph that captures the statistical properties of the coefficients of the wavelet transform. Since the HMT is particularly well suited to images containing singularities (edges and ridges), it provides a good classifier for distinguishing between textures. Utilizing the inherent tree structure of the wavelet HMT and its fast training and likelihood computation algorithms, we perform texture classification at a range of different scales. We then fuse these multiscale classifications using a Bayesian probabilistic graph to obtain reliable final segmentations. Since HMTseg works on the wavelet transform of the image, it can directly segment wavelet-compressed images without the need for decompression into the space domain. We demonstrate the performance of HMTseg with synthetic, aerial photo, and document image segmentations.     

Image denoising using sparse representation classification and non-subsampled shearlet transform

In this paper, an image denoising method is proposed which uses sparse un-mixing by variable splitting and augmented Lagrangian (SUnSAL) classifier in the non-subsampled shearlet transform (NSST) domain. To this aim, the noisy image is decomposed into various scales and directional components using the NSST and then the feature vector for a pixel is constituted by the spatial regularity in the NSST domain. Subsequently, the NSST detail coefficients are labeled as edge-related coefficients or noise-related ones by using the SUnSAL classifier. The noisy coefficients of the NSST subbands are then denoised by the shrink method, which uses the adaptive Bayesian threshold for denoising. Finally, the inverse NSST transform is applied to the denoised coefficients. Our experiments demonstrate that the proposed approach improves the image quality in terms of both subjective and objective inspections, compared with some other state-of-the-art denoising techniques.     

基于图上随机游走过程的SAR图像图谱分割方法

基于图上的随机游走过程,提出了一种新的合成孔径雷达(SAR)图像图谱分割方法。首先根据SAR图像的统计性质,构造了适合于SAR图像的相似度度量函数;然后在正交谱分解和矩阵逼近理论的基础上,建立了SAR图像图谱分割方法中分类数目的确定准则。最后实现了基于谱聚类的SAR图像分割,并通过实验证明了所提方法的有效性和应用潜力。     

Graph regularized low-rank feature mapping for multi-label learning with application to image annotation

Automatic image annotation has emerged as a hot research topic in the last two decades due to its application in social images organization. Most studies treat image annotation as a typical multi-label classification problem, where the shortcoming of this approach lies in that in order to a learn reliable model for label prediction, it requires sufficient number of training images with accurate annotations. Being aware of this, we develop a novel graph regularized low-rank feature mapping for image annotation under semi-supervised multi-label learning framework. Specifically, the proposed method concatenate the prediction models for different tags into a matrix, and introduces the matrix trace norm to capture the correlations among different labels and control the model complexity. In addition, by using graph Laplacian regularization as a smooth operator, the proposed approach can explicitly take into account the local geometric structure on both labeled and unlabeled images. Moreover, considering the tags of labeled images tend to be missing or noisy, we introduce a supplementary ideal label matrix to automatically fill in the missing tags as well as correct noisy tags for given training images. Extensive experiments conducted on five different multi-label image datasets demonstrate the effectiveness of the proposed approach.     

基于子空间类标传播和正则判别分析的单标记图像人脸识别

针对单标记图像人脸识别问题,该文提出一种基于子空间类标传播和正则判别分析的半监督维数约简方法。首先,基于子空间假设设计了一种类标传播方法,将类标信息传播到无类标样本上。然后,在传播得到的带类标数据集上使用正则判别分析对数据进行维数约简。最后,在低维空间使用最近邻方法对测试人脸完成识别。在3个公共人脸数据库CMU PIE, Extended Yale B和AR上的实验,验证了该方法的可行性和有效性。     

基于多维度特征遥感图像分类方法的研究北大核心CSCD

为了解决传统高光谱图像分类方法精度低、计算成本高及未能充分利用空-谱信息的问题,本文提出一种基于多维度并行卷积神经网络(multidimensional parallel convolutional neural network,3D-2D-1D PCNN)的高光谱图像分类方法。首先,该算法利用不同维度卷积神经网络(convolutional neural network,CNN)提取高光谱图像信息中的空-谱特征、空间特征及光谱特征;之后,采用相同并行卷积层将组合后的空-谱特征、空间特征及光谱特征进行特征融合;最后,通过线性分类器对高光谱图像信息进行精准分类。本文所提方法不仅可以提取高光谱图像中更深层次的空间特征和光谱特征信息,同时能够将光谱图像不同维度的特征进行融合,减小计算成本。在Indian Pines、Pavia Center和Pavia University数据集上对本文算法和4种传统算法进行对比实验,结果表明,本文算法均得到最优结果,分类精度分别达到了99.210%、99.755%和99.770%。