基于MR图像三维纹理特征的阿尔茨海默病和轻度认知障碍的分类

目的 利用三维纹理特征对阿尔茨海默病(AD)患者和轻度认知障碍(MCI)患者进行分类识别,以探索AD早期诊断新途径。方法 对12例早期AD患者(AD组)、12例MCI患者(MCI组)及12名健康对照者(NC组)的MR图像进行三维纹理分析,采用灰度共生矩阵和游程长矩阵提取每位受试者左、右侧海马结构及胼胝体的三维纹理特征,选取三组间存在显著性差异的纹理参数作为特征变量,采用支持向量机(SVM)方法对各组进行分类,利用留一法估算分类准确率。结果 对NC组与MCI组、MCI组与AD组、NC组与AD组进行分类识别的最高准确率分别为79.17%、83.33%、91.67%。结论 利用三维纹理分析可分类识别早期AD患者及MCI患者,有助于AD的早期诊断。     

联机测量灰质皮层体积在阿尔茨海默病诊断中的应用

目的 探讨采用联机软件测量脑灰质体积对阿尔茨海默病（AD）患者的诊断价值。方法 对36例轻度认知障碍（MCI）患者（MCI组）、29例AD患者（AD组）进行MR扫描,正常对照（NC）组为28名认知正常的老年人。获得三维脑结构数据,通过联机软件计算各脑区体积的相对定量值。采用单因素方差分析和非参数秩和检验获得组间差异脑区,并利用ROC曲线和支持向量机（SVM）分析各脑区在组间鉴别诊断中的效能。结果 3组双侧海马体积、左侧和右侧海马体积及双侧扣带回、岛叶、额叶、顶叶、颞叶体积差异均有统计学意义（P均<0.001）,且AD组与MCI组、AD组与NC组间差异均有统计学意义（P均<0.001）。ROC分析显示,鉴别诊断AD组与NC组、MCI组与NC组、AD组与MCI组、（AD组+MCI组）与（NC组）时,最大AUC值分别位于左侧颞叶（0.95）、左侧岛叶（0.69）、右侧扣带回（0.85）、左侧颞叶（0.80）。SVM分析结果提示,AD组与NC组、MCI组与NC组、AD组与MCI组、（AD组+MCI组）与（NC组）中分类准确率最高的区域分别位于双侧海马（89.09%）、左侧岛叶（64.52%）、右侧海马（77.78%）和左侧海马（71.11%）;综合海马、颞叶与岛叶体积鉴别AD/NC的准确率高达94.55%。结论 联机测量反映的脑区改变符合AD病理改变及其发展过程,可以用于临床诊断。     

轻度认知障碍进展为阿尔茨海默病过程中脑灰质体积特征改变的MRI研究

目的 探讨轻度认知障碍(MCI)患者进展为阿尔茨海默病(AD)过程中,脑灰质(包括皮层和灰质核团)萎缩发生的部位及其进展趋势。方法 自ADNI数据网站下载15例2年内进展为AD的MCI患者和14名健康老年人的MR结构图像和MMSE评分结果。15例进展为AD的MCI患者基线时间(随访开始时间)为MCI组,进展为AD时作为AD组。14名健康老年人为对照组(基线时间为NC0组,2年后为NC1组)。利用SPM 8对MCI组、AD组和对照组的全脑灰质体积进行基于体素的统计学比较。结果 与NC0组比较,MCI组和AD组双侧内侧颞叶灰质体积萎缩,且AD组左侧尾状核头部、左侧丘脑前部体积萎缩;NC1组左侧海马头部、左侧中央后回灰质体积萎缩。结论 MCI进展为AD过程中,脑灰质萎缩主要发生在与记忆相关的内侧颞叶,全脑灰质萎缩存在左侧半球严重于右侧半球的发展趋势,在边缘系统内部呈现自海马向杏仁核、丘脑的蔓延趋势。     

阿尔茨海默病及轻度认知损伤患者PET与MRI分析

目的 探讨PET葡萄糖代谢成像与MR结构成像诊断阿尔茨海默病（AD）与轻度认知损伤（MCI）的临床价值。方法 收集AD患者18例（AD组）、MCI患者6例（MCI组）,其中AD患者包括11例中重度AD） 中重度AD组）及7例轻度AD） 轻度AD组）,另招募10名健康志愿者（对照组）,同期进行PET与MR结构成像,通过视觉评价与定量分析法观察脑内放射性分布及海马萎缩情况。结果 所有AD患者（18/18,100%）均可见脑内特定区域葡萄糖代谢减低,其中11例中重度AD患者均同时伴有海马萎缩,7例轻度AD患者中3例可见海马萎缩;MCI患者中,5例（5/6,83.33%）未见海马萎缩,但其中2例可见葡萄糖代谢减低。对照组（10/10,100%）均未见海马萎缩,其中2例可见轻度脑萎缩,FDG分布对称性轻度减低。结论 PET及MRI均可用于诊断AD与MCI,但各有侧重,二者联合应用有利于进一步提高对AD的诊断能力。     

多参数结构脑网络融合技术诊断双相障碍

目的 基于node2vec算法和连续词袋(CBOW)模型建立多参数融合网络模型,评价其诊断双相障碍(BD)的价值。方法 纳入48例BD患者(BD组)和58名健康人[正常对照(NC)组],以node2vec算法挖掘节点隐含关系特征,利用CBOW模型将高维多参数网络转换为低维节点嵌入向量;拼接多参数节点嵌入向量,以余弦相似度重构融合网络,并划分为左、右2个半球网络。分析组间全局特征和节点度属性差异,筛选分类特征;以支持向量机(SVM)建立BD诊断模型,估算准确率。结果 相比NC组,BD组多数全局特征显著改变(P均＜0.001),额叶、顶叶和边缘系统等区域多脑区节点度显著异常。以左、右半球合并特征构建的融合网络诊断BD准确率达99.10%,显著高于单一参数网络分类(93.55%~94.45%)。结论 多参数融合网络模型能有效提取脑网络特征并辅助诊断BD。     

早期相11C-PIB作为神经功能指标：与18F-FDG比较分析

目的 评价早期相动态¹¹C-PIB可否提供等价于¹⁸F-FDG的神经功能信息。方法 对17名正常对照（NC组）、11例轻度认知障碍（MCI）患者（MCI组）及15例阿尔茨海默病（AD）患者（AD组）行¹⁸F-FDG和¹¹C-PIB双示踪剂检查,通过训练集（3名NC,3例MCI及3例AD）及测试集（其余受试者）数据提取标准摄取值比（SUVR）,计算与¹⁸F-FDG具有最大相关的早期相¹¹C-PIB时间窗,生成灌注¹¹C-PIB图像（¹¹C-pPIB）。选取最后10 min ¹¹C-PIB数据,评价淀粉样斑块沉积情况（¹¹C-aPIB）,比较¹⁸F-FDG、¹¹C-pPIB及¹¹C-aPIB图像在3组受试人群的放射性分布的差异。结果 AD组14例、MCI组 11例、NC组15名纳入分析。给药后近7 min（开始时间1.33 min,持续至8 min）的早期相¹¹C-pPIB与¹⁸F-FDG在训练集（R=0.8680±0.0339）及测试集（R=0.8737±0.0277）均存在强烈相关。¹¹C-pPIB与¹⁸F-FDG在3组中呈现相似的放射性分布模式,但与¹¹C-aPIB放射性分布明显不同。结论 早期相¹¹C-pPIB可通过反映局部脑血流信息而提供与¹⁸F-FDG相似的神经功能信息。     

磁敏感加权成像相位值评估阿尔茨海默病脑内铁沉积

目的 采用SWI技术观察阿尔茨海默病(AD)患者与正常对照组脑内铁含量的差异,并探讨相位值与MMSE评分的相关性。 方法 对23例AD患者(AD组)及18名健康老年人(NC组)进行垂直于海马长轴的斜冠状位SWI,扫描范围自双侧颞极至齿状核。在所得相位图上测量各脑区的相位值,并进行组间统计学分析,比较AD组各脑区相位值与MMSE评分的相关性。 结果 与NC组相比,AD组双侧海马、苍白球、尾状核、黑质、右侧额叶皮质及左侧壳核相位值降低,差异有统计学意义(P<0.05)。AD组左侧壳核的相位值与MMSE评分具有最高的相关性,相关系数为0.53,左侧海马的相位值与MMSE评分相关系数为0.44。 结论 相位值可作为评价AD患者脑内铁沉积异常的敏感而有效的手段。左侧壳核相位值与AD疾病进展关系密切。     

MRI分析阿尔茨海默病进程中海马头、体、尾部体积改变

目的 探讨阿尔茨海默病（AD）进程中,海马头、体、尾部形态学改变。方法 对AD、轻度认知障碍（MCI）患者各30例（AD组、MCI组）及30名正常老年人（正常对照组）行颅脑MRI扫描。基于MRI扫描图像将海马头、体、尾部进行分段,并测量其体积。比较AD组、MCI组、正常对照组海马体积整体差异及头、体、尾部体积差异。分析海马体积与各神经评定量表评分的相关性。结果 3组中,左侧海马总体积及头、体、尾部体积均大于右侧（P均<0.05）。3组间左、右海马总体积比较,AD组小于正常对照组（P均<0.01）及MCI组（P均<0.05）,MCI组小于正常对照组（P均<0.05）。与正常对照组比较,AD组左、右海马头、体、尾部体积均减小（P均<0.05）,MCI组左海马头、体部及右海马头部体积减小（P均<0.05）。AD组左、右海马头、体部体积均小于MCI组（P均<0.05）。简易智能状态检查表（MMSE）评分与双侧海马头、体、尾部体积及总体积均呈正相关。除左海马尾部外,双侧海马头、体、尾部体积及总体积均与日常生活能力量表（ADL）评分及临床痴呆分级量表（CDR）评分呈负相关,均与蒙特利尔认知评估量表（MoCA）评分呈正相关。结论 AD患者双侧海马体积明显缩小,MCI患者海马体部、尾部萎缩不明显,但海马头部体积明显缩小。     

轻度认知功能障碍患者大脑fMRI网络小世界特性

目的 应用静息态fMRI观察轻度认知功能障碍（MCI）患者大脑功能网络是否具有小世界特性。方法 采集13例MCI患者（MCI组）和17名正常老年人（NC组）的大脑静息态BOLD-fMRI数据。采用SPM5软件对图像进行预处理,将大脑分割为90个区域,计算90个区域间的相关系数。以矩阵稀疏度（Sparsity）为阈值,将相关矩阵转换为网络。计算网络的聚类系数（C）和平均路径长度（L）,若满足γ=C/C_rand>1且λ=L/L_rand≈1（rand代表相应随机网络）,为则认为大脑功能网络具有小世界特性。采用双样本t检验比较MCI组与NC组大脑功能网络小世界参数的差异。结果 在0.10~0.40阈值范围内,MCI组和NC组均符合γ>1且λ≈1。MCI组γ和δ均大于NC组,且在0.10≤Sparsity≤0.18时差异有统计学意义（P<0.05）;MCI组λ在各阈值处均小于NC组,在Sparsity=0.18、0.28和0.32处差异有统计学意义（P<0.05）。结论 MCI患者大脑fMRI网络具有小世界特性,且与正常老年人相比有所增强。     

基于DTI数据分析轻度认知功能障碍患者脑结构网络

目的 基于DTI数据构建大脑结构网络观察轻度认知障碍（MCI）患者脑结构网络是否具有小世界属性及其相关特征参数变化。方法 对26例MCI患者（MCI组）和27名正常老年人（NC组）采集大脑DTI数据，以PANDA软件对图像进行预处理，以自动解剖标定（AAL）模板将大脑皮质划分为90个区域，采用确定性纤维示踪算法示踪纤维，以每对脑区间纤维束数目（FN）为阈值T，构建白质纤维连接网络。设定T的取值范围为1~5，步长为1，分别计算不同T值时脑结构网络特征参数，包括平均路径长度（L_P）、聚类系数（C_P）、全局效率（E_global）及局部效率（E_local），若满足γ=C/C_rand>1且λ=L/L_rand≈1（rand代表相应随机网络）或δ=γ/λ>1，则脑结构网络具有小世界特性。比较不同T值时2组大脑结构网络特征参数的差异。结果 1≤T≤5时，MCI组和NC组均符合γ>1且λ≈1；MCI组L_P均高于NC组（P均<0.05）；MCI组C_p与NC组差异均无统计学意义（P均>0.05）。1≤T≤4时，MCI组E_global均低于NC组（P均<0.05）；T=2时，MCI组E_local值低于NC组（P<0.05）。结论 MCI患者大脑结构网络具有小世界属性，但其小世界特性受损。     

动脉自旋标记技术定量分析阿尔茨海默病不同阶段脑血流量

目的基于三维动脉自旋标记(3D-ASL)技术定量分析阿尔兹海默病(AD)不同进展阶段脑血流量(CBF)改变,评价其鉴别效能。方法针对22例AD(AD组)、22例轻度认知功能障碍(MCI组)、25例主观认知功能下降(SCD组)患者和25名正常志愿者(NC组)采集头部3D T1WI和3D-ASL图像,经后处理获得双侧苍白球(GP)、壳核(PU)、尾状核(CA)、海马(HP)、丘脑(TH)、额叶皮层(FC)、顶叶皮层(PC)和枕叶皮质(OC)的CBF值。比较各组间CBF值差异,观察其与年龄、简易精神状态量表(MMSE)和蒙特利尔认知评估量表(MoCA)评分的相关性;以ROC曲线评价各脑区CBF值鉴别AD不同阶段的效能。结果AD组及MCI组除OC外各脑区CBF值均较NC组减低(P均<0.01);SCD组CA、PU及TH的CBF值均较NC组增高(P均<0.05)。AD组及MCI组HP的CBF值与MoCA评分均呈正相关(r=0.584、0.595,P均<0.01)。HP、TH、FC、PC、OC的CBF值鉴别AD不同进展阶段的AUC均较高。结论AD及MCI存在广泛脑灌注减少;SCD部分脑区存在灌注代偿;HP、TH、FC、PC、OC的CBF值对诊断及鉴别不同阶段AD有一定价值。     

Combining MRI and CSF measures for classification of Alzheimer's disease and prediction of mild cognitive impairment conversion

The suggested revision of the NINCDS-ADRDA criterion for the diagnosis of Alzheimer's disease (AD) includes at least one abnormal biomarker among magnetic resonance imaging (MRI), positron emission tomography (PET) and cerebrospinal fluid (CSF). We aimed to investigate if the combination of baseline MRI and CSF could enhance the classification of AD compared to using either alone and predict mild cognitive impairment (MCI) conversion at multiple future time points. 369 subjects from the Alzheimer's disease Neuroimaging Initiative (ADNI) were included in the study (AD=96, MCI=162 and CTL=111). Freesurfer was used to generate regional subcortical volumes and cortical thickness measures. A total of 60 variables were used for orthogonal partial least squares to latent structures (OPLS) multivariate analysis (57 MRI measures and 3 CSF measures: Aβ(42), t-tau and p-tau). Combining MRI and CSF gave the best results for distinguishing AD vs. CTL. We found an accuracy of 91.8% for the combined model at baseline compared to 81.6% for CSF measures and 87.0% for MRI measures alone. The combined model also gave the best accuracy when distinguishing between MCI vs. CTL (77.6%) at baseline. MCI subjects who converted to AD by 12 and 18month follow-up were accurately predicted at baseline using an AD vs. CTL model (82.9% and 86.4% respectively), with lower prediction accuracies for those MCI subjects converting by 24 and 36month follow up (75.4% and 68.0% respectively). The overall prediction accuracies for converters and non-converters ranged from 58.6% to 66.4% at different time points. Combining MRI and CSF measures in a multivariate model at baseline gave better accuracy for discriminating between AD and CTL, between MCI and CTL and for predicting future conversion from MCI to AD, than using either MRI or CSF separately.     

Multimodal classification of Alzheimer's disease and mild cognitive impairment

Effective and accurate diagnosis of Alzheimer's disease (AD), as well as its prodromal stage (i.e., mild cognitive impairment (MCI)), has attracted more and more attention recently. So far, multiple biomarkers have been shown to be sensitive to the diagnosis of AD and MCI, i.e., structural MR imaging (MRI) for brain atrophy measurement, functional imaging (e.g., FDG-PET) for hypometabolism quantification, and cerebrospinal fluid (CSF) for quantification of specific proteins. However, most existing research focuses on only a single modality of biomarkers for diagnosis of AD and MCI, although recent studies have shown that different biomarkers may provide complementary information for the diagnosis of AD and MCI. In this paper, we propose to combine three modalities of biomarkers, i.e., MRI, FDG-PET, and CSF biomarkers, to discriminate between AD (or MCI) and healthy controls, using a kernel combination method. Specifically, ADNI baseline MRI, FDG-PET, and CSF data from 51AD patients, 99 MCI patients (including 43 MCI converters who had converted to AD within 18 months and 56 MCI non-converters who had not converted to AD within 18 months), and 52 healthy controls are used for development and validation of our proposed multimodal classification method. In particular, for each MR or FDG-PET image, 93 volumetric features are extracted from the 93 regions of interest (ROIs), automatically labeled by an atlas warping algorithm. For CSF biomarkers, their original values are directly used as features. Then, a linear support vector machine (SVM) is adopted to evaluate the classification accuracy, using a 10-fold cross-validation. As a result, for classifying AD from healthy controls, we achieve a classification accuracy of 93.2% (with a sensitivity of 93% and a specificity of 93.3%) when combining all three modalities of biomarkers, and only 86.5% when using even the best individual modality of biomarkers. Similarly, for classifying MCI from healthy controls, we achieve a classification accuracy of 76.4% (with a sensitivity of 81.8% and a specificity of 66%) for our combined method, and only 72% even using the best individual modality of biomarkers. Further analysis on MCI sensitivity of our combined method indicates that 91.5% of MCI converters and 73.4% of MCI non-converters are correctly classified. Moreover, we also evaluate the classification performance when employing a feature selection method to select the most discriminative MR and FDG-PET features. Again, our combined method shows considerably better performance, compared to the case of using an individual modality of biomarkers.     

Multi-modal neuroimaging feature selection with consistent metric constraint for diagnosis of Alzheimer's disease

The accurate diagnosis of Alzheimer's disease (AD) and its early stage, e.g., mild cognitive impairment (MCI), is essential for timely treatment or possible intervention to slow down AD progression. Recent studies have demonstrated that multiple neuroimaging and biological measures contain complementary information for diagnosis and prognosis. Therefore, information fusion strategies with multi-modal neuroimaging data, such as voxel-based measures extracted from structural MRI (VBM-MRI) and fluorodeoxyglucose positron emission tomography (FDG-PET), have shown their effectiveness for AD diagnosis. However, most existing methods are proposed to simply integrate the multi-modal data, but do not make full use of structure information across the different modalities. In this paper, we propose a novel multi-modal neuroimaging feature selection method with consistent metric constraint (MFCC) for AD analysis. First, the similarity is calculated for each modality (i.e. VBM-MRI or FDG-PET) individually by random forest strategy, which can extract pairwise similarity measures for multiple modalities. Then the group sparsity regularization term and the sample similarity constraint regularization term are used to constrain the objective function to conduct feature selection from multiple modalities. Finally, the multi-kernel support vector machine (MK-SVM) is used to fuse the features selected from different models for final classification. The experimental results on the Alzheimer's Disease Neuroimaging Initiative (ADNI) show that the proposed method has better classification performance than the start-of-the-art multimodality-based methods. Specifically, we achieved higher accuracy and area under the curve (AUC) for AD versus normal controls (NC), MCI versus NC, and MCI converters (MCI-C) versus MCI non-converters (MCI-NC) on ADNI datasets. Therefore, the proposed model not only outperforms the traditional method in terms of AD/MCI classification, but also discovers the characteristics associated with the disease, demonstrating its promise for improving disease-related mechanistic understanding.     

AD与MCI病人情景记忆编码及提取加工变化

目的观察阿尔茨海默病（AD）及轻度认知障碍（MCI）病人情景记忆（EM）编码和提取加工的变化。方法 AD组病人55例,MCI组病人86例,正常对照组（NC组）95例。应用E-prime软件进行情景记忆编码和提取测试,记录编码和提取成绩及反应时。结果 AD组和MCI组编码正确率均低于NC组,差异有显著性（F=22.3,q=2.9、6.6,P〈0.05）,且AD组低于MCI组,差异有显著性（q=3.9,P〈0.05）;AD组和MCI组提取正确率均低于NC组,差异有显著性（F=24.6,q=2.4、5.0,P〈0.05）,且AD组低于MCI组,差异有显著性（q=2.4,P〈0.05）;AD组和MCI组编码反应时较NC组明显延延长,差异均有显著性（F=23.1,q=3.5、6.8,P〈0.05）,且AD组较MCI组明显延长,差异有显著性（q=3.7,P〈0.05）;AD组和MCI组提取反应时较NC组明显延长,差异均有显著性（F=12.8,q=3.3、6.6,P〈0.05）,且AD组较MCI组明显延长,差异有显著性（q=3.3,P〈0.05）。结论AD和MCI病人情景记忆编码和提取加工出现损伤,且AD病人较MCI病人损伤明显。     

Multidimensional classification of hippocampal shape features discriminates Alzheimer's disease and mild cognitive impairment from normal aging

We describe a new method to automatically discriminate between patients with Alzheimer's disease (AD) or mild cognitive impairment (MCI) and elderly controls, based on multidimensional classification of hippocampal shape features. This approach uses spherical harmonics (SPHARM) coefficients to model the shape of the hippocampi, which are segmented from magnetic resonance images (MRI) using a fully automatic method that we previously developed. SPHARM coefficients are used as features in a classification procedure based on support vector machines (SVM). The most relevant features for classification are selected using a bagging strategy. We evaluate the accuracy of our method in a group of 23 patients with AD (10 males, 13 females, age ± standard-deviation (SD) = 73 ± 6 years, mini-mental score (MMS) = 24.4 ± 2.8), 23 patients with amnestic MCI (10 males, 13 females, age ± SD = 74 ± 8 years, MMS = 27.3 ± 1.4) and 25 elderly healthy controls (13 males, 12 females, age ± SD = 64 ± 8 years), using leave-one-out cross-validation. For AD vs controls, we obtain a correct classification rate of 94%, a sensitivity of 96%, and a specificity of 92%. For MCI vs controls, we obtain a classification rate of 83%, a sensitivity of 83%, and a specificity of 84%. This accuracy is superior to that of hippocampal volumetry and is comparable to recently published SVM-based whole-brain classification methods, which relied on a different strategy. This new method may become a useful tool to assist in the diagnosis of Alzheimer's disease.