基于统计学纹理特征的阿尔兹海默病MR图像研究

阿尔兹海默病（Alzheimer’s disease,AD）是一种老年神经系统退行性疾病。流行病学研究显示,在过去的50年里,AD的发病率增加了4倍,是目前威胁老年健康的重要疾病。对AD的影像学研究目前主要采用对图像上特征线、面积、体积测量的方法,还没有发现对AD具有特异性的影像学指标。本文尝试采用基于统计学理论的灰度共生矩阵、游程长矩阵的纹理分析方法提取AD患者MR图像上感兴趣区的纹理特征参数,通过筛选得到的参数,对AD患者和健康对照组进行分类识别,并对采用不同分类方法得到的识别结果进行比较。研究结果显示对统计学纹理特征参数使用非线性判别分析的分类方法得到的识别率最高达到90．12％。可以预见,此项研究对AD的早期诊断具有积极作用。     

基于肺部PET/CT图像不同纹理特征的K最近邻分类器

目的对PET/CT图像高维纹理参数进行降维,基于不同纹理参数建立肺结节良恶性的K最近邻(K-nearest neighbor,KNN)分类器,探究最佳建模方法,提高分类的准确率。方法采用回顾性研究的方式,收集52例首都医科大学宣武医院核医学科肺结节患者的PET/CT图像,对图像的感兴趣区域基于Contourlet变换提取灰度共生矩阵的纹理参数。对肺结节PET/CT图像的纹理参数首先采用单因素分析的方法,根据ROC曲线下面积筛选纹理参数,再对其进行主成分分析提取主要成分。基于主成分、根据ROC曲线筛选的纹理及原始纹理分别采用K最近邻分类算法建立肺结节良恶性的分类器,通过正确率、灵敏度、特异度、阳性预测值(positive predictive value,PPV)、阴性预测值(negative predictive value,NPV)、ROC曲线下面积(area under curve,AUC)这些指标评价分类效果。结果 PET/CT图像共提取1344个原始纹理参数,经单因素分析后筛选出89个纹理参数,对筛选后的纹理共提取11个主成分。基于主成分、筛选纹理、原始纹理的分类模型正确率分别为0.614、0.579、0.263;AUC分别为0.645、0.610、0.515。结论在主成分纹理、单因素分析筛选的纹理、原始纹理中,基于主成分纹理建立K最近邻分类器的效果最好。     

阿尔茨海默病患者扣带部位磁共振图像纹理特征及性别特点

目的 分析阿尔茨海默（Alzheimer＇s disease,AD）、轻度认知障碍（mild cognitive impairment,MCI）和正常对照者（normal controls,NC）MR图像扣带纹理特征,并按性别进行分组分析,探索纹理特征在疾病早期诊断上的应用.方法 利用灰度共生矩阵和游程长矩阵对52例MR图像（AD14例、MCI20例、NC18例）进行纹理分析,测试组间参数是否显著不同,并用支持向量机方法对在组间具有显著性差异的纹理特征进行分类识别.结果 与NC组相比,AD和MCI组的能量、游程长不均匀度等纹理特征在前扣带和后扣带均存在显著性差异.按性别分组的实验结果显示,除AD组和NC组间存在显著不同外,男性后扣带在MCI与NC及MCI与AD间均存在显著性差异（P〈0.05）,女性前扣带在MCI和NC组间存在显著性差异（P〈0.05）.分类识别结果显示,男性后扣带分类正确率最高,为90%.结论 MR图像纹理特征可以反映扣带病理变化,不同性别MR图像表现不同,有可能为AD的早期诊断提供帮助.     

基于纹理分析的阿尔茨海默症及轻度认知功能障碍的分类研究

目的 利用脑MR图像中胼胝体的三维纹理特征对阿尔茨海默症患者（Alzheimer disease,AD）及轻度认知功能障碍（mild cognitive impairment,MCI）患者进行分类识别,以探索AD早期诊断新途径.方法 选取AD患者、MCI患者及健康对照者各l8例,采用灰度共生矩阵和游程长矩阵提取每位受试者胼胝体部位的三维纹理特征.通过筛选得到的纹理特征参量,利用BP神经网络建立识别模型,对AD患者、MCI患者和健康对照者进行分类识别,并对采用主成分分析、线性判别分析和非线性判别分析3种方法得到的识别结果进行比较.结果 使用神经网络模型的非线性判别分析的分类识别正确率最高.结论 利用三维纹理特征的神经网络模型可分类识别早期AD患者及MCI患者.     

基于磁共振图像海马三维纹理特征的阿尔茨海默病及健康对照的分类研究

利用磁共振(MR)图像对阿尔茨海默病(AD)和健康对照(NC)进行分类识别,比较双侧海马在分类识别中的意义。选取AD患者和NC各25人,采用灰度共生矩阵和游程长矩阵提取每位受试者的海马部位的三维纹理特征。通过筛选得到组间存在显著差异的纹理特征参量,对主成分分析、线性判别分析和非线性判别分析3种方法得到的识别结果进行比较。利用反向传播(BP)神经网络建立识别模型,对AD和NC进行分类识别,采用相关性分析比较双侧海马纹理参数与简明智力状态检查(MMSE)评分的相关性。结果显示使用神经网络模型的非线性判别分析的分类识别正确率最高,右侧海马分类识别的正确率均高于左侧。两侧海马的纹理特征与MMSE评分均具有相关性且右侧海马的相关性系数均大于左侧。利用三维纹理特征的神经网络模型可分类识别AD组和NC组,并且采用右侧海马进行分类识别可能更有利于AD的诊断。     

基于结构磁共振成像海马多特征组合的阿尔茨海默病分类新方法

本文提出了一种利用结构磁共振图像多特征组合的阿尔茨海默病(AD)分类新方法。首先,利用FreeSurfer软件进行海马分割及皮层厚度、体积测量。然后,采用直方图、梯度、灰度共生矩阵及游程长度矩阵提取海马三维纹理特征,选取AD、MCI及NC三组间均具有显著差异的参数,与MMSE评分进行相关性研究。最后,利用极限学习机,对AD、MCI及NC进行分类识别。结果显示,无论左侧还是右侧,纹理特征相比于体积特征可以提供更好的分类结果;纹理、体积和皮层厚度互补的特征参量具有更高的分类识别率,且右侧(100%)分类正确率高于左侧(91.667%)。结果表明三维纹理分析可反映AD及MCI患者海马结构的病理变化,并且结合多特征的分析更能反映AD与MCI的认知障碍实质差别,更有利于临床鉴别诊断。     

基于MR图像女性阿尔茨海默症海马纹理特征研究

目的基于MR图像研究女性阿尔茨海默症患者海马纹理特征的改变。方法取阿尔茨海默症(Alzheimer’s disease,AD)患者组、老年和青年对照组各9例女性样本,提取海马和均值、灰度不均匀性等纹理参数和海马体积参数,测试各组间参数是否显著不同,并测试纹理特征和体积的相关性。结果 AD组与老年对照组海马和均值、灰度不均匀性以及体积显著不同(p0.05),纹理参数与海马体积显著相关(r0.5,p0.01)。老年对照组和青年对照组各参数均未见显著性差异。结论纹理参数可能反映AD脑组织的病理改变,海马增龄性变化与AD病理改变有本质不同。此项研究可能为AD早期诊断提供帮助。     

Alzheimer病MR图像纹理和形态学特征的比较研究

目的 比较MR图像纹理分析和形态学测量方法在鉴别阿尔茨海默病（Alzheimer＇s disease,AD）患者的实际效果,探讨纹理分析技术对AD早期诊断的价值.方法 提取29例AD患者和19例健康对照者（NC）的海马纹理参数,并测量内侧颞叶最窄宽度和海马结构体积等形态学指标,在t检验基础上对纹理参数与形态学指标进行判别分析,然后采用Kappa参数值评价上述两种方法的一致性.结果 AD组与NC组间的和均值、能量等纹理参数均显著不同,右侧海马和均值与形态学测量指标内侧颞叶最窄宽度的判别准确度均为97.9%.经多元逐步判别分析,纹理参数联合判别的准确度为97.9%.纹理分析与形态学测量的Kappa值为0.957（p〈0.001）.结论 MR图像的纹理分析与形态学测量具有较好的一致性,纹理分析可能有助于AD的早期诊断.     

脑部PET图像在阿尔茨海默病早期诊断中的应用

目的本研究使用脑部正电子发射型计算机断层显像(positron emission computed tomography,PET),并且设计了一个3D卷积神经网络(convolutional neural networks,CNN),以实现对阿尔茨海默病(Alzheimer disease,AD)的早期诊断。方法研究数据取自美国国立卫生研究院老年研究所的ADNI(Alzheimer’s Disease Neuroimaging Initiative)数据库,PET图像和磁共振(magnetic resonance,MR)图像均有收集并对数据进行相关预处理。为避免过早的下采样给模型性能带来不利影响,设计了一个3D CNN模型,比较两种不同模态的数据在AD早期诊断中各自的优缺点。结果使用本研究组设计的3D CNN模型在基于PET图像的AD早期诊断实验中,预测准确率、灵敏度、特异度以及曲线下面积(area under curve,AUC)分别达到71.19%、79.29%、61.35%、71.09%。此外,对本研究组的模型与计算机视觉中的经典模型VGG和ResNet使用相同数据进行对比实验,许多评价指标都要更优。结论使用脑部PET图像并结合3D CNN可以更好地利用3D图像的空间位置信息,更有效地提取特征,能对AD早期的病变情况有更准确高效的识别。     

基于PET/CT图像纹理参数的肺结节诊断模型

目的基于PET/CT融合图像纹理参数建立肺结节良恶性诊断模型,提高肺癌的识别率。方法选取宣武医院核医学科经PET/CT检查的52例肺结节患者,收集其PET/CT影像图像及人口学、影像学信息。以Contourlet变换和灰度共生矩阵相结合的方式,对PET/CT图像的感兴趣区域提取纹理参数。基于所提取的纹理参数建立支持向量机模型,得到每个肺结节良恶性判别结果。为了提高模型的诊断效果,将结节边缘、最大摄取值、有晕征等影像学信息也纳入模型,重新建立支持向量机模型。通过灵敏度、特异度、正确率等指标对模型诊断效果进行评价。结果纹理参数肺结节诊断模型的灵敏度、特异度分别为90.7%、93.5%,纹理参数结合影像学信息的肺结节诊断模型的灵敏度、特异度分别为95.7%、100.0%。结论基于PET/CT图像纹理参数建立的支持向量机模型对良恶性肺结节具有较好的鉴别诊断效果。     

Diagnostic utility of hippocampal size and mean diffusivity in amnestic MCI

Hippocampus atrophy is a frequent finding in mild cognitive impairment (MCI), whereas diffusion-tensor-imaging (DTI) has demonstrated its value to detect subtle brain tissue changes in several neuropsychiatric diseases including MCI. To compare the diagnostic accuracy of both methods, high resolution MRI scans for hippocampus volumetry, and co-registered DTI-scans for ROI-based mean diffusivity (MD) and fractional anisotropy (FA) were carried out in 18 patients with amnestic MCI (7 females, age 67.3+/-8.7 years, MMSE 25.2+/-2.2) and 18 controls (age 66.9+/-9.0 years, MMSE 28.7+/-1.0). Diagnostic properties of normalized hippocampus volume (HV) and DTI measures with regard to MCI status were estimated by receiver operating characteristics (ROC) analyses and logistic regression. Parameters of the left hippocampus showed superior predictive power when compared to the right. At a specificity set to 80%, left HV had low sensitivity (50%); left hippocampal MD values revealed superior sensitivity (89%), similar to left hippocampal FA (78%). The results demonstrate higher sensitivity of DTI-derived left hippocampal parameters than volume measures in detecting subtle hippocampal abnormalities related to MCI.     

Hippocampus and entorhinal cortex in mild cognitive impairment and early AD

Magnetic resonance imaging (MRI) has been suggested as a useful tool in early diagnosis of Alzheimer's disease (AD). Based on MRI-derived volumes, we studied the hippocampus and entorhinal cortex (ERC) in 59 controls, 65 individuals with mild cognitive impairment (MCI) and 48 patients with AD. The controls and individuals with MCI were derived from population-based cohorts. Volumes of the hippocampus and ERC were significantly reduced in the following order: control > MCI > AD. Stepwise discriminant function analysis showed that the most efficient overall classification between controls and individuals with MCI subjects was achieved with ERC measurements (65.9%). However, the best overall classification between controls and AD patients (90.7%), and between individuals with MCI and AD patients (82.3%) was achieved with hippocampal volumes. Our results suggest that the ERC atrophy precedes hippocampal atrophy in AD. The ERC volume loss is dominant over the hippocampal volume loss in MCI, whereas more pronounced hippocampal volume loss appears in mild AD.     

Mild cognitive impairment as predictor for Alzheimer's disease in clinical practice: effect of age and diagnostic criteria

BACKGROUND: We investigated whether the predictive accuracy of mild cognitive impairment (MCI) for Alzheimer-type dementia (AD) in a clinical setting is dependent on age and the definition of MCI used. METHOD: Non-demented subjects older than 40 (n=320) who attended a memory clinic of a university hospital were reassessed 5 years later for the presence of AD. MCI was diagnosed according to the criteria of amnestic MCI, mild functional impairment (MFI), ageing-associated cognitive decline (AACD), and age-associated memory impairment (AAMI). The main outcome measure was the area under the curve (AUC) of a receiver operating characteristic (ROC) curve. Analyses were conducted on the entire sample and on subgroups of subjects aged 40-54, 55-69 and 70-85 years. RESULTS: A diagnosis of AD at follow-up was made in 58 subjects. Four of them were in the 40-54 age group, 29 in the 55-69 age group and 25 in the 70-85 age group. The diagnostic accuracy in the entire sample was low to moderately high with AUCs ranging from 0.56 (AACD) to 0.75 (amnestic MCI). A good predictive accuracy with an AUC >0.80 was only observed in subjects aged 70-85 using the criteria of amnestic MCI (AUC=0.84). CONCLUSIONS: The predictive accuracy of MCI for AD is dependent on age and the definition of MCI used. The predictive accuracy is good only for amnestic MCI in subjects 70-85 years. As subjects with prodromal AD are often younger than 70, the usefulness of MCI as predictor of AD in clinical practice is limited.     

Measurements of medial temporal lobe atrophy for prediction of Alzheimer's disease in subjects with mild cognitive impairment

Our aim was to compare the predictive accuracy of 4 different medial temporal lobe measurements for Alzheimer's disease (AD) in subjects with mild cognitive impairment (MCI). Manual hippocampal measurement, automated atlas-based hippocampal measurement, a visual rating scale (MTA-score), and lateral ventricle measurement were compared. Predictive accuracy for AD 2 years after baseline was assessed by receiver operating characteristics analyses with area under the curve as outcome. Annual cognitive decline was assessed by slope analyses up to 5 years after baseline. Correlations with biomarkers in cerebrospinal fluid (CSF) were investigated. Subjects with MCI were selected from the Development of Screening Guidelines and Clinical Criteria for Predementia AD (DESCRIPA) multicenter study (n = 156) and the single-center VU medical center (n = 172). At follow-up, area under the curve was highest for automated atlas-based hippocampal measurement (0.71) and manual hippocampal measurement (0.71), and lower for MTA-score (0.65) and lateral ventricle (0.60). Slope analysis yielded similar results. Hippocampal measurements correlated with CSF total tau and phosphorylated tau, not with beta-amyloid 1–42. MTA-score and lateral ventricle volume correlated with CSF beta-amyloid 1–42. We can conclude that volumetric hippocampal measurements are the best predictors of AD conversion in subjects with MCI.     

阿尔茨海默病患者海马结构的断层影像学研究

目的观察阿尔茨海默病(AD)发病进程中海马结构在断层影像上的形态学改变。方法依据AD发病进程,分别采集正常对照(NC)组、轻度认知损害(MCI)组、AD组各34例共102例受试者脑核磁共振图像,每组男、女各17例。观测海马面积、横径、矢径和颞叶钩回间距、颞角宽度等。分析组间各测量值变化趋势,以及海马面积等相关测量值与各神经评定量表评分的相关性。结果各组海马面积侧别均无统计学差异。各组间测量值比较,AD组海马面积小于NC组及MCI组(P均<0.05);AD组海马横径小于NC组及MCI组,MCI组海马横径小于NC组(P均<0.01);AD组颞叶钩回间距大于NC组及MCI组(P均<0.01),MCI组颞叶钩回间距大于NC组(P<0.05)。海马面积、海马横径与临床痴呆分级量表(CDR)及汉密尔顿抑郁量表(HAMD)评分均呈负相关,与蒙特利尔认知评估量表(MoCA)评分均呈正相关;颞叶钩回间距与神经心理量表评分相关性同海马面积、海马横径相反。结论海马面积与海马横径随AD病情进展逐渐缩小,颞叶钩回间距随AD病情进展逐渐增大;海马结构的改变可损伤其认知功能。