基于脑部磁共振图像三维局部模式变换特征提取进行阿尔茨海默病病程预测分类

本文提出一种三维局部模式变换提取进行纹理特征并与常规特征相融合的方法,基于脑部磁共振图像,对认知功能正常的健康人体（CN）、轻度认知障碍（MCI）患者和阿尔茨海默病（AD）患者进行预测分类.首先对46例CN对照组、61例MCI患者和25例AD患者的脑部磁共振图像提取感兴趣区域,然后提取双侧海马体组织、灰质和白质的三维局部模式变换纹理特征和常规特征,并将两类特征融合,使用支持向量机分类算法进行分类.结果显示利用本方法,基于双侧海马体组织对AD组和CN组进行分类的准确率为88.73%、敏感度为78.00%、特异度为95.7%、受试者工作特征（ROC）曲线下面积（AUC）为0.886 5;基于灰质的准确率为85.92%、敏感度为80.00%、特异度为86.6%、AUC为0.854 3.这证明基于海马体磁共振图像,利用本文提出的改进三维局部模式变换提取的纹理特征进行阿尔茨海默病病程分类效果较好,融合常规特征后更可提高分类预测的精度.     

Non-Gaussian diffusion MRI assessment of brain microstructure in mild cognitive impairment and Alzheimer’s disease

We report the first application of a novel diffusion-based MRI method, called diffusional kurtosis imaging (DKI), to investigate changes in brain tissue microstructure in patients with mild cognitive impairment (MCI) and AD and in cognitively intact controls. The subject groups were characterized and compared in terms of DKI-derived metrics for selected brain regions using analysis of covariance with a Tukey multiple comparison correction. Receiver operating characteristic (ROC) and binary logistic regression analyses were used to assess the utility of regional diffusion measures, alone and in combination, to discriminate each pair of subject groups. ROC analyses identified mean and radial kurtoses in the anterior corona radiata as the best individual discriminators of MCI from controls, with the measures having an area under the ROC curve (AUC) of 0.80 and 0.82, respectively. The next best discriminators of MCI from controls were diffusivity and kurtosis (both mean and radial) in the prefrontal white matter (WM), with each measure having an AUC between 0.77 and 0.79. Finally, the axial diffusivity in the hippocampus was the best overall discriminator of MCI from AD, having an AUC of 0.90. These preliminary results suggest that non-Gaussian diffusion MRI may be beneficial in the assessment of microstructural tissue damage at the early stage of MCI and may be useful in developing biomarkers for the clinical staging of AD.     

A 3D densely connected convolution neural network with connection-wise attention mechanism for Alzheimer's disease classification

PurposeAlzheimer's disease (AD) is a progressive and irreversible neurodegenerative disease. In recent years, machine learning methods have been widely used on analysis of neuroimage for quantitative evaluation and computer-aided diagnosis of AD or prediction on the conversion from mild cognitive impairment (MCI) to AD. In this study, we aimed to develop a new deep learning method to detect or predict AD in an efficient way.Materials and methodsWe proposed a densely connected convolution neural network with connection-wise attention mechanism to learn the multi-level features of brain MR images for AD classification. We used the densely connected neural network to extract multi-scale features from pre-processed images, and connection-wise attention mechanism was applied to combine connections among features from different layers to hierarchically transform the MR images into more compact high-level features. Furthermore, we extended the convolution operation to 3D to capture the spatial information of MRI. The features extracted from each 3D convolution layer were integrated with features from all preceding layers with different attention, and were finally used for classification. Our method was evaluated on the baseline MRI of 968 subjects from ADNI database to discriminate (1) AD versus healthy subjects, (2) MCI converters versus healthy subjects, and (3) MCI converters versus non-converters.ResultsThe proposed method achieved 97.35% accuracy for distinguishing AD patients from healthy control, 87.82% for MCI converters against healthy control, and 78.79% for MCI converters against non-converters. Compared with some neural networks and methods reported in recent studies, the classification performance of our proposed algorithm was among the top ranks and improved in discriminating MCI subjects who were in high risks of conversion to AD.ConclusionsDeep learning techniques provide a powerful tool to explore minute but intricate characteristics in MR images which may facilitate early diagnosis and prediction of AD.     

Combined multi-kernel support vector machine and wavelet analysis for hyperspectral remote sensing image classification

Many remote sensing image classifiers are limited in their ability to combine spectral features with spatial features.Multi-kernel classifiers,however,are capable of integrating spectral features with spatial or structural features using multiple kernels and summing them for final outputs.Using a support vector machine(SVM) as classifier,different multi-kernel classifiers are constructed and tested using 64-band Operational Modular Imaging Spectrometer II hyperspectral image of Changping Area,Beijing City.Results show that by integrating spectral and wavelet texture information,multi-kernel SVM classifiers can obtain more accurate classification results than sole-kernel SVM classifiers and cross-information SVM kernel classifiers.Moreover,when the multi-kernel SVM classifier is used,the combination of the first four principal components from principal component analysis and wavelet texture provides the highest accuracy(97.06%).Multi-kernel SVM is therefore an effective approach to improve the accuracy of hyperspectral image classification and to expand possibilities for remote sensing image interpretation and application.     

A novel binary tree support vector machine for hyperspectral remote sensing image classification

According to the principle of support vector machine (SVM) and the inter-class separability rule of hyperspectral data, a novel binary tree SVM classifier based on separability measure among different classes is proposed for hyperspectral image classification. J–M distance is used to measure the separability in order to generate the binary tree automatically. By experiments using airborne operational modular imaging spectrometer II (OMIS II) data, satellite EO-1 Hyperion hyperspectral data and airborne AVIRIS data, the classification accuracy of different multi-class SVMs is obtained and compared. Experimental results indicate that the proposed adaptive binary tree classifier outperforms other existing multi-class SVM strategies. Use of the adaptive binary tree SVM classifier is a novel approach to improve the accuracy of hyperspectral image classification and expand the possibilities for interpretation and application of hyperspectral remote sensing image.     

Classifier ensembles for fMRI data analysis: an experiment

Functional magnetic resonance imaging (fMRI) is becoming a forefront brain–computer interface tool. To decipher brain patterns, fast, accurate and reliable classifier methods are needed. The support vector machine (SVM) classifier has been traditionally used. Here we argue that state-of-the-art methods from pattern recognition and machine learning, such as classifier ensembles, offer more accurate classification. This study compares 18 classification methods on a publicly available real data set due to Haxby et al. [Science 293 (2001) 2425–2430]. The data comes from a single-subject experiment, organized in 10 runs where eight classes of stimuli were presented in each run. The comparisons were carried out on voxel subsets of different sizes, selected through seven popular voxel selection methods. We found that, while SVM was robust, accurate and scalable, some classifier ensemble methods demonstrated significantly better performance. The best classifiers were found to be the random subspace ensemble of SVM classifiers, rotation forest and ensembles with random linear and random spherical oracle.     

基于ICA与SVM算法的高光谱遥感影像分类

提出了一种利用独立分量分析(ICA)与支撑向量机(SVM)算法进行高光谱遥感影像分类的新方法。采用ICA算法对高光谱遥感影像(PHI传感器获取,80波段)进行了特征提取,并以提取出的影像数据(光谱维数为20)构建SVM分类器。对SVM算法进行核函数删选与参数寻优后,发现采用RBF核的SVM算法(C=103,γ=0.05)分类结果最佳,分类精度与Kappa系数分别达94.5127%与0.935 1,优于BP-神经网络(分类精度39.4758%,Kappa系数0.315 5)、波谱角分类(分类精度80.282 6,Kappa系数0.770 9)、最小距离分类(分类精度85.462 7%,Kappa系数0.827 7)以及最大似然分类(分类精度86.015 6%,Kappa系数0.835 1)4种方法。针对分类结果常出现的"椒盐"现象,利用形态学算子对SVM(RBF核)分类结果进行了类别集群处理,将分类精度与Kappa系数分别提高至94.758 4%与0.938 0,获得了更接近实况的分类图像。结果表明:ICA结合SVM算法准确率高,是高光谱遥感影像分类的优选方法,且类别集群是优化影像分类的有效方法之一。     

Usefulness of event-related potentials in the assessment of mild cognitive impairment

Background  

The aim of this study was to determine if changes in latencies and amplitudes of the major waves of Auditory Event-Related Potentials (AERP), correlate with memory status of patients with mild cognitive impairment (MCI) and conversion to Alzheimer's disease (AD).     

A semi-supervised learning approach for detection of phishing webpages

This paper proposes a new phishing webpage detection approach based on a kind of semi-supervised learning method-transductive support vector machine (TSVM). Firstly the features of web image are extracted for complementing the disadvantage of phishing detection only based on document object model (DOM); they include gray histogram, color histogram, and spatial relationship between subgraphs. Then the features of sensitive information are examined by using page analysis based on DOM objects. In contrast to the drawback of support vector machine (SVM) algorithm which simply trains classifier by learning little and poor representative labeled samples, this method introduces the TSVM to train classifier that it takes into account the distribution information implicitly embodied in the large quantity of the unlabeled samples, and have better performance than SVM. The experimental results show that the proposed method not only achieves better classification accuracy, but also has strong applicability as the independent method of phishing detection.     

基于小波降噪与支持向量机的恒星光谱识别研究

提出了一种对恒星光谱识别的新方法。 根据恒星光谱数据的特性,我们以支持向量机为核心技术构建光谱识别器。 由于恒星光谱数据通常含有较高的噪声,如果直接进行分类,识别率往往较低。 因此作者首先采用小波分析的方法对原始光谱数据进行降噪预处理,提取光谱的特征,然后馈送到支持向量机完成对光谱数据的最终识别。 利用实际光谱数据(Jacoby, 1984)对所提出的技术进行检测,实验结果表明使用这种小波分析结合支持向量机的技术的识别效果要优于使用支持向量机结合主分量分析降维技术的识别方法。 另外,作者还比较了支持向量机与传统甄别分析的分类性能,对实际及合成光谱进行实验的结果显示了支持向量机的识别正确率不但优于常见的5种甄别分析方法的识别率,而且有较强的泛化能力。     

基于克隆选择支持向量机高光谱遥感影像分类技术

作为支持向量机(support vector machine, SVM)高光谱影像分类的一个重要环节,参数设置的效率和精度直接影响到SVM模型训练效率和最终分类精度。本文首先建立一个SVM高光谱影像分类器,提出了利用免疫克隆选择算法优化的交叉验证进行核函数参数和惩罚因子C的优化选择的方法,得到了一种基于克隆选择优化的支持向量机(clonal selection SVM, CSSVM)高光谱影像分类器。然后将CSSVM与传统的基于网格搜索交叉验证的支持向量机（gird search SVM, GSSVM）分类器进行了对比评价,评价指标包括模型训练时间和分类精度等。最后基于AVIRIS高光谱遥感影像进行了两算法分类对比试验,结果表明：提出的CSSVM测试样本总分类精度超过85.1%和Kappa系数超过0.821 3,影像总分类精度超过81.58%和Kappa系数超过0.772 8,CSSVM与GSSVM的分类精度差别在0.08%以内,Kappa系数差别在0.001以内;CSSVM的模型训练时间是GSSVM的1/6至1/10,得到显著缩短;CSSVM方法在保持传统GSSVM优良分类精度的基础上,极大提高了模型的训练效率。     

A preliminary study of functional abnormalities in aMCI subjects during different episodic memory tasks

Functional magnetic resonance imaging (fMRI) is an important imaging modality to understand the neurodegenerative course of mild cognitive impairment (MCI) and early Alzheimer's disease (AD), because the memory dysfunction may occur before structural degeneration is obvious. In this research, we investigated the functional abnormalities of subjects with amnestic MCI (aMCI) using three episodic memory paradigms that are relevant to different memory domains in both encoding and recognition phases. Both whole-brain analysis and region-of-interest (ROI) analysis of the medial temporal lobes (MTL), which are central to the memory formation and retrieval, were used to compare the efficiency of the different memory paradigms and the functional difference between aMCI subjects and normal control subjects. We also investigated the impact of using different functional activation measurements in ROI analysis. This pilot study could facilitate the use of fMRI activations in the MTL as a marker for early detection and monitoring progression of AD.     

基于高光谱图像技术的苹果粉质化LLE-SVM分类

苹果粉质化程度是衡量其内部品质的一个重要因素,采用了高光谱散射图像技术进行苹果粉质化的无损检测。针对高光谱散射图像数据量大的特点,提出了局部线性嵌入(local linear embedded,LLE)和支持向量机(support vector machine,SVM)相结合的用于检测苹果粉质化的新分类方法。LLE是一种通过局部线性关系的联合来揭示全局非线性结构的非线性降维方法,能有效计算高维输入数据在低维空间的嵌入流形。对降维后的高光谱数据采用SVM进行分类。将LLE-SVM分类方法与传统的SVM分类方法比较,仿真结果表明,对高光谱数据而言,用LLE-SVM得到的训练精度高于单纯使用SVM的训练精度;降维前后,分类器的测试精度变化不大,波动范围不超过5%。LLE-SVM为高光谱散射图像技术进行苹果粉质化无损检测提供了一个有效的分类方法。     

ISG-FHEV等效燃油消耗最小控制策略

针对室内复杂环境下火灾识别准确率会降低的问题,提出了一种改进的粒子群算法优化支持向量机参数进行火灾火焰识别的方法。首先在 颜色空间进行火焰图像分割,对获得的火焰图像进行预处理并提取相关特征量;其次采用PSO算法搜索SVM的最优核参数和惩罚因子,并在PSO算法中加入变异操作和非线性动态调整惯性权值的方法,加快了搜索SVM最优参数的精度和速度;然后将提取的火焰各个特征量作为训练样本输入SVM模型进行训练,并建立参数优化后的SVM分类器模型;最后将待测试样本输入SVM模型进行分类识别。算法的火灾识别准确率达到94.09%,分类效果明显优于其他分类算法。仿真结果表明,改进的PSO优化SVM算法提高了火焰识别的准确率和实时性,算法的自适应性更强,误判率更低。     

Brain Dynamics Altered by Photic Stimulation in Patients with Alzheimer’s Disease and Mild Cognitive Impairment

Individuals with mild cognitive impairment (MCI) are at high risk of developing Alzheimer’s disease (AD). Repetitive photic stimulation (PS) is commonly used in routine electroencephalogram (EEG) examinations for rapid assessment of perceptual functioning. This study aimed to evaluate neural oscillatory responses and nonlinear brain dynamics under the effects of PS in patients with mild AD, moderate AD, severe AD, and MCI, as well as healthy elderly controls (HC). EEG power ratios during PS were estimated as an index of oscillatory responses. Multiscale sample entropy (MSE) was estimated as an index of brain dynamics before, during, and after PS. During PS, EEG harmonic responses were lower and MSE values were higher in the AD subgroups than in HC and MCI groups. PS-induced changes in EEG complexity were less pronounced in the AD subgroups than in HC and MCI groups. Brain dynamics revealed a “transitional change” between MCI and Mild AD. Our findings suggest a deficiency in brain adaptability in AD patients, which hinders their ability to adapt to repetitive perceptual stimulation. This study highlights the importance of combining spectral and nonlinear dynamical analysis when seeking to unravel perceptual functioning and brain adaptability in the various stages of neurodegenerative diseases.     

基于波段子集特征提取的最小二乘支持向量机高光谱图像分类技术

针对高光谱图像分类,文章提出一种基于波段子集最大噪声分量特征提取的最小二乘支持向量机的高光谱图像分类算法.利用高光谱图像的谱间相关性将原始光谱波段划分为若干个波段子集,并在各个子集上采用最大噪声分量方法进行特征提取,将提取的特征合成为分类的组合特征矢量,避免了高光谱图像较强的波段相关性,减少了谱间冗余.并且采用了最小二...     

Longitudinal stability of resting-state networks in normal aging,mild cognitive impairment,and Alzheimer's disease

Test–retest reliability is essential for using resting-state functional magnetic resonance imaging (rs-fMRI) as a potential biomarker for Alzheimer's disease (AD), especially when monitoring longitudinal changes and treatment effects. In addition, test–retest variability itself might represent a feature of AD. Using 3.0 T rs-fMRI data from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database, we examined the long-term (1-year) test–retest reliability of resting-state networks (RSNs) in 31 healthy elderly subjects, 63 patients with mild cognitive impairment (MCI), and 17 patients with AD by applying temporal concatenation group independent component analysis and dual regression. The intraclass correlation coefficient estimates of RSN amplitudes ranged from 0.44 to 0.77 in healthy elderly subjects, from 0.31 to 0.62 in patients with MCI, and from −0.06 to 0.44 in patients with AD. The overall test–retest reliability of RSNs was lower in patients with MCI than in healthy elderly subjects, and was lower in patients with AD than in patients with MCI. The differences in the test–retest reliabilities were due to the RSN amplitudes rather than the RSN shapes. Head motion was not significantly different among the three groups of subjects. The results indicate that the test–retest stability of RSNs generally declines with progression to MCI and AD, mainly due to the RSN amplitudes rather than the RSN shapes. The test–retest instability in MCI and AD may reflect progressive neurofunctional alterations related to the pathology of AD.     

Correlations between microstructural alterations and severity of cognitive deficiency in Alzheimer's disease and mild cognitive impairment: a diffusional kurtosis imaging study

Object

Diffusional kurtosis imaging (DKI), a natural extension of diffusion tensor imaging (DTI), can characterize non-Gaussian diffusion in the brain. We investigated the capability of DKI parameters for detecting microstructural changes in both gray matter (GM) and white matter (WM) in patients with mild cognitive impairment (MCI) and Alzheimer's disease (AD) and sought to determine whether these DKI parameters could serve as imaging biomarkers to indicate the severity of cognitive deficiency.

Materials and Methods

DKI was performed on 18 AD patients and 12 MCI patients. Fractional anisotropy, kurtosis and diffusivity parameters in the temporal, parietal, frontal and occipital lobes were compared between the two groups using Mann–Whitney U test. The correlations between regional DKI parameters and mini-mental state examination (MMSE) score were tested using Pearson's correlation.

Results

In ADs, significantly increased diffusivity and decreased kurtosis parameters were observed in both the GM and WM of the parietal and occipital lobes as compared to MCIs. Significantly decreased fractional anisotropy was also observed in the WM of these lobes in ADs. With the exception of fractional anisotropy and radial kurtosis, all the five other DKI parameters exhibited significant correlations with MMSE score in both GM and WM.

Conclusion

Bearing additional information, the DKI model can provide sensitive imaging biomarkers for assessing the severity of cognitive deficiency in reference to MMSE score and potentially improve early detection and progression monitoring of AD based on characterizing microstructures in both the WM and especially the GM.     

Combining clustering and classification for remote-sensing images using unlabeled data

A joint clustering and classification approach is proposed.This approach exploits unlabeled data for efficient clustering,which is applied in the classification with support vector machine(SVM) in the case of small-size training samples.The proposed method requires no prior information on data labels,and yields better cluster structures.Through cluster assumption and the notions of support vectors,the most confident k cluster centers and data points near the cluster boundaries are labeled and used to train a reliable SVM classifier.Our method gains better estimation of data distributions and mitigates the unrepresentative problem of small-size training samples.The data set collected from Landsat Thematic Mapper(Landsat TM-5) validates the effectiveness of the proposed approach.     

Magnetic resonance spectroscopy and brain volumetry in mild cognitive impairment. A prospective study

ObjectiveTo assess the accuracy of magnetic resonance spectroscopy (1H-MRS) and brain volumetry in mild cognitive impairment (MCI) to predict conversion to probable Alzheimer's disease (AD).MethodsForty-eight patients fulfilling the criteria of amnestic MCI who underwent a conventional magnetic resonance imaging (MRI) followed by MRS, and T1-3D on 1.5 Tesla MR unit. At baseline the patients underwent neuropsychological examination. 1H-MRS of the brain was carried out by exploring the left medial occipital lobe and ventral posterior cingulated cortex (vPCC) using the LCModel software. A high resolution T1-3D sequence was acquired to carry out the volumetric measurement. A cortical and subcortical parcellation strategy was used to obtain the volumes of each area within the brain. The patients were followed up to detect conversion to probable AD.ResultsAfter a 3-year follow-up, 15 (31.2%) patients converted to AD. The myo-inositol in the occipital cortex and glutamate + glutamine (Glx) in the posterior cingulate cortex predicted conversion to probable AD at 46.1% sensitivity and 90.6% specificity. The positive predictive value was 66.7%, and the negative predictive value was 80.6%, with an overall cross-validated classification accuracy of 77.8%. The volume of the third ventricle, the total white matter and entorhinal cortex predict conversion to probable AD at 46.7% sensitivity and 90.9% specificity. The positive predictive value was 70%, and the negative predictive value was 78.9%, with an overall cross-validated classification accuracy of 77.1%. Combining volumetric measures in addition to the MRS measures the prediction to probable AD has a 38.5% sensitivity and 87.5% specificity, with a positive predictive value of 55.6%, a negative predictive value of 77.8% and an overall accuracy of 73.3%.ConclusionEither MRS or brain volumetric measures are markers separately of cognitive decline and may serve as a noninvasive tool to monitor cognitive changes and progression to dementia in patients with amnestic MCI, but the results do not support the routine use in the clinical settings.