Spectral and complexity analysis of scalp EEG characteristics for mild cognitive impairment and early Alzheimer's disease

Amnestic mild cognitive impairment (aMCI) often is an early stage of Alzheimer's disease (AD). MCI is characterized by cognitive decline departing from normal cognitive aging but that does not significantly interfere with daily activities. This study explores the potential of scalp EEG for early detection of alterations from cognitively normal status of older adults signifying MCI and AD. Resting 32-channel EEG records from 48 age-matched participants (mean age 75.7 years)—15 normal controls (NC), 16 early MCI, and 17 early stage AD—are examined. Regional spectral and complexity features are computed and used in a support vector machine model to discriminate between groups. Analyses based on three-way classifications demonstrate overall discrimination accuracies of 83.3%, 85.4%, and 79.2% for resting eyes open, counting eyes closed, and resting eyes closed protocols, respectively. These results demonstrate the great promise for scalp EEG spectral and complexity features as noninvasive biomarkers for detection of MCI and early AD.     

F-FDG PET imaging analysis for computer aided Alzheimer’s diagnosis

Finding sensitive and appropriate technologies for non-invasive observation and early detection of Alzheimer’s disease (AD) is of fundamental importance to develop early treatments. In this work we develop a fully automatic computer aided diagnosis (CAD) system for high-dimensional pattern classification of baseline ¹⁸F-FDG PET scans from Alzheimer’s disease neuroimaging initiative (ADNI) participants. Image projection as feature space dimension reduction technique is combined with an eigenimage based decomposition for feature extraction, and support vector machine (SVM) is used to manage the classification task. A two folded objective is achieved by reaching relevant classification performance complemented with an image analysis support for final decision making. A 88.24% accuracy in identifying mild AD, with 88.64% specificity, and 87.70% sensitivity is obtained. This method also allows the identification of characteristic AD patterns in mild cognitive impairment (MCI) subjects.     

Re-transfer learning and multi-modal learning assisted early diagnosis of Alzheimer’s disease

Nowadays more and more elderly people are suffering from Alzheimer’s disease (AD). Finely recognizing mild cognitive impairment (MCI) in early stage of the symptom is vital for AD therapy. However, brain image samples are relatively scarce, meanwhile have multiple modalities, which makes finely classifying brain images by computers extremely difficult. This paper proposes a fine-grained brain image classification approach for diagnosing Alzheimer’s disease, with re-transfer learning and multi-modal learning. First of all, an end-to-end deep neural network classifier CNN4AD is designed to finely classify diffusion tensor image (DTI) into four categories. And according to the characteristics of multi-modal brain image dataset, the re-transfer learning method is proposed based on transfer learning and multi-modal learning theories. Experimental results show that the proposed approach obtain higher accuracy with less labeled training samples. This could help doctors diagnose Alzheimer’s disease more timely and accurately.

     

Browsing a document collection represented in two- and three-dimensional virtual information space

This paper reports a study of information retrieval performance using an interface in which documents were represented by objects in a virtual environment. Spatial location was determined by semantic content, with inter-object distance representing semantic similarity of documents. The quality of spatial-semantic mapping was manipulated as was the number of dimensions (two versus three) in which document nodes were arranged. Participants were required to browse the information space and identify all documents relevant to a specified topic. Results indicated that participants were able to use three-dimensional spatial mapping of semantic information to facilitate task performance, with performance being better when the quality of the mapping was higher. Strategy differences were identified, with participants adopting a more ‘exhaustive’ approach when searching two-dimensional node arrangements, and a more ‘focused’ approach for three-dimensional arrangements. Cognitive ability was not strongly associated with task performance, but participants of relatively lower cognitive ability tended to out-perform those of higher cognitive ability in three-dimensional conditions. Possible reasons for these findings are discussed.     

Evaluation of customer impressions using virtual prototypes in the internet environment

This study aims to investigate a cost effective and efficient way of analyzing customer impressions on design alternatives by incorporating the benefits of virtual prototyping into the Internet-based experimental environment. It is hypothesized that the results of the Internet-based experiment using the images of virtual prototypes are comparable to those of the virtual reality-based environment using virtual prototypes. Two experiments were conducted. In the virtual reality environment, participants were employed to evaluate virtual prototypes while in the Internet environment participants evaluated images of the same virtual prototypes from their own places. For each experiment, 16 male participants were employed to evaluate 32 different virtual prototypes generated from the combination of 17 design elements of automobile interior. The results of the experiments indicated that there were no significant differences between the two experimental methods while the Internet environment-based method could save considerable time and efforts for experimentation. This study concludes that the Internet-based evaluation method using the images of virtual prototypes could be a cost effective and efficient way of analyzing customer impressions on design alternatives.

Relevance to Industry

This study showed that the results of the Internet-based evaluation method using the images of virtual prototypes are comparable to those of the virtual reality-based method using real virtual prototypes. The Internet-based evaluation method could be used as a cost effective and efficient way of collecting and analyzing various customers’ impressions on design alternatives at the early stage of product development process.     

Virtually old: Embodied perspective taking and the reduction of ageism under threat

Intergroup threat harms attitudes toward the outgroup, leading to greater levels of prejudice and outgroup derogation (Rothgerber, 1997). Two experiments were conducted to examine (1) if perspective taking mitigates the negative influence of threat on explicit and implicit intergenerational attitudes and, if so, (2) whether this buffering effect would be stronger for participants who embodied an elderly person in an immersive virtual environment (IVE) compared to those who engaged in a traditional perspective taking exercise via mental simulation (MS). When intergroup threat was presented without intergroup contact (Study 1), the negative effect of threat on ageism dissipated when participants engaged in a perspective taking exercise. Differential effects were found depending on the perspective taking medium. However, when participants were exposed to a concrete and experiential intergroup threat (Study 2), neither modality of perspective taking (IVE and MS) buffered negative intergenerational attitudes.     

Relationship between tau,neuroinflammation and atrophy in Alzheimer's disease: The NIMROD study

In addition to beta-amyloid accumulation, misfolded tau and activated microglia are also present in Alzheimer's disease (AD). It is important to study the relationship amongst these pathologies in vivo and their effects on the cognitive deficits for developing effective trails and future therapeutic or preventive strategies for AD. To investigate the relationships amongst different pathologies in AD, in particular how they interact resulting in cognitive impairments, we conducted a study of sixty-six subjects (15 AD, 24 Mild Cognitive Impairment (MCI) and 27 similarly aged healthy controls), who underwent standardised clinical and neuropsychological assessments followed by dynamic PET using [¹⁸F]AV1451 (tau) and [¹¹C]PK11195 (activated microglia) and multimodal 3T MRI. MCI patients also underwent [¹¹C]PIB (beta-amyloid) PET. We compared regional PET binding and grey matter atrophy amongst AD, amyloid positive MCI and controls, as well as their spatial distribution across different brain areas. We also applied a mediation analysis to infer the direct and indirect effects of tau, neuroinflammation and grey matter atrophy on cognitive functioning. We found increased [¹⁸F]AV1451 and [¹¹C]PK11195 binding as well as grey matter atrophy in AD, with a strong spatial overlap amongst these AD related biomarkers suggesting them interacting with each other. We demonstrated that both tau ([¹⁸F]AV1451) and neuroinflammation ([¹¹C]PK11195) have significant effects on cognition however their effects were fully mediated by grey matter atrophy. No mediation effect between tau and neuroinflammation were found with respect to cognition. In conclusion, grey matter atrophy not only spatially overlapped with tau and microglia activity in AD, but also mediate them in affecting cognitive impairments. The mediation analysis enabled data fusion across multiple imaging modalities (PET and MRI) and multiple PET tracers. Our results have significant implications for trials targeting tau and inflammation, and future therapeutic or preventive strategies for AD.     

Role of cognitive and functional performance in the interactions between elderly people with cognitive decline and an avatar on TV

The complexity of new information technologies (IT) may limit the access of elderly people to the information society, exacerbating what is known as “the digital divide,” as they appear to be too challenging for elderly citizens regardless of the integrity of their cognitive status. This study is an attempt to clarify how some cognitive functions (such as attention or verbal memory) may determine the interaction of cognitively impaired elderly people with technology. Twenty participants ranging from mild cognitive impairment to moderate Alzheimer’s disease were assessed by means of a neuropsychological and functional battery and were asked to follow simple commands from an avatar appearing on a TV by means of a remote control, such as asking the participant to confirm their presence or to respond Yes/No to a proposal to see a TV program. The number of correct answers and command repetitions required for the user to respond were registered. The results show that participants with a better cognitive and functional state in specific tests show a significantly better performance in the TV task. The derived conclusion is that neuropsychological assessment may be used as a useful complementary tool for assistive technology developers in the adaptation of IT to the elderly with different cognitive and functional profiles. Further studies with larger samples are required to determine to what extent cognitive functions can actually predict older users’ interaction with technology.     

A novel method for the classification of Alzheimer's disease from normal controls using magnetic resonance imaging

Alzheimer's disease (AD) is the most prevalent form of dementia. Although fewer people, who suffer from AD are correctly and promptly diagnosed, due to a lack of knowledge of its cause and unavailability of treatment, AD is more manageable if the symptoms of mild cognitive impairment (MCI) are in an early stage. In recent years, computer‐aided diagnosis has been widely used for the diagnosis of AD. The main motive of this paper is to improve the classification and prediction accuracy of AD. In this paper, a novel approach is developed to classify MCI, normal control (NC), and AD using structural magnetic resonance imaging (sMRI) from the Alzheimer's disease Neuroimaging Initiative (ADNI) dataset (50 AD, 50 NC, 50 MCI subjects). FreeSurfer is used to process these MRI data and obtain cortical features such as volume, surface area, thickness, white matter (WM), and intrinsic curvature of the brain regions. These features are modified by normalizing each cortical region's features using the absolute maximum value of that region's features from all subjects in each group of MCI, NC, and AD independently. A total of 420 features are obtained. To address the curse of dimensionality, the obtained features are reduced to 30 features using a sequential feature selection technique. Three classifiers, namely the twin support vector machine (TSVM), least squares TSVM (LSTSVM), and robust energy‐based least squares TSVM (RELS‐TSVM), are used to evaluate the classification accuracy from the obtained features. Five‐fold and 10‐fold cross‐validation are used to validate the proposed method. Experimental results show an accuracy of 100% for the studied database. The proposed approach is innovative due to its higher classification accuracy compared to methods in the existing literature.     

用于阿尔茨海默病诊断的权值分布特征学习

针对当前基于机器学习的早期阿尔茨海默病（AD）诊断中有标记训练样本不足的问题,提出一种基于多模态特征数据的权值分布稀疏特征学习方法,并将其应用于早期阿尔茨海默病的诊断.具体来说,该诊断方法主要包括两大模块：基于权值分布的Lasso特征选择模型（WDL）和大间隔分布分类机模型（LDM）.首先,为了获取多模态特征之间的数据分布信息,对传统Lasso模型进行改进,引入权值分布正则化项,从而构建出基于权值分布的Lasso特征选择模型;然后,为了有效地利用多模态特征之间的数据分布信息,以保持多模态特征之间的互补性,直接采用大间隔分布学习算法训练分类器.选取国际阿尔茨海默症数据库（ADNI）中202个多模态特征的被试者样本进行实验,分类AD最高平均精度为97.5%,分类轻度认知功能障碍（MCI）最高平均精度为83.1%,分类轻度认知功能障碍转化为AD（pMCI）最高平均精度为84.8%.实验结果表明,所提WDL特征学习方法可从串联的多模态特征学到性能更优的特征子集,并能根据权值分布获取多模态特征之间的数据分布信息,从而提高早期阿尔茨海默病诊断的性能.     

多模态网络融合在轻度认知障碍分类中的应用

针对早期轻度认知障碍（MCI）根据医学诊断认知量表评估极有可能无法判断的问题,提出了一种多模态网络融合的MCI辅助诊断分类方法。基于图论的复杂网络分析方法在神经影像领域的应用已得到广泛认可,但采用不同模态的成像技术研究脑部疾病对大脑网络拓扑结构属性的影响会产生不同结果。首先,使用弥散张量成像（DTI）与静息态功能磁共振成像（rs-fMRI）数据构建大脑结构和功能连接的融合网络。然后,融合网络的拓扑属性被施以单因素方差分析（ANOVA）,选择具有显著差异的属性作为分类特征。最后,利用支持向量机（SVM）留一法交叉验证对健康组和MCI组分类,估算准确率。实验结果表明,所提方法的分类结果准确率达到94.44%,相较单一模态数据法的分类结果有明显提高。所提方法诊断出的MCI患者在扣带回、颞上回以及额叶和顶叶部分区域等许多脑区表现出显著异常,与已有研究结果基本一致。     

A Comparative Study of Two Wayfinding Aids With Simulated Driving Tasks—GPS and a Dual-Scale Exploration Aid

Global Positioning System (GPS) is currently the most often used wayfinding aid for driving. Yet GPS is originally designed to provide a driving guide rather than to help users gain spatial knowledge. Accordingly, GPS might be less usable in situations where spatial knowledge is required. This study experimentally compared two wayfinding aids using simulated driving tasks in a virtual environment: a simulated GPS and a dual-scale exploration aid (DSEA). The DSEA, which provides two levels of details—both detailed and contextual information—was proposed to support participants in finding and selecting routes by themselves. The results show that although DSEA was less helpful in leading participants to their destination and corresponded to more turning errors in simulated driving, it was more useful for the corresponding participants to establish spatial awareness and a cognitive map. The influence of participants' spatial ability test score on wayfinding performance was measured and discussed. The proposed DSEA design and experimental results show some indications for designing new wayfinding aids aimed at reducing wayfinding errors and constructing cognitive maps while still providing easy navigation.     

Construction of cognitive maps of unknown spaces using a multi-sensory virtual environment for people who are blind

Most of the information used by people for the cognitive mapping of spaces is gathered through the visual channel. People who are blind lack the ability to collect the required visual information either in advance or in situ. This study was based on the assumption that the acquisition of appropriate spatial information (perceptual and conceptual) through compensatory sensorial channels (e.g., haptic) within a virtual environment simulating a real target space may assist people who are blind in their anticipatory exploration and cognitive mapping of the unknown space. The two main goals of the study were: (a) the development of a haptic-based multi-sensory virtual environment enabling the exploration of an unknown space and (b) the study of the cognitive mapping process of the space by people who are blind working with the multi-sensory virtual environment. The findings suggest strong evidence that the work within the multi-sensory virtual environment provided a robust foundation for the participants’ development of comprehensive cognitive maps of the unknown space.     

Effects of interface and spatial ability on manipulation of virtual models in a STEM domain

Virtual models are increasingly employed in STEM education to foster learning about spatial phenomena. However, the roles of the computer interface and students’ cognitive abilities in moderating learning and performance with virtual models are not yet well understood. In two experiments students solved spatial organic chemistry problems using a virtual model system. Two aspects of the virtual model interface were manipulated: display dimensionality (stereoscopic vs. monoscopic displays) and the location of the hand-held device used to manipulate the virtual molecules (co-located with the visual display vs. displaced). The experimental task required participants to interpret the spatial structure of organic molecules and to manipulate the models to align them with orientations and configurations depicted by diagrams in Experiment 1 and three-dimensional models in Experiment 2. Co-locating the interaction device with the virtual image led to better performance in both experiments and stereoscopic viewing led to better performance in Experiment 2. The effect of co-location on performance was moderated by spatial ability in Experiment 1, and the effect of providing stereo viewing was moderated by spatial ability in Experiment 2. The results are in line with the ability-as-compensator hypothesis: participants with lower ability uniquely benefited from the treatment, while those with higher ability were not affected by stereo or co-location. The findings suggest that increased fidelity in a virtual model system may be one way of alleviating difficulties of low-spatial participants in learning spatially demanding content in STEM domains.     

The Effect of Learning in a Virtual Environment on Explicit and Implicit Memory by Applying a Process Dissociation Procedure

Virtual reality-based neuropsychological assessment has unique features that have the potential to increase the level of ecological validity of test results. Based on findings from the literature on the task difficulty of cognitive tasks embedded into virtual environments, we aimed to explore the task difficulty hypothesis of virtual reality in memory assessment. Our main objective was to test for differences or equivalences between performance on explicit and on implicit memory tasks in three learning environments: a computerized measure, a 3D desktop environment, and a 3D virtual environment. Seventy-seven healthy participants, aged between 19 and 39 years old, enrolled in the study and were randomly assigned to the learning conditions and responded to typical virtual reality measures. Outcomes of explicit and implicit memory resulted after applying Process Dissociation Procedure. One-way analysis of variance did not reveal a significant main effect of learning environment on explicit memory performance and equivalence testing showed similar performance on implicit memory across the learning conditions. In our study, both controlled and automatic memory processes were not influenced by the learning environment.     

A comparative study of two wayfinding aids for simulated driving tasks – single-scale and dual-scale GPS aids

Global Positioning System (GPS) is currently the most frequently used wayfinding aid for driving. Yet, GPS is designed to act as a driving guide rather than to help users gain spatial knowledge. Accordingly, GPS might be less usable in situations where such knowledge is required or highly desirable. In this study, we experimentally study the influence of GPS display scales (single-scale vs. dual-scale) using simulated driving tasks in a virtual environment. The single-scale GPS is similar to the regular GPS view. The dual-scale GPS aid is a dual-scale navigation tool that provides two levels of detail, including both detailed and contextual information. The results demonstrate that the dual-scale GPS was more efficient in leading the participants to the destination during the simulated driving and was more useful for the participants to establish spatial awareness and a cognitive map; the dual-scale GPS participants also reported higher subjective evaluations. The proposed dual-scale GPS design and experimental results show some indications for designing new wayfinding aids aimed at increasing wayfinding performance while simultaneously helping users construct a cognitive map.     

虚拟手术中缝合线打结的仿真研究

针对实习医生基本技能训练时难以真实地融入到手术环境中的问题,通过研究虚拟环境下缝合线的建模方法,实现了基于连续控制点的缝合线3D模型的建立及其位置变换过程,提出了一种基于球形包围盒的缝合线碰撞检测的算法,并由此设计出一种适用于缝合线打结的仿真方法。该仿真使用的缝合线符合外科医生实际操作习惯,具有较好的实用性。在此基础上所做的虚拟打结实验表明,此缝合线仿真能较好地对缝合线打结进行再现,可以使操作者体验到实地做手术的感觉,可用于实习外科医生的培训当中。     

The relationship between individual characteristics and experienced presence

People experience different levels of presence (e.g.  and ), and different levels of cybersickness (Sharples, Cobb, Moody, & Wilson, 2008) even though they are immersed in the same virtual environment setting. In the current study, we raised the question how differences in individual characteristics might relate to differences in sensed presence for a virtual environment related to public speaking. The individual characteristics included in the experiment were related to visual abilities, personality traits, cognitive styles, and demographic factors. We recruited 88 participants, who were first immersed in a non-stereoscopic neutral environment, and then in a public speaking world: once with stereoscopic rendering and once without stereoscopic rendering, in a counter-balanced order. The results showed that immersive tendency and monocular visual ability were significantly correlated with presence and these correlations were consistent among the three virtual environments. Immersive tendencies and its subscale “involvement” were also found to be significantly correlated with cybersickness in all three worlds. Screening people on these variables may help to recognize the users who are more likely to benefit from virtual reality applications and may help to reduce the number of dropouts during virtual reality exposure therapy.     

Ontology driven decision support for the diagnosis of mild cognitive impairment

In recent years, mild cognitive impairment (MCI) has attracted significant attention as an indicator of high risk for Alzheimer's disease (AD), and the diagnosis of MCI can alert patient to carry out appropriate strategies to prevent AD. To avoid subjectivity in diagnosis, we propose an ontology driven decision support method which is an automated procedure for diagnosing MCI through magnetic resonance imaging (MRI). In this approach, we encode specialized MRI knowledge into an ontology and construct a rule set using machine learning algorithms. Then we apply these two parts in conjunction with reasoning engine to automatically distinguish MCI patients from normal controls (NC). The rule set is trained by MRI data of 187 MCI patients and 177 normal controls selected from Alzheimer's Disease Neuroimaging Initiative (ADNI) using C4.5 algorithm. By using a 10-fold cross validation, we prove that the performance of C4.5 with 80.2% sensitivity is better than other algorithms, such as support vector machine (SVM), Bayesian network (BN) and back propagation (BP) neural networks, and C4.5 is suitable for the construction of reasoning rules. Meanwhile, the evaluation results suggest that our approach would be useful to assist physicians efficiently in real clinical diagnosis for the disease of MCI.