Some forms of mild cognitive impairment (MCI) are the clinical precursors of Alzheimer's disease (AD), while other MCI types tend to remain stable over-time and do not progress to AD. To identify and ...choose effective and personalized strategies to prevent or slow the progression of AD, we need to develop objective measures that are able to discriminate the MCI patients who are at risk of AD from those MCI patients who have less risk to develop AD. Here, we present a novel deep learning architecture, based on dual learning and an ad hoc layer for 3D separable convolutions, which aims at identifying MCI patients who have a high likelihood of developing AD within 3 years.
Our deep learning procedures combine structural magnetic resonance imaging (MRI), demographic, neuropsychological, and APOe4 genetic data as input measures. The most novel characteristics of our machine learning model compared to previous ones are the following: 1) our deep learning model is multi-tasking, in the sense that it jointly learns to simultaneously predict both MCI to AD conversion as well as AD vs. healthy controls classification, which facilitates relevant feature extraction for AD prognostication; 2) the neural network classifier employs fewer parameters than other deep learning architectures which significantly limits data-overfitting (we use ∼550,000 network parameters, which is orders of magnitude lower than other network designs); 3) both structural MRI images and their warp field characteristics, which quantify local volumetric changes in relation to the MRI template, were used as separate input streams to extract as much information as possible from the MRI data. All analyses were performed on a subset of the database made publicly available via the Alzheimer's Disease Neuroimaging Initiative (ADNI), (n = 785 participants, n = 192 AD patients, n = 409 MCI patients (including both MCI patients who convert to AD and MCI patients who do not covert to AD), and n = 184 healthy controls).
The most predictive combination of inputs were the structural MRI images and the demographic, neuropsychological, and APOe4 data. In contrast, the warp field metrics were of little added predictive value. The algorithm was able to distinguish the MCI patients developing AD within 3 years from those patients with stable MCI over the same time-period with an area under the curve (AUC) of 0.925 and a 10-fold cross-validated accuracy of 86%, a sensitivity of 87.5%, and specificity of 85%. To our knowledge, this is the highest performance achieved so far using similar datasets. The same network provided an AUC of 1 and 100% accuracy, sensitivity, and specificity when classifying patients with AD from healthy controls. Our classification framework was also robust to the use of different co-registration templates and potentially irrelevant features/image portions.
Our approach is flexible and can in principle integrate other imaging modalities, such as PET, and diverse other sets of clinical data. The convolutional framework is potentially applicable to any 3D image dataset and gives the flexibility to design a computer-aided diagnosis system targeting the prediction of several medical conditions and neuropsychiatric disorders via multi-modal imaging and tabular clinical data.
Objective
Differences in myelination in the cortical mantle are important neurobiological mediators of variability in cognitive, emotional, and behavioral functioning. Past studies have found that ...personality traits reflecting such variability are linked to neuroanatomical and functional changes in prefrontal and temporo‐parietal cortices. Whether these effects are partially mediated by the differences in intra‐cortical myelin remains to be established.
Method
To test this hypothesis, we employed vertex‐wise intra‐cortical myelin maps in n = 1,003 people from the Human Connectome Project. Multivariate regression analyses were used to test for the relationship between intra‐cortical myelin and each of the five‐factor model’s personality traits, while accounting for age, sex, intelligence quotient, total intracranial volume, and the remaining personality traits.
Results
Neuroticism negatively related to frontal‐pole myelin and positively to occipital cortex myelin. Extraversion positively related to superior parietal myelin. Openness negatively related to anterior cingulate myelin, while Agreeableness positively related to orbitofrontal myelin. Conscientiousness positively related to frontal‐pole myelin and negatively to myelin content in the dorsal anterior cingulate cortex.
Conclusions
Intra‐cortical myelin levels in brain regions with prolonged myelination are positively associated with personality traits linked to favorable outcome measures. These findings improve our understanding of the neurobiological underpinnings of variability in common behavioral dispositions.
The five-factor model (FFM) is a widely used taxonomy of human personality; yet its neuro anatomical basis remains unclear. This is partly because past associations between gray-matter volume and FFM ...were driven by different surface-based morphometry (SBM) indices (i.e. cortical thickness, surface area, cortical folding or any combination of them). To overcome this limitation, we used Free-Surfer to study how variability in SBM measures was related to the FFM in n = 507 participants from the Human Connectome Project.Neuroticism was associated with thicker cortex and smaller area and folding in prefrontal-temporal regions. Extraversion was linked to thicker pre-cuneus and smaller superior temporal cortex area. Openness was linked to thinner cortex and greater area and folding in prefrontal-parietal regions. Agreeableness was correlated to thinner prefrontal cortex and smaller fusiform gyrus area. Conscientiousness was associated with thicker cortex and smaller area and folding in prefrontal regions. These findings demonstrate that anatomical variability in prefrontal cortices is linked to individual differences in the socio-cognitive dispositions described by the FFM. Cortical thickness and surface area/folding were inversely related each others as a function of different FFM traits (neuroticism, extraversion and consciousness vs openness), which may reflect brain maturational effects that predispose or protect against psychiatric disorders.
The word ‘e‐motion’ derives from the Latin word ‘ex‐moveo’ which literally means ‘moving away from something/somebody’. Emotions are thus fundamental to prime action and goal‐directed behavior with ...obvious implications for individual's survival. However, the brain mechanisms underlying the interactions between emotional and motor cortical systems remain poorly understood. A recent diffusion tensor imaging study in humans has reported the existence of direct anatomical connections between the amygdala and sensory/(pre)motor cortices, corroborating an initial observation in animal research. Nevertheless, the functional significance of these amygdala‐sensory/(pre)motor pathways remain uncertain. More specifically, it is currently unclear whether a distinct amygdala‐sensory/(pre)motor circuit can be identified with resting‐state functional magnetic resonance imaging (rs‐fMRI). This is a key issue, as rs‐fMRI offers an opportunity to simultaneously examine distinct neural circuits that underpin different cognitive, emotional and motor functions, while minimizing task‐related performance confounds. We therefore tested the hypothesis that the amygdala and sensory/(pre)motor cortices could be identified as part of the same resting‐state functional connectivity network. To this end, we examined independent component analysis results in a very large rs‐fMRI data‐set drawn from the Human Connectome Project (n = 820 participants, mean age: 28.5 years). To our knowledge, we report for the first time the existence of a distinct amygdala‐sensory/(pre)motor functional network at rest. rs‐fMRI studies are now warranted to examine potential abnormalities in this circuit in psychiatric and neurological diseases that may be associated with alterations in the amygdala‐sensory/(pre)motor pathways (e.g. conversion disorders, impulse control disorders, amyotrophic lateral sclerosis and multiple sclerosis).
It is unclear whether the putatively direct anatomical connections between the amygdala and sensory/(pre)motor cortices previously identified in animals and humans have functional significance. We addressed this issue and found that the amygdala and sensory/(pre)motor cortices could be identified as part of the same resting‐state functional connectivity circuit. Our study highlights the importance of examining potential abnormalities in limbic/motor networks in neuro‐psychiatric disorders.
Unlike other sensory systems, the structural connectivity patterns of the human vestibular cortex remain a matter of debate. Based on their functional properties and hypothesized centrality within ...the vestibular network, the ‘core’ cortical regions of this network are thought to be areas in the posterior peri-sylvian cortex, in particular the retro-insula (previously named the posterior insular cortex-PIC), and the subregion OP2 of the parietal operculum.
To study the vestibular network, structural connectivity matrices from n=974 healthy individuals drawn from the public Human Connectome Project (HCP) repository were estimated using multi-shell diffusion-weighted data followed by probabilistic tractography and spherical-deconvolution informed filtering of tractograms in combination with subject-specific grey-matter parcellations. Weighted graph-theoretical measures, modularity, and ‘hubness’ of the multimodal vestibular network were then estimated, and a structural lateralization index was defined in order to assess the difference in fiber density of homonym regions in the right and left hemisphere. Differences in connectivity patterns between OP2 and PIC were also estimated.
We found that the bilateral intraparietal sulcus, PIC, and to a lesser degree OP2, are key ‘hub’ regions within the multimodal vestibular network. PIC and OP2 structural connectivity patterns were lateralized to the left hemisphere, while structural connectivity patterns of the posterior peri-sylvian supramarginal and superior temporal gyri were lateralized to the right hemisphere. These lateralization patterns were independent of handedness.
We also found that the structural connectivity pattern of PIC is consistent with a key role of PIC in visuo-vestibular processing and that the structural connectivity pattern of OP2 is consistent with integration of mainly vestibular somato-sensory and motor information. These results suggest an analogy between PIC and the simian visual posterior sylvian (VPS) area and OP2 and the simian parieto-insular vestibular cortex (PIVC).
Overall, these findings may provide novel insights to the current models of vestibular function, as well as to the understanding of the complexity and lateralized signs of vestibular syndromes.
Prion-like, trans-neuronal spread of tau pathology in humans is controversial. By evaluating tau burden and functional connectivity in living patients, Cope et al. demonstrate relationships ...consistent with this in Alzheimer's disease but not progressive supranuclear palsy. Tau distribution in the latter is better explained by metabolic demand and trophic support.
Abstract
Alzheimer's disease and progressive supranuclear palsy (PSP) represent neurodegenerative tauopathies with predominantly cortical versus subcortical disease burden. In Alzheimer's disease, neuropathology and atrophy preferentially affect 'hub' brain regions that are densely connected. It was unclear whether hubs are differentially affected by neurodegeneration because they are more likely to receive pathological proteins that propagate trans-neuronally, in a prion-like manner, or whether they are selectively vulnerable due to a lack of local trophic factors, higher metabolic demands, or differential gene expression. We assessed the relationship between tau burden and brain functional connectivity, by combining in vivo PET imaging using the ligand AV-1451, and graph theoretic measures of resting state functional MRI in 17 patients with Alzheimer's disease, 17 patients with PSP, and 12 controls. Strongly connected nodes displayed more tau pathology in Alzheimer's disease, independently of intrinsic connectivity network, validating the predictions of theories of trans-neuronal spread but not supporting a role for metabolic demands or deficient trophic support in tau accumulation. This was not a compensatory phenomenon, as the functional consequence of increasing tau burden in Alzheimer's disease was a progressive weakening of the connectivity of these same nodes, reducing weighted degree and local efficiency and resulting in weaker 'small-world' properties. Conversely, in PSP, unlike in Alzheimer's disease, those nodes that accrued pathological tau were those that displayed graph metric properties associated with increased metabolic demand and a lack of trophic support rather than strong functional connectivity. Together, these findings go some way towards explaining why Alzheimer's disease affects large scale connectivity networks throughout cortex while neuropathology in PSP is concentrated in a small number of subcortical structures. Further, we demonstrate that in PSP increasing tau burden in midbrain and deep nuclei was associated with strengthened cortico-cortical functional connectivity. Disrupted cortico-subcortical and cortico-brainstem interactions meant that information transfer took less direct paths, passing through a larger number of cortical nodes, reducing closeness centrality and eigenvector centrality in PSP, while increasing weighted degree, clustering, betweenness centrality and local efficiency. Our results have wide-ranging implications, from the validation of models of tau trafficking in humans to understanding the relationship between regional tau burden and brain functional reorganization.
Pathological alterations to the locus coeruleus, the major source of noradrenaline in the brain, are histologically evident in early stages of neurodegenerative diseases. Novel MRI approaches now ...provide an opportunity to quantify structural features of the locus coeruleus in vivo during disease progression. In combination with neuropathological biomarkers, in vivo locus coeruleus imaging could help to understand the contribution of locus coeruleus neurodegeneration to clinical and pathological manifestations in Alzheimer's disease, atypical neurodegenerative dementias and Parkinson's disease. Moreover, as the functional sensitivity of the noradrenergic system is likely to change with disease progression, in vivo measures of locus coeruleus integrity could provide new pathophysiological insights into cognitive and behavioural symptoms. Locus coeruleus imaging also holds the promise to stratify patients into clinical trials according to noradrenergic dysfunction. In this article, we present a consensus on how non-invasive in vivo assessment of locus coeruleus integrity can be used for clinical research in neurodegenerative diseases. We outline the next steps for in vivo, post-mortem and clinical studies that can lay the groundwork to evaluate the potential of locus coeruleus imaging as a biomarker for neurodegenerative diseases.
While a large body of research has focused on the study of functional brain "connectivity", few investigators have focused on directionality of brain-brain interactions which, in spite of the mostly ...bidirectional anatomical substrates, cannot be assumed to be symmetrical. We employ a multivariate Granger Causality-based approach to estimating directed in-network interactions and quantify its advantages using extensive realistic synthetic BOLD data simulations to match Human Connectome Project (HCP) data specification. We then apply our framework to resting state functional MRI (rs-fMRI) data provided by the HCP to estimate the directed connectome of the human brain. We show that the functional interactions between parietal and prefrontal cortices commonly observed in rs-fMRI studies are not symmetrical, but consists of directional connectivity from parietal areas to prefrontal cortices rather than vice versa. These effects are localized within the same hemisphere and do not generalize to cross-hemispheric functional interactions. Our data are consistent with neurophysiological evidence that posterior parietal cortices involved in processing and integration of multi-sensory information modulate the function of more anterior prefrontal regions implicated in action control and goal-directed behaviour. The directionality of functional connectivity can provide an additional layer of information in interpreting rs-fMRI studies both in health and disease.
Early and profound pathological changes are evident in the locus coeruleus (LC) in dementia and Parkinson's disease, with effects on arousal, attention, cognitive and motor control. The LC can be ...identified in vivo using non-invasive magnetic resonance imaging techniques which have potential as biomarkers for detecting and monitoring disease progression. Technical limitations of existing imaging protocols have impaired the sensitivity to regional contrast variance or the spatial variability on the rostrocaudal extent of the LC, with spatial mapping consistent with post mortem findings. The current study employs a sensitive magnetisation transfer sequence using ultrahigh field 7T MRI to investigate the LC structure in vivo at high-resolution (0.4 × 0.4 × 0.5 mm). Magnetisation transfer images from 53 healthy older volunteers (52 - 84 years) clearly revealed the spatial features of the LC and were used to create a probabilistic LC atlas for older adults. This atlas may be especially relevant for studying disorders associated with older age. To use the atlas does not require use of the same MT sequence of 7T MRI, provided good co-registration and normalisation is achieved. Consistent rostrocaudal gradients of slice-wise volume, contrast and variance along the LC were observed, mirroring distinctive ex vivo spatial distributions of LC cells in its subregions. The contrast-to-noise ratios were calculated for the peak voxels, and for the averaged signals within the atlas, to accommodate the volumetric differences in estimated contrast. The probabilistic atlas is freely available, and the MRI dataset will be made available for non-commercial research, for replication or to facilitate accurate LC localisation and unbiased contrast extraction in future studies.