Junming Shao

Aberrant topology of striatum's connectivity is associated with the number of episodes in depression

In major depressive disorder, depressive episodes reoccur in ∼60% of cases; however, neural mechanisms of depressive relapse are poorly understood. Depressive episodes are characterized by aberrant topology of the brains intrinsic functional connectivity network, and the number of episodes is one of the most important predictors for depressive relapse. In this study we hypothesized that specific changes of the topology of intrinsic connectivity interact with the course of episodes in recurrent depressive disorder. To address this hypothesis, we investigated which changes of connectivity topology are associated with the number of episodes in patients, independently of current symptoms and disease duration. Fifty subjects were recruited including 25 depressive patients (two to 10 episodes) and 25 gender- and age-matched control subjects. Resting-state functional magnetic resonance imaging, Harvard-Oxford brain atlas, wavelet-transformation of atlas-shaped regional time-series, and their pairwise Pearsons correlation were used to define individual connectivity matrices. Matrices were analysed by graph-based methods, resulting in outcome measures that were used as surrogates of intrinsic network topology. Topological scores were subsequently compared across groups, and, for patients only, related with the number of depressive episodes and current symptoms by partial correlation analysis. Concerning the whole brain connectivity network of patients, small-world topology was preserved but global efficiency was reduced and global betweenness-centrality increased. Aberrant nodal efficiency and centrality of regional connectivity was found in the dorsal striatum, inferior frontal and orbitofrontal cortex as well as in the occipital and somatosensory cortex. Inferior frontal changes were associated with current symptoms, whereas aberrant right putamen network topology was associated with the number of episodes. Results were controlled for effects of total grey matter volume, medication, and total disease duration. This finding provides first evidence that in major depressive disorder aberrant topology of the right putamens intrinsic connectivity pattern is associated with the course of depressive episodes, independently of current symptoms, medication status and disease duration. Data suggest that the reorganization of striatal connectivity may interact with the course of episodes in depression thereby contributing to depressive relapse risk.

Aberrant Intrinsic Connectivity of Hippocampus and Amygdala Overlap in the Fronto-Insular and Dorsomedial-Prefrontal Cortex in Major Depressive Disorder

Neuroimaging studies of major depressive disorder (MDD) have consistently observed functional and structural changes of the hippocampus (HP) and amygdale (AY). Thus, these brain regions appear to be critical elements of the pathophysiology of MDD. The HP and AY directly interact and show broad and overlapping intrinsic functional connectivity (iFC) to other brain regions. Therefore, we hypothesized the HP and AY would show a corresponding pattern of aberrant intrinsic connectivity in MDD. Resting-state functional MRI was acquired from 21 patients with MDD and 20 healthy controls. ß-Maps of region-of-interest-based FC for bilateral body of the HP and basolateral AY were used as surrogates for iFC of the HP and AY. Analysis of variance was used to compare ß-maps between MDD and healthy control groups, and included covariates for age and gender as well as gray matter volume of the HP and AY. The HP and AY of MDD patient’s showed an overlapping pattern of reduced FC to the dorsomedial-prefrontal cortex and fronto-insular operculum. Both of these regions are known to regulate the interactions among intrinsic networks (i.e., default mode, central executive, and salience networks) that are disrupted in MDD. These results provide the first evidence of overlapping aberrant HP and AY intrinsic connectivity in MDD. Our findings suggest that aberrant HP and AY connectivity may interact with dysfunctional intrinsic network activity in MDD.

Learning in high-dimensional multimedia data: the state of the art

AbstractDuring the last decade, the deluge of multimedia data has impacted a wide range of research areas, including multimedia retrieval, 3D tracking, database management, data mining, machine learning, social media analysis, medical imaging, and so on. Machine learning is largely involved in multimedia applications of building models for classification and regression tasks, etc., and the learning principle consists in designing the models based on the information contained in the multimedia dataset. While many paradigms exist and are widely used in the context of machine learning, most of them suffer from the ‘curse of dimensionality’, which means that some strange phenomena appears when data are represented in a high-dimensional space. Given the high dimensionality and the high complexity of multimedia data, it is important to investigate new machine learning algorithms to facilitate multimedia data analysis. To deal with the impact of high dimensionality, an intuitive way is to reduce the dimensionality. On the other hand, some researchers devoted themselves to designing some effective learning schemes for high-dimensional data. In this survey, we cover feature transformation, feature selection and feature encoding, three approaches fighting the consequences of the curse of dimensionality. Next, we briefly introduce some recent progress of effective learning algorithms. Finally, promising future trends on multimedia learning are envisaged.

Prediction of Alzheimer's disease using individual structural connectivity networks

Alzheimers disease (AD) progressively degrades the brains gray and white matter. Changes in white matter reflect changes in the brains structural connectivity pattern. Here, we established individual structural connectivity networks (ISCNs) to distinguish predementia and dementia AD from healthy aging in individual scans. Diffusion tractography was used to construct ISCNs with a fully automated procedure for 21 healthy control subjects (HC), 23 patients with mild cognitive impairment and conversion to AD dementia within 3 years (AD-MCI), and 17 patients with mild AD dementia. Three typical pattern classifiers were used for AD prediction. Patients with AD and AD-MCI were separated from HC with accuracies greater than 95% and 90%, respectively, irrespective of prediction approach and specific fiber properties. Most informative connections involved medial prefrontal, posterior parietal, and insular cortex. Patients with mild AD were separated from those with AD-MCI with an accuracy of approximately 85%. Our finding provides evidence that ISCNs are sensitive to the impact of earliest stages of AD. ISCNs may be useful as a white matter-based imaging biomarker to distinguish healthy aging from AD.

Clustering by synchronization

Synchronization is a powerful basic concept in nature regulating a large variety of complex processes ranging from the metabolism in the cell to social behavior in groups of individuals. Therefore, synchronization phenomena have been extensively studied and models robustly capturing the dynamical synchronization process have been proposed, e.g. the Extensive Kuramoto Model. Inspired by the powerful concept of synchronization, we propose Sync, a novel approach to clustering. The basic idea is to view each data object as a phase oscillator and simulate the interaction behavior of the objects over time. As time evolves, similar objects naturally synchronize together and form distinct clusters. Inherited from synchronization, Sync has several desirable properties: The clusters revealed by dynamic synchronization truly reflect the intrinsic structure of the data set, Sync does not rely on any distribution assumption and allows detecting clusters of arbitrary number, shape and size. Moreover, the concept of synchronization allows natural outlier handling, since outliers do not synchronize with cluster objects. For fully automatic clustering, we propose to combine Sync with the Minimum Description Length principle. Extensive experiments on synthetic and real world data demonstrate the effectiveness and efficiency of our approach.

Synchronization-Inspired Partitioning and Hierarchical Clustering

Synchronization is a powerful and inherently hierarchical concept regulating a large variety of complex processes ranging from the metabolism in a cell to opinion formation in a group of individuals. Synchronization phenomena in nature have been widely investigated and models concisely describing the dynamical synchronization process have been proposed, e.g., the well-known Extensive Kuramoto Model. We explore the potential of the Extensive Kuramoto Model for data clustering. We regard each data object as a phase oscillator and simulate the dynamical behavior of the objects over time. By interaction with similar objects, the phase of an object gradually aligns with its neighborhood, resulting in a nonlinear object movement naturally driven by the local cluster structure. We demonstrate that our framework has several attractive benefits: 1) It is suitable to detect clusters of arbitrary number, shape, and data distribution, even in difficult settings with noise points and outliers. 2) Combined with the Minimum Description Length (MDL) principle, it allows partitioning and hierarchical clustering without requiring any input parameters which are difficult to estimate. 3) Synchronization faithfully captures the natural hierarchical cluster structure of the data and MDL suggests meaningful levels of abstraction. Extensive experiments demonstrate the effectiveness and efficiency of our approach.

Prototype-based learning on concept-drifting data streams

Data stream mining has gained growing attentions due to its wide emerging applications such as target marketing, email filtering and network intrusion detection. In this paper, we propose a prototype-based classification model for evolving data streams, called SyncStream, which dynamically models time-changing concepts and makes predictions in a local fashion. Instead of learning a single model on a sliding window or ensemble learning, SyncStream captures evolving concepts by dynamically maintaining a set of prototypes in a new data structure called the P-tree. The prototypes are obtained by error-driven representativeness learning and synchronization-inspired constrained clustering. To identify abrupt concept drift in data streams, PCA and statistics based heuristic approaches are employed. SyncStream has several attractive benefits: (a) It is capable of dynamically modeling evolving concepts from even a small set of prototypes and is robust against noisy examples. (b) Owing to synchronization-based constrained clustering and the P-Tree, it supports an efficient and effective data representation and maintenance. (c) Gradual and abrupt concept drift can be effectively detected. Empirical results shows that our method achieves good predictive performance compared to state-of-the-art algorithms and that it requires much less time than another instance-based stream mining algorithm.

Based on the network degeneration hypothesis: separating individual patients with different neurodegenerative syndromes in a preliminary hybrid PET/MR study

The network degeneration hypothesis (NDH) of neurodegenerative syndromes suggests that pathologic brain changes distribute primarily along distinct brain networks, which are characteristic for different syndromes. Brain changes of neurodegenerative syndromes can be characterized in vivo by different imaging modalities. Our aim was to test the hypothesis whether multimodal imaging based on the NDH separates individual patients with different neurodegenerative syndromes. Methods: Twenty patients with Alzheimer disease (AD) and 20 patients with frontotemporal lobar degeneration (behavioral variant frontotemporal dementia [bvFTD, n = 11], semantic dementia [SD, n = 4], or progressive nonfluent aphasia [PNFA, n = 5]) underwent simultaneous MRI and 18F-FDG PET in a hybrid PET/MR scanner. The 3 outcome measures were voxelwise values of degree centrality as a surrogate for regional functional connectivity, glucose metabolism as a surrogate for regional metabolism, and volumetric-based morphometry as a surrogate for regional gray matter volume. Outcome measures were derived from predefined core regions of 4 intrinsic networks based on the NDH, which have been demonstrated to be characteristic for AD, bvFTD, SD, and PNFA, respectively. Subsequently, we applied support vector machine to classify individual patients via combined imaging measures, and results were evaluated by leave-one-out cross-validation. Results: On the basis of multimodal voxelwise regional patterns, classification accuracies for separating patients with different neurodegenerative syndromes were 77.5% for AD versus others, 82.5% for bvFTD versus others, 97.5% for SD versus others, and 87.5% for PNFA versus others. Multimodal classification results were significantly superior to unimodal approaches. Conclusion: Our finding provides initial evidence that the combination of regional metabolism, functional connectivity, and gray matter volume, which were derived from disease characteristic networks, separates individual patients with different neurodegenerative syndromes. Preliminary results suggest that employing multimodal imaging guided by the NDH may generate promising biomarkers of neurodegenerative syndromes.

Feature selection methods for characterizing and classifying adaptive Sustainable Flood Retention Basins

The European Unions Flood Directive 2007/60/EC requires member states to produce flood risk maps for all river basins and coastal areas at risk of flooding by 2013. As a result, flood risk assessments have become an urgent challenge requiring a range of rapid and effective tools and approaches. The Sustainable Flood Retention Basin (SFRB) concept has evolved to provide a rapid assessment technique for impoundments, which have a pre-defined or potential role in flood defense and diffuse pollution control. A previous version of the SFRB survey method developed by the co-author Scholz in 2006 recommends gathering of over 40 variables to characterize an SFRB. Collecting all these variables is relatively time-consuming and more importantly, these variables are often correlated with each other. Therefore, the objective is to explore the correlation among these variables and find the most important variables to represent an SFRB. Three feature selection techniques (Information Gain, Mutual Information and Relief) were applied on the SFRB data set to identify the importance of the variables in terms of classification accuracy. Four benchmark classifiers (Support Vector Machine, K-Nearest Neighbours, C4.5 Decision Tree and Naïve Bayes) were subsequently used to verify the effectiveness of the classification with the selected variables and automatically identify the optimal number of variables. Experimental results indicate that our proposed approach provides a simple, rapid and effective framework for variable selection and SFRB classification. Only nine important variables are sufficient to accurately classify SFRB. Finally, six typical cases were studied to verify the performance of the identified nine variables on different SFRB types. The findings provide a rapid scientific tool for SFRB assessment in practice. Moreover, the generic value of this tool allows also for its wide application in other areas.

Predicting dam failure risk for sustainable flood retention basins: A generic case study for the wider Greater Manchester area

This study aims to provide a rapid screening tool for assessment of sustainable flood retention basins (SFRBs) to predict corresponding dam failure risks. A rapid expert-based assessment method for dam failure of SFRB supported by an artificial neural network (ANN) model has been presented. Flood storage was assessed for 110 SFRB and the corresponding Dam Failure Risk was evaluated for all dams across the wider Greater Manchester study area. The results show that Dam Failure Risk can be estimated by using the variables Dam Height, Dam Length, Maximum Flood Water Volume, Flood Water Surface Area, Mean Annual Rainfall (based on Met Office data), Altitude, Catchment Size, Urban Catchment Proportion, Forest Catchment Proportion and Managed Maximum Flood Water Volume. A cross-validation R2 value of 0.70 for the ANN model signifies that the tool is likely to predict variables well for new data sets. Traditionally, dams are considered safe because they have been built according to high technical standards. However, many dams that were constructed decades ago do not meet the current state-of-the-art dam design guidelines. Spatial distribution maps show that dam failure risks of SFRB located near cities are higher than those situated in rural locations. The proposed tool could be used as an early warning system in times of heavy rainfall.