基于DT-CWT变换统计模型的医学图像纹理检索

针对离散小波变换具有平移变化性和弱方向性的特性,本文提出了一种基于双树复小波变换(DT-CWT)统计模型的医学图像纹理检索方法 .该方法 首先利用双树复小波变换系数的平移不变和多方向选择特性,建立广义高斯分布的统计模型,然后基于该模型提取图像的特征矢量,最后利用改进的Log-likelih60d(ILL)相似性测度算法进行纹理图像检索.实验结果 表明,该方法 的检索查准率达到了82.8%,相比于传统的Gabor算法和小波算法都有了较大的提高,对今后的纹理图像检索具有重要的理论与实际意义.     

基于新疆维吾尔医草药图像形状特征的检索研究

目的探讨草药图像的Hu不变矩对基于内容的维吾尔草药图像的检索效果。方法对维吾尔草药图像进行预处理,使用Canny算子、轮廓跟踪等方法获取草药图像的形状,提取草药图像的Hu不变矩形状特征,构建基于草药图像形状特征的草药图像检索系统,并进行图像检索效果验证。结果检索结果表明,基于草药图像的Hu不变矩特征对叶类、花类维吾尔草药图像的平均查准率达到70％,平均查全率达到80％。结论草药图像的Hu不变矩形状特征对基于内容的维吾尔草药图像的检索有较好的检索效果。     

基于Faster R-CNN的图像检索手腕骨折分类研究

目的 为克服手腕X射线图像病灶区域排列复杂容易造成骨科医生漏诊误诊及诊断效率低的问题,提出一种更快速的基于区域的卷积神经网络（Faster Region-Convolutional Neural Network,Faster R-CNN）的医学图像检索手腕分类算法。方法 首先利用限制对比度自适应直方图均衡化算法对手腕样本数据进行预处理,然后利用Faster R-CNN快速定位手腕图像的感兴趣区域,并提取其方向梯度直方图特征、Haralick纹理特征以及深度特征,最后利用卷积神经网络将提取到的多种特征进行有效融合后,送入本文改进的图像检索诊断模型完成对手腕图像的分类任务。结果 本文提出的手腕图像检测模型分类的曲线下面积均值为0.893,诊断的准确率优于对比实验结果,较之前的研究方法提高了约5%。结论 本文提出的Faster R-CNN的图像检索手腕骨折分类研究具有一定的有效性和鲁棒性。     

一种改进的FCM多分辨率图像分割算法及其应用

提出了一种改进的模糊C均值聚类多分辨率图像分割算法,该算法利用像点的邻域信息对像点的模糊隶属度函数进行修正。实验证明:该算法具有对噪声不敏感的优点,在进行图像分割,特别是对含噪图像进行分割时能获得较好的效果。     

CT图像特征的自动获取与检索新方法

目的自动获取CT图像特征,提出实现基于内容的CT图像数据库检索新方法。方法本研究针对CT医学图像,提出应用最大期望分割算法来获取其区域特征,并组合感兴趣区域的累积直方图特征、纹理和形状信息构成检索的特征向量,从而把图像表征为特征空间中的一个向量集合。结果当向数据库提交查询图像时,经过特征匹配,最终按相似度由大到小的顺序返回目标图像。结论实验结果表明,本研究提出的基于内容的CT图像检索方案在满足临床需求的同时,获得了较高的查询精度和效率。     

CT图像特征的自动获取与检索新方法

目的 自动获取CT图像特征，提出实现基于内容的CT图像数据库检索新方法。方法 本研究针对CT医学图像，提出应用最大期望分割算法来获取其区域特征．并组合感兴趣区域的累积直方图特征、纹理和形状信息构成检索的特征向量，从而把图像表征为特征空间中的一个向量集合。结果 当向数据库提交查询图像时，经过特征匹配，最终按相似度由大到小的顺序返回目标图像。结论 实验结果表明，本研究提出的基于内容的CT图像检索方案在满足临床需求的同时．获得了较高的查询精度和效率。     

一种基于正交多项式展开的CT三维投影数据重建算法

提出了一种新的基于正交多项式展开的CT三维投影数据重建算法。首先利用正交多项式空间中的一组正交基对定义在圆柱域的三维密度函数进行傅里叶展开,推导函数与投影数据的部分和关系;然后使用高斯求积公式对上述部分和表达式积分,得到针对三维投影数据的重建算法。在此基础上引入快速傅里叶变换,以提升算法整体的重建效率和数值计算的可行性。实验结果表明:本文提出的算法能够很好地对CT三维投影数据进行重建,且重建效率较高。     

基于改进的GHSOM聚类算法的图像检索

传统的图像检索需要顺序比较图像库中的图像与请求图像的相似度,检索速度和检索准确度都很低。针对此问题,提出了一种基于改进的增长型分层自组织映射网络（GHSOM）的图像检索方法。先将图像特征库用改进的GHSOM算法进行聚类,在图像检索时先在GHSOM网络模型上找到相似的类,然后在相似的类上继续进行检索,大大提高了检索效率。并且在搜索相似的类时充分利用GHSOM网络的分层结构,更进一步地提高了检索效率。改进的GHSOM网络根据算法的特点构建了赤迟信息量（AIC）准则,用该准则来选择每个独立的SOM网络的生长参数,使得每个网络都能正确地表达映射到它的数据集的结构,提高GHSOM网络的聚类效果,从而提高检索的准确性。实验结果表明,改进的GHSOM算法得到了更好的聚类效果,基于它的图像检索方法提高了将近3倍的图像匹配速度,同时图像检索准确率也得到了一定程度的提高。     

一种基于图像正交矩的肿瘤细胞识别技术的研究

肿瘤细胞自动识别一直是研究的焦点.由于矩不变量具有高度浓缩的平移、尺度、旋转、灰度多畸不变图像特征,本研究选择圆谐-傅立叶正交矩作为肿瘤细胞的特征表征量,使用最小加权平均距离方法进行分类,利用计算机识别系统,对痰、尿、胸腹水细胞学涂片进行了细胞识别实验,获得了较好的识别结果,具有临床应用潜力.     

基于多尺度小波残差网络的稀疏角度CT图像恢复

目的 稀疏角度CT具有加速数据采集和减少辐射剂量的优点。然而,由于采集信息的减少,使用传统滤波反投影算法（FBP）进行重建得到的图像中伴有严重的条形伪影和噪声。针对这一问题,本文提出基于多尺度小波残差网络（MWResNet）对稀疏角度CT图像进行恢复。方法 本网络中将小波网络与残差块相结合,用以增强网络对图像特征的提取能力和加快网络训练效率。实验中使用真实的螺旋几何CT图像数据“Low-dose CT Grand Challenge”数据集训练网络。通过观察图像表征和计算定量参数的方法对结果进行评估,并与其他现有网络进行比较,包括图像恢复迭代残差卷积网络（IRLNet）,残差编码解码卷积神经网络（REDCNN）和FBP卷积神经网络（FBPConvNet）。结果 实验结果表明,本文提出的多尺度小波残差网络优于其余对比方法。结论 本文提出的MWResNet网络能够在保持稀疏角度CT图像边缘细节信息的同时有效抑制噪声和伪影。     

Evaluation of a Content-Based Retrieval System for Blood Cell Images with Automated Methods

Content-based image retrieval techniques have been extensively studied for the past few years. With the growth of digital medical image databases, the demand for content-based analysis and retrieval tools has been increasing remarkably. Blood cell image is a key diagnostic tool for hematologists. An automated system that can retrieved relevant blood cell images correctly and efficiently would save the effort and time of hematologists. The purpose of this work is to develop such a content-based image retrieval system. Global color histogram and wavelet-based methods are used in the prototype. The system allows users to search by providing a query image and select one of four implemented methods. The obtained results demonstrate the proposed extended query refinement has the potential to capture a user’s high level query and perception subjectivity by dynamically giving better query combinations. Color-based methods performed better than wavelet-based methods with regard to precision, recall rate and retrieval time. Shape and density of blood cells are suggested as measurements for future improvement. The system developed is useful for undergraduate education.     

Comparison of Several Texture Features for Tumor Detection in CE Images

Capsule endoscopy (CE) has been widely used as a new technology to diagnose gastrointestinal tract diseases, especially for small intestine. However, the large number of images in each test is a great burden for physicians. As such, computer aided detection (CAD) scheme is needed to relieve the workload of clinicians. In this paper, automatic differentiation of tumor CE image and normal CE image is investigated through comparative textural feature analysis. Four different color textures are studied in this work, i.e., texture spectrum histogram, color wavelet covariance, rotation invariant uniform local binary pattern and curvelet based local binary pattern. With support vector machine being the classifier, the discrimination ability of these four different color textures for tumor detection in CE images is extensively compared in RGB, Lab and HSI color space through ten-fold cross-validation experiments on our CE image data. It is found that HSI color space is the most suitable color space for all these texture based CAD systems. Moreover, the best performance achieved is 83.50% in terms of average accuracy, which is obtained by the scheme based on rotation invariant uniform local binary pattern.     

Medical Image Retrieval with Compact Binary Codes Generated in Frequency Domain Using Highly Reactive Convolutional Features

Efficient retrieval of relevant medical cases using semantically similar medical images from large scale repositories can assist medical experts in timely decision making and diagnosis. However, the ever-increasing volume of images hinder performance of image retrieval systems. Recently, features from deep convolutional neural networks (CNN) have yielded state-of-the-art performance in image retrieval. Further, locality sensitive hashing based approaches have become popular for their ability to allow efficient retrieval in large scale datasets. In this paper, we present a highly efficient method to compress selective convolutional features into sequence of bits using Fast Fourier Transform (FFT). Firstly, highly reactive convolutional feature maps from a pre-trained CNN are identified for medical images based on their neuronal responses using optimal subset selection algorithm. Then, layer-wise global mean activations of the selected feature maps are transformed into compact binary codes using binarization of its Fourier spectrum. The acquired hash codes are highly discriminative and can be obtained efficiently from the original feature vectors without any training. The proposed framework has been evaluated on two large datasets of radiology and endoscopy images. Experimental evaluations reveal that the proposed method significantly outperforms other features extraction and hashing schemes in both effectiveness and efficiency.     

Endoscopic Image Classification and Retrieval using Clustered Convolutional Features

With the growing use of minimally invasive surgical procedures, endoscopic video archives are growing at a rapid pace. Efficient access to relevant content in such huge multimedia archives require compact and discriminative visual features for indexing and matching. In this paper, we present an effective method to represent images using salient convolutional features. Convolutional kernels from the first layer of a pre-trained convolutional neural network (CNN) are analyzed and clustered into multiple distinct groups, based on their sensitivity to colors and textures. Dominant features detected by each cluster are collected into a single, layout-preserving feature map using a spatial maximal activator pooling (SMAP) approach. A moving window based structured pooling method then captures spatial layout features and global shape information from the aggregated feature map to populate feature histograms. Finally, individual histograms for each cluster are combined into a single comprehensive feature histogram. Clustering convolutional feature space allow extraction of color and texture features of varying strengths. Further, the SMAP approach enable us to select dominant discriminative features. The proposed features are compact and capable of conveniently outperforming several existing features extraction approaches in retrieval and classification tasks on endoscopy images dataset.     

一种基于改进SURF和K-Means聚类的布料图像匹配算法

计算机图像智能处理技术为服装设计师开展设计、启发灵感提供了方便和可能。通过提取布料图像的SURF特征可以实现布料图像形状分析,但由于SURF特征维数高、特征提取是基于灰度图进行,因此存在匹配速度慢、匹配结果不够符合人眼视觉特点的问题。本文提出了基于小波变换的自适应SURF特征提取算法和基于K-Means聚类的布料图像颜色分析方法。通过融合图像形状特征、颜色特征,加快了布料图像匹配速度,使布料图像的匹配结果更加符合人眼视觉感受。在8种不同类型布料图像上的实验验证了该算法的有效性。