GNN-CRC: Discriminative Collaborative Representation-Based Classification via Gabor Wavelet Transformation and Nearest Neighbor

Collaborative representation-based classification (CRC) is a distance based method, and it obtains the original contributions from all samples to solve the sparse representation coefficient. We find out that it helps to enhance the discrimination in classification by integrating other distance based features and/or adding signal preprocessing to the original samples. In this paper, we propose an improved version of the CRC method which uses the Gabor wavelet transformation to preprocess the samples and also adapts the nearest neighbor (NN) features, and hence we call it GNN-CRC. Firstly, Gabor wavelet transformation is applied to minimize the effects from the background in face images and build Gabor features into the input data. Secondly, the distances solved by NN and CRC are fused together to obtain a more discriminative classification. Extensive experiments are conducted to evaluate the proposed method for face recognition with different instantiations. The experimental results illustrate that our method outperforms the naive CRC as well as some other state-of-the-art algorithms.     

基于Gabor变换和灰度梯度共生矩阵的人耳识别研究

人耳识别作为一种新兴的生物特征识别技术,具有其自身独特的优势。提出一种基于Gabor变换和灰度梯度共生矩阵的人耳身份识别方法。首先,利用Gabor变换和灰度-梯度共生矩阵融合提取人耳图像的纹理特征,然后采用K-NN分类器对特征进行分类。该方法用USTB人耳图像库做测试。实验结果表明介绍的提取人耳图像的纹理融合特征的方法优于只采用Ga-bor变换提取特征或是只提取灰度梯度共生矩阵的二次统计特征的性能。在明氏距离测度及K=1时,交叉验证识别率达到81.77%。     

基于差分能量图和CGBP的微表情识别

微表情是一种不能自主控制和伪装的面部表情,其与诚信度的关系密切,具有持续时间短且难以识别的特征.为提高计算机自动识别微表情的准确性,提出一种基于差分能量图和中心化Gabor二值模式（centralized Gabor binary patterns,CGBP）的微表情识别方法.该方法首先利用差分法计算微表情序列的能量得到差分能量图,获得人脸面部肌肉相位的变化;其次将Gabor与中心二值模式CBP相结合,得到CGBP算子对能量图进行微表情的特征提取;最后利用ELM分类器进行微表情分类识别.在CASME微表情库上的实验结果表明,该方法比LBP-TOP、DTSA3、Gabor、VLBP、CBP-TOP算法更能有效地获得微表情序列的时空纹理特征,平均识别率为86.54%.      

灰度一梯度共生／环形Gabor滤波纹理分类

解决旋转不变纹理分析问题，提出一种新的旋转不变纹理分类方法：灰度～梯度共生（GGC）／环形Gabor滤波（CGF）联合。将灰度—梯度共生矩阵用于纹理图像的统计分析中。此外，将传统的Gabor滤波器（TGF）改进为环形对称形式，通过CGF信道输出区得旋转不变纹理特征。将两种方法结合起来作为分类纹理依据，提出基于信息增益的特征选择算法。实验结果表明该方法具有较高的分类性能。     

Kinect-based automatic spatial registration framework for neurosurgical navigation

As image-guided navigation plays an important the pre-operative images with the intra-operative patient role in neurosurgery, the spatial registration mapping position becomes crucial for a high accurate surgi- cal output. Conventional landmark-based registration requires expensive and time-consuming logistic support. Surface-based registration is a plausible alternative due to its simplicity and efficacy. In this paper, we propose a comprehensive framework for surface-based registration in neurosurgical navigation, where Kinect is used to auto- matically acquire patient＇s facial surface in a real time manner. Coherent point drift （CPD） algorithm is employed to register the facial surface with pre-operative images （e.g., computed tomography （CT） or magnetic resonance imaging （MRI）） using a coarse-to-fine scheme. The spatial registration results of 6 volunteers demonstrate that the proposed framework has potential for clinical use.     

MUTUAL INFORMATION BASED 3D NON-RIGID REGISTRATION OF CT/MR ABDOMEN IMAGES

Introduction　　 Automating medical image registration is be-coming an increasingly important goal. It formsthe basis of image processing techniques to com-bine information from the different modalities,which are now frequently acquired for many pa-tients. Such combined representations of patientimages have been shown to assistin the interpreta-tion of the complementary information provided bythe modalities[1,2 ] .　　 A variety of imaging modalities gives insightto different parameters and in…     

D-山梨醇清除率法评估肝储备功能

目的探讨D-山梨醇肝脏清除率(CLh-s)法补充吲哚箐绿15min潴留率(ICGR15)和Child-Pugh分级相结合评估肝硬化门脉高压患者肝储备功能的可行性。方法41名肝硬化门脉高压患者分别给予Child-Pugh分级、ICGR15、CLh-s检测评估肝储备功能,对前两种评估方法出现交叉重叠的患者,进一步分析其CLh-s值与手术并发症的相关性。结果Child-Pugh分级与ICGR15值(以40%为界)交错重叠主要集中在B级和C级之间。在Child-Pugh分级B级的18例患者中,>40%的患者有5例,术后3例出现明显并发症(CLh-s分别为629.52、509.79、450.71 mL/min),2例未出现明显并发症(CLh-s分别为784.49、779.36 mL/min);在Child-Pugh分级C级的13例患者中,有4例ICGR15<40%的患者,2例行手术治疗,其中1例出现并发症(CLh-s为484.57 mL/min)。1例未出现明显并发症(CLh-s为723.36 mL/min)。概括之,CLh-s>700 mL/min者,手术并发症少;CLh-s<700 mL/min,者手术并发症多。结论CLh-s与肝硬化门脉高压患者手术并发症有关。该法可对ICGR15和Child-Pugh分级联合评估肝储备功能时出现交叉重叠者进一步分类,使肝储备功能评估更为准确可靠。     

指纹图像预处理方法的研究与比较

指纹图像预处理需针对不同的噪声产生原因而采用不同的方法,先对采集到的退化图像进行Wiener滤波。然后对复原后的图像进行增强预处理．着重对主要预处理方法Gabor方法和各向异性扩散技术进行了分析对比,并就这些方法中的参数选择进行了对比研究．     

Computer-aided detection for CT colonography

CT colonography （CTC） is a non-invasive screening technique for the detection of eolorectal polyps, as an alternative to optical colonoscopy in clinical practice. Computer-aided detection （CAD） for CTC refers to a scheme which automatically detects colorectal polyps and masses in CT images of the colon. It has the potential to increase radiologists＇ detection performance and greatly shorten the detection time. Over the years, technical developments have advanced CAD for CTC substantially. In this paper, key techniques used in CAD for polyp detection are reviewed. Illustrations about the performance of existing CAD schemes show their relatively high sensitivity and low false positive rate. However, these CAD schemes are still suffering from technical or clinical problems. Some existing challenges faced by CAD are also pointed out at the end of this paper.     

Segmentation of haustral folds and polyps on haustral folds in CT colonography using complementary geodesic distance transformation

Computer-aided detection （CAD） for CT colonography refers to a scheme that automatically detects polyps in CT images of colon. Current CAD schemes already have a relatively high sensitivity and a low false positive rate. However, misdiagnosis and missed diagnosis are still common to happen, mainly due to the existence of haustral folds （HFs）. An innovative idea of segmenting semilunar HFs from the smooth colonic wall and then using different methods to detect polyps on HFs and those on the smooth colonic wall is proposed in this paper to reduce the false positives and false negatives caused by HFs. For the polyps on HFs, a novel segmentation method is specially developed based on complementary geodesic distance transformation （CGDT）. The proposed method is tested on four different models and real CT data, The property of CGDT is proved and our method turns out to be effective for HF segmentation and polyp segmentation. The encouraging experimental results primarily show the feasibility of the proposed method and its potential to improve the detection performance of CAD schemes.     

Classification decision tree algorithm assisting in diagnosing solitary pulmonary nodule by SPECT/CT fusion imaging

Objective To develop a classification tree algorithm to improve diagnostic performances of 99mTc-MIBI SPECT/CT fusion imaging in differentiating solitary pulmonary nodules (SPNs). Methods Forty-four SPNs, including 30 malignant cases and 14 benign ones that were eventually pathologically identified, were included in this prospective study. All patients received 99Tcm-MIBI SPECT/CT scanning at an early stage and a delayed stage before operation. Thirty predictor variables, including 11 clinical variables, 4 variables of emission and 15 variables of transmission information from SPECT/CT scanning, were analyzed independently by the classification tree algorithm and radiological residents. Diagnostic rules were demonstrated in tree-topology, and diagnostic performances were compared with Area under Curve (AUC) of Receiver Operating Characteristic Curve (ROC). Results A classification decision tree with lowest relative cost of 0.340 was developed for 99Tcm-MIBI SPECT/CT scanning in which the value of Target/Normal region of 99Tcm-MIBI uptake in the delayed stage and in the early stage, age, cough and specula sign were five most important contributors. The sensitivity and specificity were 93.33% and 78. 57e, respectively, a little higher than those of the expert. The sensitivity and specificity by residents of Grade one were 76.67% and 28.57%, respectively, and AUC of CART and expert was 0.886±0.055 and 0.829±0.062, respectively, and the corresponding AUC of residents was 0.566±0.092. Comparisons of AUCs suggest that performance of CART was similar to that of expert (P=0.204), but greater than that of residents (P<0.001). Conclusion Our data mining technique using classification decision tree has a much higher accuracy than residents. It suggests that the application of this algorithm will significantly improve the diagnostic performance of residents.     

肝移植术后并发症的影像学诊断

目的系统分析肝移植术后正常及常见并发症的影像学表现。方法使用Philips Secura螺旋CT扫描仪对50例肝移植术后患者进行检查,CT扫描范围自膈顶至腰3椎体下缘水平,对比剂1.3mL/kg体质量,注药流率2.5mL/s,延迟时间30、60、120s。对拔除T管后出现胆管并发症患者使用Philips Gyroscan NT1.5T磁共振扫描仪检查。使用GE Advance Lp/Lc数字血管造影机,经股动脉穿刺进行肝动脉造影。结果27例肝移植术后患者出现移植肝下积液及右侧胸腔积液,门静脉伴行影像4例,肝动脉吻合口狭窄2例,肝动脉血栓1例,门静脉吻合口狭窄2例,胆管吻合口部位狭窄1例,非吻合口狭窄3例,胆瘘4例,肿瘤复发4例。结论CT、磁共振胆道水成像(MRCP)和数字减影(DSA)可以清晰显示肝移植术后血管、胆管并发症及其他少见并发症。     

CT reconstruction with priori MRI images through multi-group datasets expansion

Computed tomography (CT) reconstruction with a well-registered priori magnetic resonance imaging (MRI) image can improve reconstruction results with low-dose CT, because well-registered CT and MRI images have similar structures. However, in clinical settings, the CT image of patients does not always match the priori MRI image because of breathing and movement of patients during CT scanning. To improve the image quality in this case, multi-group datasets expansion is proposed in this paper. In our method, multi-group CT-MRI datasets are formed by expanding CT-MRI datasets. These expanded datasets can also be used by most existing CT-MRI algorithms and improve the reconstructed image quality when the CT image of a patient is not registered with the priori MRI image. In the experiments, we evaluate the performance of the algorithm by using multi-group CT-MRI datasets in several unregistered situations. Experiments show that when the CT and priori MRI images are not registered, the reconstruction results of using multi-group dataset expansion are better than those obtained without using the expansion.     

基于小波变换和Gabor滤波的指纹图像增强算法

在指纹自动识别系统中,图像增强是比较重要的一个环节,它直接影响到指纹识别系统的识别精度．利用指纹图像在经小波多尺度分解后,低频部分集中了指纹图像的主要纹理信息这一特性,提出了一种在小波域对指纹图像进行Gabor滤波增强的算法,实验表明,该算法能够使图像的质量明显得到增强,方便了后续指纹特征的提取。     

TELEMEDICINE NETWORK BASED ON CODE-DIVISION MULTIPLE ACCESS WIRELESS TECHNOLOGY

Telemedicinehasbeenwidelyusedinmanyhealthcareapplicationssuchasmedicalcareinre moteruralareasandaftercareofpatientswithpace maker implanted[4] .Anotherwell knownexampleoftelemedicineistheremotetransmissionanddiag nosisofECGthroughtelephonenetwork[1 -3 ] .Telemedicineisalsoveryhelpfulinmanyemergen cyandambulancesituations.Earlydiagnosisbyaspecialistinemergenciesisparticularlyimportanttothepatients[5,6] .RecentstudyhasshownthatsocialchangesinJapanhaveresultedinarapidincreaseofacutecardiovascul…     

基于结构性字典学习的高光谱遥感图像分类

为提高高光谱遥感图像的分类精度,提出了一种新的结构性稀疏表示及字典学习的高光谱遥感图像分类方法.该方法能同时利用高光谱遥感图像像素间的空间及光谱关系得到表示每个像素的字典,被划分为同一像素组的像素具有通用的稀疏模式;由字典计算图像的稀疏表示系数获得遥感图像的稀疏表示特征;利用线性支持向量机算法实现对高光谱遥感图像的分类.对AVIRIS和ROSIS高光谱遥感图像进行的实验结果表明:提出的方法比普通字典学习分类精度分别提高0.041 1和0.046 6,Kappa系数分别提高0.179 3和0.056 3.      

基于特征脸和LS-SVM分类器的人脸性别分类

提出使用特征脸和最小二乘支持向量机(LS-SVM)分类器相结合进行人脸性别分类.我们首先从训练图像中求得特征脸空间,然后将训练集和测试集图像投影到特征脸空间得到投影系数.使用训练样本投影系数训练LS-SVM分类器,对训练图像和测试图像进行分类试验,同时计算出分类准确率,实验结果表明LS-SVM分类要比其他分类算法有更好的优越性.在实验中我们也使用交叉验证来确定特征脸数目和核函数参数.     

An information-based color feature representation and its application in detecting adult images

For many image classification tasks, color histogram is usually employed as an important “signature” to describe the color distribution of the image and infer the image content. However, most traditional color histograms cannot achieve satisfactory results in many image classification systems. In order to improve the accuracy and reduce the computational complexity of the classification task, an information-based color feature representation is proposed in this paper. The mutual information between the feature and the class label is adopted to evaluate the discriminative power of the feature. A novel quantization scheme is presented, which removes the redundant color components and combines the adjacent components together to generate a new feature to maximize the discriminative ability. An iterative algorithm is performed to derive the color space quantization and color feature generation. In order to illustrate the effectiveness of the proposed color representation, a specific image classification task, i.e., differentiating the adult images from benign ones, is employed. Experimental results show that our color feature achieves better classification performance and better efficiency compared with the traditional color histogram.     

Multi-Model Ensemble Deep Learning Method to Diagnose COVID-19 Using Chest Computed Tomography Images

Deep learning based analyses of computed tomography (CT) images contribute to automated diagnosis of COVID-19,and ensemble learning may commonly provide a better solution.Here,we proposed an ensemble learning method that integrates several component neural networks to jointly diagnose COVID-19.Two ensemble strategies are considered:the output scores of all component models that are combined with the weights adjusted adaptively by cost function back propagation;voting strategy.A database containing 8347 CT slices of COVID-19,common pneumonia and normal subjects was used as training and testing sets.Results show that the novel method can reach a high accuracy of 99.37％ (recall:0.9981;precision:0.9893),with an increase of about 7％in comparison to single-component models.And the average test accuracy is 95.62％ (recall:0.9587;precision:0.9559),with a corresponding increase of 5.2％.Compared with several latest deep learning models on the identical test set,our method made an accuracy improvement up to 10.88％.The proposed method may be a promising solution for the diagnosis of COVID-19.