Alzheimer’s disease multiclass diagnosis via multimodal neuroimaging embedding feature selection and fusion

Alzheimer’s disease (AD) will become a global burden in the coming decades according to the latest statistical survey. How to effectively detect AD or MCI (mild cognitive impairment) using reliable biomarkers and robust machine learning methods has become a challenging problem. In this study, we propose a novel AD multiclass classification framework with embedding feature selection and fusion based on multimodal neuroimaging. The framework has three novel aspects: (1) An $l_{2,1}$-norm regularization term combined with the multiclass hinge loss is used to naturally select features across all the classes in each modality. (2) To fuse the complementary information contained in each modality, an $l_p$-norm $(1<p<\infty )$ regularization term is introduced to combine different kernels to perform multiple kernel learning to avoid a sparse kernel coefficient distribution, thereby effectively exploiting complementary modalities. (3) A theorem that transforms the multiclass hinge loss minimization problem using the $l_{2,1}$-norm and $l_p$-norm regularizations to a previous solvable optimization problem and its proof are given. Additionally, it is theoretically proved that the optimization process converges to the global optimum. Extensive comparison experiments and analysis support the promising performance of the proposed method.     

Introduction to the special section on aging, cognition, and neuroimaging.

In response to the recent increase in the number of laboratories engaged in the use of functional and structure neuroimaging to study cognitive aging, this special section has been compiled to serve as an entry into this area for the readers of Psychology and Aging. These articles are representative of the field and cover many of the issues faced by researchers in this area. This introduction presents some background into the techniques that are used and provides an overview of the articles. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Neuroimaging Methods to Map In Vivo Changes of OXPHOS and Oxidative Stress in Neurodegenerative Disorders

Mitochondrial dysfunction is a pathophysiological hallmark of most neurodegenerative diseases. Several clinical trials targeting mitochondrial dysfunction have been performed with conflicting results. Reliable biomarkers of mitochondrial dysfunction in vivo are thus needed to optimize future clinical trial designs. This narrative review highlights various neuroimaging methods to probe mitochondrial dysfunction. We provide a general overview of the current biological understanding of mitochondrial dysfunction in degenerative brain disorders and how distinct neuroimaging methods can be employed to map disease-related changes. The reviewed methodological spectrum includes positron emission tomography, magnetic resonance, magnetic resonance spectroscopy, and near-infrared spectroscopy imaging, and how these methods can be applied to study alterations in oxidative phosphorylation and oxidative stress. We highlight the advantages and shortcomings of the different neuroimaging methods and discuss the necessary steps to use these for future research. This review stresses the importance of neuroimaging methods to gain deepened insights into mitochondrial dysfunction in vivo, its role as a critical disease mechanism in neurodegenerative diseases, the applicability for patient stratification in interventional trials, and the quantification of individual treatment responses. The in vivo assessment of mitochondrial dysfunction is a crucial prerequisite for providing individualized treatments for neurodegenerative disorders.     

In vivo pharmacology of MDMA and its enantiomers in rhesus monkeys.

The chiral nature of the MDMA molecule gives rise to two enantiomers, each of which is biologically active. This review attempts to cover the author's research into the in vivo effects of MDMA and its enantiomers, as well as other relevant publications which pertain to this topic. No particular differences between the capacities of racemic MDMA and its enantiomers to maintain behavior were noted, but antagonism of the 5-HT2A receptor produces a parallel rightward shift in the dose-effect function for the S(+)-enantiomer, but insurmountably reduces the reinforcing effects of R(-)-MDMA. Long-term self-administration of MDMA may lead to the development of chronic tolerance to the reinforcing effects of MDMA, but S(+)-MDMA is somewhat less susceptible to this effect than the racemate or the R(-)-enantiomer. Using PET neuroimaging, negligible occupancy at the dopamine transporter (DAT) was observed following administration of R(-)-MDMA, but reasonable DAT interaction was quantified following injection of S(+)-MDMA. The non-human primate studies reviewed herein caution that any results obtained in vivo with the MDMA enantiomers may not be particularly informative with regards to the racemate and vice versa. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Data modeling and method analysis for brain imaging genetics

Brain imaging genetics is a popular research topic on evaluating the association between genetic variations and neuroimaging quantitative traits (QTs). As a bi‐multivariate analysis method, sparse canonical correlation analysis (CCA) is a useful technique which identifies efficiently genetic diseases on the brain with modeling dependencies between the variables of genotype data and phenotype data. The initial efforts on evaluating several space CCA methods are made for brain imaging genetics. A linear model is proposed to generate realistic imaging genomic data with selected genotype‐phenotype associations from real data and effectively capture the sparsity underlying projects. Three space CCA algorithms are applied to the synthetic data, and show better or comparable performance on the synthetic data in terms of the estimated canonical correlations. They have successfully identified an important association between genotype and phenotype. Experiments on simulated and real imaging genetic data show that approximating covariance structure using an identity or diagonal matrix and the approach used in these space CCA algorithms could limit the space CCA capability in identifying the underlying imaging genetics associations. Further development depends largely on enhanced space CCA methods that effectively pay attention to the covariance structures in simulated and real imaging genetics data.     

Nanotechnology for Neuroscience: Promising Approaches for Diagnostics,Therapeutics and Brain Activity Mapping

Unlocking the secrets of the brain is a task fraught with complexity and challenge – not least due to the intricacy of the circuits involved. With advancements in the scale and precision of scientific technologies, we are increasingly equipped to explore how these components interact to produce a vast range of outputs that constitute function and disease. Here, an insight is offered into key areas in which the marriage of neuroscience and nanotechnology has revolutionized the industry. The evolution of ever more sophisticated nanomaterials culminates in network‐operant functionalized agents. In turn, these materials contribute to novel diagnostic and therapeutic strategies, including drug delivery, neuroprotection, neural regeneration, neuroimaging and neurosurgery. Further, the entrance of nanotechnology into future research arenas including optogenetics, molecular/ion sensing and monitoring, and piezoelectric effects is discussed. Finally, considerations in nanoneurotoxicity, the main barrier to clinical translation, are reviewed, and direction for future perspectives is provided.     

The Implications of Cortical Recruitment and Brain Morphology for Individual Differences in Inhibitory Function in Aging Humans.

The authors assessed individual differences in cortical recruitment, brain morphology, and inhibitory task performance. Similar to previous studies, older adults tended toward bilateral activity during task performance more than younger adults. However, better performing older adults showed less bilateral activity than poorer performers, contrary to the idea that additional activity is universally compensatory. A review of the results and of extant literature suggests that compensatory activity in prefrontal cortex may only be effective if the additional cortical processors brought to bear on the task can play a complementary role in task performance. Morphological analyses revealed that frontal white matter tracts differed as a function of performance in older adults, suggesting that hemispheric connectivity might impact both patterns of recruitment and cognitive performance. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Neural activity during health messaging predicts reductions in smoking above and beyond self-report.

Objective: The current study tested whether neural activity in response to messages designed to help smokers quit could predict smoking reduction, above and beyond self-report. Design: Using neural activity in an a priori region of interest (a subregion of medial prefrontal cortex [MPFC]), in response to ads designed to help smokers quit smoking, we prospectively predicted reductions in smoking in a community sample of smokers (N = 28) who were attempting to quit smoking. Smoking was assessed via expired carbon monoxide (CO; a biological measure of recent smoking) at baseline and 1 month following exposure to professionally developed quitting ads. Results: A positive relationship was observed between activity in the MPFC region of interest and successful quitting (increased activity in MPFC was associated with a greater decrease in expired CO). The addition of neural activity to a model predicting changes in CO from self-reported intentions, self-efficacy, and ability to relate to the messages significantly improved model fit, doubling the variance explained (R2self-report = .15, R2self-report + neural activity = .35, R2change = .20). Conclusion: Neural activity is a useful complement to existing self-report measures. In this investigation, we extend prior work predicting behavior change based on neural activity in response to persuasive media to an important health domain and discuss potential psychological interpretations of the brain–behavior link. Our results support a novel use of neuroimaging technology for understanding the psychology of behavior change and facilitating health promotion. (PsycINFO Database Record (c) 2011 APA, all rights reserved)     

Analysis of nerve fibers and their distribution in histologic sections of the human brain

The field of quantitative analysis and subsequent mapping of the cerebral cortex has developed rapidly. New powerful tools have been applied to investigate large regions of complex folded gyrencephalic cortices in order to detect structural transition regions that might partition different cortical fields of disjunct neuronal functions. We have developed a new mapping approach based on axoarchitectonics, a method of cortical visualization that previously has been used only indirectly with regard to myeloarchitectonics. Myeloarchitectonic visualization has the disadvantage of producing strong agglomerative effects of closely neighbored nerve fibers. Therefore, single and neurofunctional-relevant parameters such as axonal branchings, axon areas, and axon numbers have not been determinable with satisfying precision. As a result, different staining techniques had to be explored in order to achieve a suitable histologic staining for axon visualization. The best results were obtained after modifying the Naoumenko-Feigin staining for axons. From these contrast-rich stained histologic sections, videomicroscopic digital image tiles were generated and analyzed using a new fiber analysis framework. Finally, the analysis of histologic images provided topologic ordered parameters of axons that were transferred into parameter maps. The axon parameter maps were analyzed further via a recently developed traverse generating algorithm that calculated test lines oriented perpendicular to the cortical surface and white matter border. The gray value coded parameters of the parameter maps were then transferred into profile arrays. These profile arrays were statistically analyzed by a reliable excess mass approach we recently developed. We found that specific axonal parameters are preferentially distributed throughout granular and agranular types of cortex. Furthermore, our new procedure detected transition regions originally defined by changes of cytoarchitectonic layering. Statistically significant inhomogeneities of the distribution of certain axon quantities were shown to indicate a subparcellation of areas 4 and 6. The quantification techniques established here for the analysis of spatial axon distributions within larger regions of the cerebral cortex are suitable to detect inhomogeneities of laminar axon patterns. Hence, these techniques can be recommended for systematic and observer-supported cortical area mapping and parcellation studies.     

Functional neuroimaging of working memory in schizophrenia: Task performance as a moderating variable.

Functional neuroimaging studies in schizophrenia have demonstrated abnormal activation of dorsolateral prefrontal cortex (DLPFC) during working memory (WM) performance. However, findings of increased and decreased activity have been reported. The authors used meta-analysis to investigate whether diverging results arise as a function of differential WM task performance between patients and control participants. Results indicate that the magnitude of the group difference in WM performance is a moderator of DLPFC activation differences, and concepts such as hypo- or hyperfrontality do not universally characterize WM findings in schizophrenia. Thus, the variability in the WM activation findings between participants with schizophrenia and control participants reflects the specific conditions under which WM functions are evaluated, not just the WM construct per se. (PsycINFO Database Record (c) 2010 APA, all rights reserved)