Brain tissues have single-voxel signatures in multi-spectral MRI.

Since the seminal works by Brodmann and contemporaries, it is well-known that different brain regions exhibit unique cytoarchitectonic and myeloarchitectonic features. Transferring the approach of classifying brain tissues - and other tissues - based on their intrinsic features to the realm of magnetic resonance (MR) is a longstanding endeavor. In the 1990s, atlas-based segmentation replaced earlier multi-spectral classification approaches because of the large overlap between the class distributions. Here, we explored the feasibility of performing global brain classification based on intrinsic MR features, and used several technological advances: ultra-high field MRI, q-space trajectory diffusion imaging revealing voxel-intrinsic diffusion properties, chemical exchange saturation transfer and semi-solid magnetization transfer imaging as a marker of myelination and neurochemistry, and current neural network architectures to analyze the data. In particular, we used the raw image data as well to increase the number of input features. We found that a global brain classification of roughly 97 brain regions was feasible with gross classification accuracy of 60%; and that mapping from voxel-intrinsic MR data to the brain region to which the data belongs is possible. This indicates the presence of unique MR signals of different brain regions, similar to their cytoarchitectonic and myeloarchitectonic fingerprints.

Mapping the superficial morphology of the occipital lobe: proposal of a universal nomenclature for clinical and anatomical use.

The superficial anatomy of the occipital lobe has been described as irregular and highly complex. This notion mainly arises from the variability of the regional sulco-gyral architecture. Our aim was to investigate the prevalence, morphology, and correlative anatomy of the sulci and gyri of the occipital region in cadaveric specimens and to summarize the nomenclature used in the literature to describe these structures. To this end, 33 normal, adult, formalin-fixed hemispheres were studied. In addition, a review of the relevant literature was conducted with the aim to compare our findings with data from previous studies. Hence, in the lateral occipital surface, we recorded the lateral occipital sulcus and the intraoccipital sulcus in 100%, the anterior occipital sulcus in 24%, and the inferior occipital sulcus in 15% of cases. In the area of the occipital pole, we found the transverse occipital sulcus in 88% of cases, the lunate sulcus in 64%, the occipitopolar sulcus in 24%, and the retrocalcarine sulcus in 12% of specimens. In the medial occipital surface, the calcarine fissure and parieto-occipital sulcus were always present. Finally, the basal occipital surface was always indented by the posterior occipitotemporal and posterior collateral sulci. A sulcus not previously described in the literature was identified on the supero-lateral aspect of the occipital surface in 85% of cases. We named this sulcus "marginal occipital sulcus" after its specific topography. In this study, we offer a clear description of the occipital surface anatomy and further propose a standardized taxonomy for clinical and anatomical use.

Abnormal changes of multidimensional surface features using multivariate pattern classification in amnestic mild cognitive impairment patients.

Previous studies have suggested that amnestic mild cognitive impairment (aMCI) is associated with changes in cortical morphological features, such as cortical thickness, sulcal depth, surface area, gray matter volume, metric distortion, and mean curvature. These features have been proven to have specific neuropathological and genetic underpinnings. However, most studies primarily focused on mass-univariate methods, and cortical features were generally explored in isolation. Here, we used a multivariate method to characterize the complex and subtle structural changing pattern of cortical anatomy in 24 aMCI human participants and 26 normal human controls. Six cortical features were extracted for each participant, and the spatial patterns of brain abnormities in aMCI were identified by high classification weights using a support vector machine method. The classification accuracy in discriminating the two groups was 76% in the left hemisphere and 80% in the right hemisphere when all six cortical features were used. Regions showing high weights were subtle, spatially complex, and predominately located in the left medial temporal lobe and the supramarginal and right inferior parietal lobes. In addition, we also found that the six morphological features had different contributions in discriminating the two groups even for the same region. Our results indicated that the neuroanatomical patterns that discriminated individuals with aMCI from controls were truly multidimensional and had different effects on the morphological features. Furthermore, the regions identified by our method could potentially be useful for clinical diagnosis.

Large scale screening of neural signatures of consciousness in patients in a vegetative or minimally conscious state.

In recent years, numerous electrophysiological signatures of consciousness have been proposed. Here, we perform a systematic analysis of these electroencephalography markers by quantifying their efficiency in differentiating patients in a vegetative state from those in a minimally conscious or conscious state. Capitalizing on a review of previous experiments and current theories, we identify a series of measures that can be organized into four dimensions: (i) event-related potentials versus ongoing electroencephalography activity; (ii) local dynamics versus inter-electrode information exchange; (iii) spectral patterns versus information complexity; and (iv) average versus fluctuations over the recording session. We analysed a large set of 181 high-density electroencephalography recordings acquired in a 30 minutes protocol. We show that low-frequency power, electroencephalography complexity, and information exchange constitute the most reliable signatures of the conscious state. When combined, these measures synergize to allow an automatic classification of patients' state of consciousness.

Multi-atlas based representations for Alzheimer's disease diagnosis.

Brain morphometry based classification from magnetic resonance (MR) acquisitions has been widely investigated in the diagnosis of Alzheimer's disease (AD) and its prodromal stage, i.e., mild cognitive impairment (MCI). In the literature, a morphometric representation of brain structures is obtained by spatial normalization of each image into a common space (i.e., a pre-defined atlas) via non-linear registration, thus the corresponding regions in different brains can be compared. However, representations generated from one single atlas may not be sufficient to reveal the underlying anatomical differences between the groups of disease-affected patients and normal controls (NC). In this article, we propose a different methodology, namely the multi-atlas based morphometry, which measures morphometric representations of the same image in different spaces of multiple atlases. Representations generated from different atlases can thus provide the complementary information to discriminate different groups, and also reduce the negative impacts from registration errors. Specifically, each studied subject is registered to multiple atlases, where adaptive regional features are extracted. Then, all features from different atlases are jointly selected by a correlation and relevance based scheme, followed by final classification with the support vector machine (SVM). We have evaluated the proposed method on 459 subjects (97 AD, 117 progressive-MCI (p-MCI), 117 stable-MCI (s-MCI), and 128 NC) from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database, and achieved 91.64% for AD/NC classification and 72.41% for p-MCI/s-MCI classification. Our results clearly demonstrate that the proposed multi-atlas based method can significantly outperform the previous single-atlas based methods.

A novel pipeline leveraging surface-based features of small subcortical structures to classify individuals with autism spectrum disorder.

Autism spectrum disorder (ASD) is accompanied with widespread impairment in social-emotional functioning. Classification of ASD using sensitive morphological features derived from structural magnetic resonance imaging (MRI) of the brain may help us to better understand ASD-related mechanisms and improve related automatic diagnosis. Previous studies using T1 MRI scans in large heterogeneous ABIDE dataset with typical development (TD) controls reported poor classification accuracies (around 60%). This may because they only considered surface-based morphometry (SBM) as scalar estimates (such as cortical thickness and surface area) and ignored the neighboring intrinsic geometry information among features. In recent years, the shape-related SBM achieves great success in discovering the disease burden and progression of other brain diseases. However, when focusing on local geometry information, its high dimensionality requires careful treatment in its application to machine learning. To address the above challenges, we propose a novel pipeline for ASD classification, which mainly includes the generation of surface-based features, patch-based surface sparse coding and dictionary learning, Max-pooling and ensemble classifiers based on adaptive optimizers. The proposed pipeline may leverage the sensitivity of brain surface morphometry statistics and the efficiency of sparse coding and Max-pooling. By introducing only the surface features of bilateral hippocampus that derived from 364 male subjects with ASD and 381 age-matched TD males, this pipeline outperformed five recent MRI-based ASD classification studies with >80% accuracy in discriminating individuals with ASD from TD controls. Our results suggest shape-related SBM features may further boost the classification performance of MRI between ASD and TD.

Fusion of ULS Group Constrained High- and Low-Order Sparse Functional Connectivity Networks for MCI Classification.

Functional connectivity networks, derived from resting-state fMRI data, have been found as effective biomarkers for identifying mild cognitive impairment (MCI) from healthy elderly. However, the traditional functional connectivity network is essentially a low-order network with the assumption that the brain activity is static over the entire scanning period, ignoring temporal variations among the correlations derived from brain region pairs. To overcome this limitation, we proposed a new type of sparse functional connectivity network to precisely describe the relationship of temporal correlations among brain regions. Specifically, instead of using the simple pairwise Pearson's correlation coefficient as connectivity, we first estimate the temporal low-order functional connectivity for each region pair based on an ULS Group constrained-UOLS regression algorithm, where a combination of ultra-least squares (ULS) criterion with a Group constrained topology structure detection algorithm is applied to detect the topology of functional connectivity networks, aided by an Ultra-Orthogonal Least Squares (UOLS) algorithm to estimate connectivity strength. Compared to the classical least squares criterion which only measures the discrepancy between the observed signals and the model prediction function, the ULS criterion takes into consideration the discrepancy between the weak derivatives of the observed signals and the model prediction function and thus avoids the overfitting problem. By using a similar approach, we then estimate the high-order functional connectivity from the low-order connectivity to characterize signal flows among the brain regions. We finally fuse the low-order and the high-order networks using two decision trees for MCI classification. Experimental results demonstrate the effectiveness of the proposed method on MCI classification.

fMRI classification method with multiple feature fusion based on minimum spanning tree analysis.

Resting state functional brain networks have been widely studied in brain disease research. Conventional network analysis methods are hampered by differences in network size, density and normalization. Minimum spanning tree (MST) analysis has been recently suggested to ameliorate these limitations. Moreover, common MST analysis methods involve calculating quantifiable attributes and selecting these attributes as features in the classification. However, a disadvantage of these methods is that information about the topology of the network is not fully considered, limiting further improvement of classification performance. To address this issue, we propose a novel method combining brain region and subgraph features for classification, utilizing two feature types to quantify two properties of the network. We experimentally validated our proposed method using a major depressive disorder (MDD) patient dataset. The results indicated that MSTs of MDD patients were more similar to random networks and exhibited significant differences in certain regions involved in the limbic-cortical-striatal-pallidal-thalamic (LCSPT) circuit, which is considered to be a major pathological circuit of depression. Moreover, we demonstrated that this novel classification method could effectively improve classification accuracy and provide better interpretability. Overall, the current study demonstrated that different forms of feature representation provide complementary information.

Classification of mouth movements using 7 T fMRI.

OBJECTIVE: A brain-computer interface (BCI) is an interface that uses signals from the brain to control a computer. BCIs will likely become important tools for severely paralyzed patients to restore interaction with the environment. The sensorimotor cortex is a promising target brain region for a BCI due to the detailed topography and minimal functional interference with other important brain processes. Previous studies have shown that attempted movements in paralyzed people generate neural activity that strongly resembles actual movements. Hence decodability for BCI applications can be studied in able-bodied volunteers with actual movements. APPROACH: In this study we tested whether mouth movements provide adequate signals in the sensorimotor cortex for a BCI. The study was executed using fMRI at 7 T to ensure relevance for BCI with cortical electrodes, as 7 T measurements have been shown to correlate well with electrocortical measurements. Twelve healthy volunteers executed four mouth movements (lip protrusion, tongue movement, teeth clenching, and the production of a larynx activating sound) while in the scanner. Subjects performed a training and a test run. Single trials were classified based on the Pearson correlation values between the activation patterns per trial type in the training run and single trials in the test run in a 'winner-takes-all' design. MAIN RESULTS: Single trial mouth movements could be classified with 90% accuracy. The classification was based on an area with a volume of about 0.5 cc, located on the sensorimotor cortex. If voxels were limited to the surface, which is accessible for electrode grids, classification accuracy was still very high (82%). Voxels located on the precentral cortex performed better (87%) than the postcentral cortex (72%). SIGNIFICANCE: The high reliability of decoding mouth movements suggests that attempted mouth movements are a promising candidate for BCI in paralyzed people.

Anatomical heterogeneity of Alzheimer disease: based on cortical thickness on MRIs.

OBJECTIVE: Because the signs associated with dementia due to Alzheimer disease (AD) can be heterogeneous, the goal of this study was to use 3-dimensional MRI to examine the various patterns of cortical atrophy that can be associated with dementia of AD type, and to investigate whether AD dementia can be categorized into anatomical subtypes. METHODS: High-resolution T1-weighted volumetric MRIs were taken of 152 patients in their earlier stages of AD dementia. The images were processed to measure cortical thickness, and hierarchical agglomerative cluster analysis was performed using Ward's clustering linkage. The identified clusters of patients were compared with an age- and sex-matched control group using a general linear model. RESULTS: There were several distinct patterns of cortical atrophy and the number of patterns varied according to the level of cluster analyses. At the 3-cluster level, patients were divided into (1) bilateral medial temporal-dominant atrophy subtype (n = 52, ∼ 34.2%), (2) parietal-dominant subtype (n = 28, ∼ 18.4%) in which the bilateral parietal lobes, the precuneus, along with bilateral dorsolateral frontal lobes, were atrophic, and (3) diffuse atrophy subtype (n = 72, ∼ 47.4%) in which nearly all association cortices revealed atrophy. These 3 subtypes also differed in their demographic and clinical features. CONCLUSIONS: This cluster analysis of cortical thickness of the entire brain showed that AD dementia in the earlier stages can be categorized into various anatomical subtypes, with distinct clinical features.

Vector-based phase classification of initial dips during word listening using near-infrared spectroscopy.

This study examined the classification of initial dips during passive listening to single words by analysis of vectors of deoxyHb and oxyHb measurements simultaneously derived from near-infrared spectroscopy. The initial dip response during a single-word 1.5-s task in 13 healthy participants was significant only in the language area, which includes the left posterior superior temporal gyrus and angular gyrus. Event-related vectors of responses to comprehended words moved significantly into phase 4, a dip phase, whereas vectors of responses to unknown words moved into a nondip phase (P<0.05). The same results were reproduced after previously unknown words were learnt by the participants. Among the five dip phases, reflecting variations in transient oxygen metabolic regulation during a task, the frequency of occurrence of hypoxic-ischemic initial dips (decreased oxyHb) was around three times that of the canonical dip (increased deoxyHb and oxyHb). Phase classification of event-related vectors enhances the slight amount of oxygen exchange that occurs in word recognition, which has been difficult to detect because of its small amplitude.

Can a single brain region predict a disorder?

We perform prediction of diverse disorders (Cocaine Use, Schizophrenia and Alzheimers disease) in unseen subjects from brain fMRI. First, we show that for multi-subject prediction of simple cognitive states (e.g. motor vs. calculation and reading), voxels-as-features methods produce clusters that are similar for different leave-one-subject-out folds; while for group classification (e.g. cocaine addicted vs. control subjects), voxels are scattered and less stable. Therefore, we chose to use a single region per experimental condition and a majority vote classifier. Interestingly, our method outperforms state-of-the-art techniques. Our method can integrate multiple experimental conditions and successfully predict disorders in unseen subjects (leave-one-subjectout generalization accuracy: 89.3% and 90.9% for Cocaine Use, 96.4% for Schizophrenia and 81.5% for Alzheimers disease). Our experimental results not only span diverse disorders, but also different experimental designs (block design and event related tasks), facilities, magnetic fields (1.5Tesla, 3Tesla, 4Tesla) and speed of acquisition (interscan interval from 1600ms to 3500ms). We further argue that our method produces a meaningful low dimensional representation that retains discriminability.

Human category learning 2.0.

During the 1990s and early 2000s, cognitive neuroscience investigations of human category learning focused on the primary goal of showing that humans have multiple category-learning systems and on the secondary goals of identifying key qualitative properties of each system and of roughly mapping out the neural networks that mediate each system. Many researchers now accept the strength of the evidence supporting multiple systems, and as a result, during the past few years, work has begun on the second generation of research questions-that is, on questions that begin with the assumption that humans have multiple category-learning systems. This article reviews much of this second generation of research. Topics covered include (1) How do the various systems interact? (2) Are there different neural systems for categorization and category representation? (3) How does automaticity develop in each system? and (4) Exactly how does each system learn?

Comparative study of SVM methods combined with voxel selection for object category classification on fMRI data.

BACKGROUND: Support vector machine (SVM) has been widely used as accurate and reliable method to decipher brain patterns from functional MRI (fMRI) data. Previous studies have not found a clear benefit for non-linear (polynomial kernel) SVM versus linear one. Here, a more effective non-linear SVM using radial basis function (RBF) kernel is compared with linear SVM. Different from traditional studies which focused either merely on the evaluation of different types of SVM or the voxel selection methods, we aimed to investigate the overall performance of linear and RBF SVM for fMRI classification together with voxel selection schemes on classification accuracy and time-consuming. METHODOLOGY/PRINCIPAL FINDINGS: Six different voxel selection methods were employed to decide which voxels of fMRI data would be included in SVM classifiers with linear and RBF kernels in classifying 4-category objects. Then the overall performances of voxel selection and classification methods were compared. Results showed that: (1) Voxel selection had an important impact on the classification accuracy of the classifiers: in a relative low dimensional feature space, RBF SVM outperformed linear SVM significantly; in a relative high dimensional space, linear SVM performed better than its counterpart; (2) Considering the classification accuracy and time-consuming holistically, linear SVM with relative more voxels as features and RBF SVM with small set of voxels (after PCA) could achieve the better accuracy and cost shorter time. CONCLUSIONS/SIGNIFICANCE: The present work provides the first empirical result of linear and RBF SVM in classification of fMRI data, combined with voxel selection methods. Based on the findings, if only classification accuracy was concerned, RBF SVM with appropriate small voxels and linear SVM with relative more voxels were two suggested solutions; if users concerned more about the computational time, RBF SVM with relative small set of voxels when part of the principal components were kept as features was a better choice.

The utility metric: a novel method to assess the overall performance of discrete brain-computer interfaces.

A relevant issue in a brain-computer interface (BCI) is the capability to efficiently convert user intentions into correct actions, and how to properly measure this efficiency. Usually, the evaluation of a BCI system is approached through the quantification of the classifier performance, which is often measured by means of the information transfer rate (ITR). A shortcoming of this approach is that the control interface design is neglected, and hence a poor description of the overall performance is obtained for real systems. To overcome this limitation, we propose a novel metric based on the computation of BCI Utility. The new metric can accurately predict the overall performance of a BCI system, as it takes into account both the classifier and the control interface characteristics. It is therefore suitable for design purposes, where we have to select the best options among different components and different parameters setup. In the paper, we compute Utility in two scenarios, a P300 speller and a P300 speller with an error correction system (ECS), for different values of accuracy of the classifier and recall of the ECS. Monte Carlo simulations confirm that Utility predicts the performance of a BCI better than ITR.

A method to study global spatial patterns related to sensory perception in scalp EEG.

Prior studies of multichannel ECoG from animals showed that beta and gamma oscillations carried perceptual information in both local and global spatial patterns of amplitude modulation, when the subjects were trained to discriminate conditioned stimuli (CS). Here the hypothesis was tested that similar patterns could be found in the scalp EEG human subjects trained to discriminate simultaneous visual-auditory CS. Signals were continuously recorded from 64 equispaced scalp electrodes and band-pass filtered. The Hilbert transform gave the analytic phase, which segmented the EEG into temporal frames, and the analytic amplitude, which expressed the pattern in each frame as a feature vector. Methods applied to the ECoG were adapted to the EEG for systematic search of the beta-gamma spectrum, the time period after CS onset, and the scalp surface to locate patterns that could be classified with respect to type of CS. Spatial patterns of EEG amplitude modulation were found from all subjects that could be classified with respect to stimulus combination type significantly above chance levels. The patterns were found in the beta range (15-22 Hz) but not in the gamma range. They occurred in three short bursts following CS onset. They were non-local, occupying the entire array. Our results suggest that the scalp EEG can yield information about the timing of episodically synchronized brain activity in higher cognitive function, so that future studies in brain-computer interfacing can be better focused. Our methods may be most valuable for analyzing data from dense arrays with very high spatial and temporal sampling rates.