Hybrid ICA-Bayesian network approach reveals distinct effective connectivity differences in schizophrenia

Bayesian networks for network inference in biology

Bayesian networks (BNs) have been used for reconstructing interactions from biological data, in disciplines ranging from molecular biology to ecology and neuroscience. BNs learn conditional dependencies between variables, which best 'explain' the data, represented as a directed graph which approximates the relationships between variables. In the 2000s, BNs were a popular method that promised an approach capable of inferring biological networks from data. Here, we review the use of BNs applied to biological data over the past two decades and evaluate their efficacy. We find that BNs are successful in inferring biological networks, frequently identifying novel interactions or network components missed by previous analyses. We suggest that as false positive results are underreported, it is difficult to assess the accuracy of BNs in inferring biological networks. BN learning appears most successful for small numbers of variables with high-quality datasets that either discretize the data into few states or include perturbative data. We suggest that BNs have failed to live up to the promise of the 2000s but that this is most likely due to experimental constraints on datasets, and the success of BNs at inferring networks in a variety of biological contexts suggests they are a powerful tool for biologists.

Recognition of Conus species using a combined approach of supervised learning and deep learning-based feature extraction

Cone snails are venomous marine gastropods comprising more than 950 species widely distributed across different habitats. Their conical shells are remarkably similar to those of other invertebrates in terms of color, pattern, and size. For these reasons, assigning taxonomic signatures to cone snail shells is a challenging task. In this report, we propose an ensemble learning strategy based on the combination of Random Forest (RF) and XGBoost (XGB) methods. We used 47,600 cone shell images of uniform size (224 x 224 pixels), which were split into an 80:20 train-test ratio. Prior to performing subsequent operations, these images were subjected to pre-processing and transformation. After applying a deep learning approach (Visual Geometry Group with a 16-layer deep model architecture) for feature extraction, model specificity was further assessed by including multiple related and unrelated seashell images. Both classifiers demonstrated comparable recognition ability on random test samples. The evaluation results suggested that RF outperformed XGB due to its high accuracy in recognizing Conus species, with an average precision of 95.78%. The area under the receiver operating characteristic curve was 0.99, indicating the model's optimal performance. The learning and validation curves also demonstrated a robust fit, with the training score reaching 1 and the validation score gradually increasing to 95 as more data was provided. These values indicate a well-trained model that generalizes effectively to validation data without significant overfitting. The gradual improvement in the validation score curve is crucial for ensuring model reliability and minimizing the risk of overfitting. Our findings revealed an interactive visualization. The performance of our proposed model suggests its potential for use with datasets of other mollusks, and optimal results may be achieved for their categorization and taxonomical characterization.

Studying time-resolved functional connectivity via communication theory: on the complementary nature of phase synchronization and sliding window Pearson correlation

Time-resolved functional connectivity (trFC) assesses the time-resolved coupling between brain regions using functional magnetic resonance imaging (fMRI) data. This study aims to compare two techniques used to estimate trFC to investigate their similarities and differences when applied to fMRI data. These techniques are the sliding window Pearson correlation (SWPC), an amplitude-based approach, and phase synchronization (PS), a phase-based technique. To accomplish our objective, we used resting-state fMRI data from the Human Connectome Project (HCP) with 827 subjects (repetition time: 0.72s) and the Function Biomedical Informatics Research Network (fBIRN) with 311 subjects (repetition time: 2s), which included 151 schizophrenia patients and 160 controls. Our simulations reveal distinct strengths in two connectivity methods: SWPC captures high-magnitude, low-frequency connectivity, while PS detects low-magnitude, high-frequency connectivity. Stronger correlations between SWPC and PS align with pronounced fMRI oscillations. For fMRI data, higher correlations between SWPC and PS occur with matched frequencies and smaller SWPC window sizes (~30s), but larger windows (~88s) sacrifice clinically relevant information. Both methods identify a schizophrenia-associated brain network state but show different patterns: SWPC highlights low anti-correlations between visual, subcortical, auditory, and sensory-motor networks, while PS shows reduced positive synchronization among these networks. In sum, our findings underscore the complementary nature of SWPC and PS, elucidating their respective strengths and limitations without implying the superiority of one over the other.

New Approach for Risk Estimation Algorithms of BRCA1/2 Negativeness Detection with Modelling Supervised Machine Learning Techniques

BRCA1/2 gene testing is a difficult, expensive, and time-consuming test which requires excessive work load. The identification of the BRCA1/2 gene mutations is significantly important in the selection of treatment and the risk of secondary cancer. We aimed to develop an algorithm considering all the clinical, demographic, and genetic features of patients for identifying the BRCA1/2 negativity in the present study. An experimental dataset was created with the collection of the all clinical, demographic, and genetic features of breast cancer patients for 20 years. This dataset consisted of 125 features of 2070 high-risk breast cancer patients. All data were numeralized and normalized for detection of the BRCA1/2 negativity in the machine learning algorithm. The performance of the algorithm was identified by studying the machine learning model with the test data. k nearest neighbours (KNN) and decision tree (DT) accuracy rates of 9 features involving Dataset 2 were found to be the most effective. The removal of the unnecessary data in the dataset by reducing the number of features was shown to increase the accuracy rate of algorithm compared with the DT. BRCA1/2 negativity was identified without performing the BRCA1/2 gene test with 92.88% accuracy within minutes in high-risk breast cancer patients with this algorithm, and the test associated result waiting stress, time, and money loss were prevented. That algorithm is suggested be useful in fast performing of the treatment plans of patients and accurately in addition to speeding up the clinical practice.

Application of machine learning in ophthalmic imaging modalities

In clinical ophthalmology, a variety of image-related diagnostic techniques have begun to offer unprecedented insights into eye diseases based on morphological datasets with millions of data points. Artificial intelligence (AI), inspired by the human multilayered neuronal system, has shown astonishing success within some visual and auditory recognition tasks. In these tasks, AI can analyze digital data in a comprehensive, rapid and non-invasive manner. Bioinformatics has become a focus particularly in the field of medical imaging, where it is driven by enhanced computing power and cloud storage, as well as utilization of novel algorithms and generation of data in massive quantities. Machine learning (ML) is an important branch in the field of AI. The overall potential of ML to automatically pinpoint, identify and grade pathological features in ocular diseases will empower ophthalmologists to provide high-quality diagnosis and facilitate personalized health care in the near future. This review offers perspectives on the origin, development, and applications of ML technology, particularly regarding its applications in ophthalmic imaging modalities.

Amalgamating evidence of dynamics

Many approaches to evidence amalgamation focus on relatively static information or evidence: the data to be amalgamated involve different variables, contexts, or experiments, but not measurements over extended periods of time. However, much of scientific inquiry focuses on dynamical systems; the system's behavior over time is critical. Moreover, novel problems of evidence amalgamation arise in these contexts. First, data can be collected at different measurement timescales, where potentially none of them correspond to the underlying system's causal timescale. Second, missing variables have a significantly different impact on time series measurements than they do in the traditional static setting; in particular, they make causal and structural inference much more difficult. In this paper, we argue that amalgamation should proceed by integrating causal knowledge, rather than at the level of "raw" evidence. We defend this claim by first outlining both of these problems, and then showing that they can be solved only if we operate on causal structures. We therefore must use causal discovery methods that are reliable given these problems. Such methods do exist, but their successful application requires careful consideration of the problems that we highlight.

Spatio-Temporal Dynamics of Intrinsic Networks in Functional Magnetic Imaging Data Using Recurrent Neural Networks

We introduce a novel recurrent neural network (RNN) approach to account for temporal dynamics and dependencies in brain networks observed via functional magnetic resonance imaging (fMRI). Our approach directly parameterizes temporal dynamics through recurrent connections, which can be used to formulate blind source separation with a conditional (rather than marginal) independence assumption, which we call RNN-ICA. This formulation enables us to visualize the temporal dynamics of both first order (activity) and second order (directed connectivity) information in brain networks that are widely studied in a static sense, but not well-characterized dynamically. RNN-ICA predicts dynamics directly from the recurrent states of the RNN in both task and resting state fMRI. Our results show both task-related and group-differentiating directed connectivity.

A novel fuzzy rough selection of non-linearly extracted features for schizophrenia diagnosis using fMRI

BACKGROUND AND OBJECTIVES

Schizophrenia is a severe brain disorder primarily diagnosed through externally observed behavioural symptoms due to the dearth of established clinical tests. Functional magnetic resonance imaging (fMRI) can capture the distortions caused by schizophrenia in the brain activation. Hence, it can be useful for developing a decision model that performs computer-aided diagnosis of schizophrenia. But, fMRI data is huge in dimension. Therefore dimension reduction is indispensable. It is additionally required to identify the discriminative brain regions. Hence, we aim to build an effective decision model that incorporates suitable dimension reduction and also identifies discriminative brain regions.

METHODS

We propose a three-phase dimension reduction. First phase involves spatially-constrained fuzzy clustering of 3-dimensional spatial maps (obtained from general linear model and independent component analysis). In the second phase, non-linear features are extracted from each cluster using a generalized discriminant analysis. In the third phase, a novel fuzzy rough feature selection is proposed. The features obtained after the third phase are used for learning a decision model by the help of support vector machine classifier. This complete method is implemented within leave-one-out cross-validation on two balanced datasets (respectively acquired on 1.5Tesla and 3Tesla scanners). Both these datasets are created using Function Biomedical Informatics Research Network multisite data and contain fMRI data acquired during auditory oddball task performed by age-matched schizophrenia patients and healthy subjects. A permutation test is also carried out to ensure that no bias is involved in the learning.

RESULTS

The results indicate that the proposed method achieves maximum classification accuracy of 97.1% and 98.0% for the two datasets respectively. The proposed method outperforms the state-of-the-art methods. The results of the permutation test show that p-values are lesser than the significance level i.e. 0.05. Therefore, the classifier has found a significant class structure and does not involve any bias. Further, discriminative brain regions are identified and are in agreement with the findings in related literature.

CONCLUSION

The proposed method is able to derive suitable non-linear features and the related brain regions for effective computer-aided diagnosis. The fuzzy and rough set based approaches help in handling uncertainty and ambiguity in real data.

Machine Learning for Medical Imaging

Machine learning is a technique for recognizing patterns that can be applied to medical images. Although it is a powerful tool that can help in rendering medical diagnoses, it can be misapplied. Machine learning typically begins with the machine learning algorithm system computing the image features that are believed to be of importance in making the prediction or diagnosis of interest. The machine learning algorithm system then identifies the best combination of these image features for classifying the image or computing some metric for the given image region. There are several methods that can be used, each with different strengths and weaknesses. There are open-source versions of most of these machine learning methods that make them easy to try and apply to images. Several metrics for measuring the performance of an algorithm exist; however, one must be aware of the possible associated pitfalls that can result in misleading metrics. More recently, deep learning has started to be used; this method has the benefit that it does not require image feature identification and calculation as a first step; rather, features are identified as part of the learning process. Machine learning has been used in medical imaging and will have a greater influence in the future. Those working in medical imaging must be aware of how machine learning works. ^©RSNA, 2017.

Flavor pleasantness processing in the ventral emotion network

The ventral emotion network-encompassing the amygdala, insula, ventral striatum, and ventral regions of the prefrontal cortex-has been associated with the identification of emotional significance of perceived external stimuli and the production of affective states. Functional magnetic resonance imaging (fMRI) studies investigating chemosensory stimuli have associated parts of this network with pleasantness coding. In the current study, we independently analyzed two datasets in which we measured brain responses to flavor stimuli in young adult men. In the first dataset, participants evaluated eight regular off the shelf drinking products while participants evaluated six less familiar oral nutritional supplements (ONS) in the second dataset. Participants provided pleasantness ratings 20 seconds after tasting. Using independent component analysis (ICA) and mixed effect models, we identified one brain network in the regular products dataset that was associated with flavor pleasantness. This network was very similar to the ventral emotion network. Although we identified an identical network in the ONS dataset using ICA, we found no linear relation between activation of any network and pleasantness scores within this dataset. Our results indicate that flavor pleasantness is processed in a network encompassing amygdala, ventral prefrontal, insular, striatal and parahippocampal regions for familiar drinking products. For more unfamiliar ONS products the association is not obvious, which could be related to the unfamiliarity of these products.

Bayesian vector autoregressive model for multi-subject effective connectivity inference using multi-modal neuroimaging data

In this article a multi-subject vector autoregressive (VAR) modeling approach was proposed for inference on effective connectivity based on resting-state functional MRI data. Their framework uses a Bayesian variable selection approach to allow for simultaneous inference on effective connectivity at both the subject- and group-level. Furthermore, it accounts for multi-modal data by integrating structural imaging information into the prior model, encouraging effective connectivity between structurally connected regions. They demonstrated through simulation studies that their approach resulted in improved inference on effective connectivity at both the subject- and group-level, compared with currently used methods. It was concluded by illustrating the method on temporal lobe epilepsy data, where resting-state functional MRI and structural MRI were used. Hum Brain Mapp 38:1311-1332, 2017. © 2016 Wiley Periodicals, Inc.

Understanding disease processes by partitioned dynamic Bayesian networks

For many clinical problems in patients the underlying pathophysiological process changes in the course of time as a result of medical interventions. In model building for such problems, the typical scarcity of data in a clinical setting has been often compensated by utilizing time homogeneous models, such as dynamic Bayesian networks. As a consequence, the specificities of the underlying process are lost in the obtained models. In the current work, we propose the new concept of partitioned dynamic Bayesian networks to capture distribution regime changes, i.e. time non-homogeneity, benefiting from an intuitive and compact representation with the solid theoretical foundation of Bayesian network models. In order to balance specificity and simplicity in real-world scenarios, we propose a heuristic algorithm to search and learn these non-homogeneous models taking into account a preference for less complex models. An extensive set of experiments were ran, in which simulating experiments show that the heuristic algorithm was capable of constructing well-suited solutions, in terms of goodness of fit and statistical distance to the original distributions, in consonance with the underlying processes that generated data, whether it was homogeneous or non-homogeneous. Finally, a study case on psychotic depression was conducted using non-homogeneous models learned by the heuristic, leading to insightful answers for clinically relevant questions concerning the dynamics of this mental disorder.

Functional Magnetic Resonance Imaging Methods

Since its inception in 1992, Functional Magnetic Resonance Imaging (fMRI) has become an indispensible tool for studying cognition in both the healthy and dysfunctional brain. FMRI monitors changes in the oxygenation of brain tissue resulting from altered metabolism consequent to a task-based evoked neural response or from spontaneous fluctuations in neural activity in the absence of conscious mentation (the "resting state"). Task-based studies have revealed neural correlates of a large number of important cognitive processes, while fMRI studies performed in the resting state have demonstrated brain-wide networks that result from brain regions with synchronized, apparently spontaneous activity. In this article, we review the methods used to acquire and analyze fMRI signals.

Directionality of large-scale resting-state brain networks during eyes open and eyes closed conditions

The present study examined directional connections in the brain among resting-state networks (RSNs) when the participant had their eyes open (EO) or had their eyes closed (EC). The resting-state fMRI data were collected from 20 healthy participants (9 males, 20.17 ± 2.74 years) under the EO and EC states. Independent component analysis (ICA) was applied to identify the separated RSNs (i.e., the primary/high-level visual, primary sensory-motor, ventral motor, salience/dorsal attention, and anterior/posterior default-mode networks), and the Gaussian Bayesian network (BN) learning approach was then used to explore the conditional dependencies among these RSNs. The network-to-network directional connections related to EO and EC were depicted, and a support vector machine (SVM) was further employed to identify the directional connection patterns that could effectively discriminate between the two states. The results indicated that the connections among RSNs are directionally connected within a BN during the EO and EC states. The directional connections from the salience network (SN) to the anterior/posterior default-mode networks and the high-level to primary-level visual network were the obvious characteristics of both the EO and EC resting-state BNs. Of the directional connections in BN, the directional connections of the salience and dorsal attention network (DAN) were observed to be discriminative between the EO and EC states. In particular, we noted that the properties of the salience and DANs were in opposite directions. Overall, the present study described the directional connections of RSNs using a BN learning approach during the EO and EC states, and the results suggested that the directionality of the attention systems (i.e., mainly for the salience and the DAN) in resting state might have important roles in switching between the EO and EC conditions.

Bayesian Models for fMRI Data Analysis

Functional magnetic resonance imaging (fMRI), a noninvasive neuroimaging method that provides an indirect measure of neuronal activity by detecting blood flow changes, has experienced an explosive growth in the past years. Statistical methods play a crucial role in understanding and analyzing fMRI data. Bayesian approaches, in particular, have shown great promise in applications. A remarkable feature of fully Bayesian approaches is that they allow a flexible modeling of spatial and temporal correlations in the data. This paper provides a review of the most relevant models developed in recent years. We divide methods according to the objective of the analysis. We start from spatio-temporal models for fMRI data that detect task-related activation patterns. We then address the very important problem of estimating brain connectivity. We also touch upon methods that focus on making predictions of an individual's brain activity or a clinical or behavioral response. We conclude with a discussion of recent integrative models that aim at combining fMRI data with other imaging modalities, such as EEG/MEG and DTI data, measured on the same subjects. We also briefly discuss the emerging field of imaging genetics.

Spatial component analysis of MRI data for Alzheimer's disease diagnosis: a Bayesian network approach

This work presents a spatial-component (SC) based approach to aid the diagnosis of Alzheimer's disease (AD) using magnetic resonance images. In this approach, the whole brain image is subdivided in regions or spatial components, and a Bayesian network is used to model the dependencies between affected regions of AD. The structure of relations between affected regions allows to detect neurodegeneration with an estimated performance of 88% on more than 400 subjects and predict neurodegeneration with 80% accuracy, supporting the conclusion that modeling the dependencies between components increases the recognition of different patterns of brain degeneration in AD.

Bayesian networks in neuroscience: a survey

Bayesian networks are a type of probabilistic graphical models lie at the intersection between statistics and machine learning. They have been shown to be powerful tools to encode dependence relationships among the variables of a domain under uncertainty. Thanks to their generality, Bayesian networks can accommodate continuous and discrete variables, as well as temporal processes. In this paper we review Bayesian networks and how they can be learned automatically from data by means of structure learning algorithms. Also, we examine how a user can take advantage of these networks for reasoning by exact or approximate inference algorithms that propagate the given evidence through the graphical structure. Despite their applicability in many fields, they have been little used in neuroscience, where they have focused on specific problems, like functional connectivity analysis from neuroimaging data. Here we survey key research in neuroscience where Bayesian networks have been used with different aims: discover associations between variables, perform probabilistic reasoning over the model, and classify new observations with and without supervision. The networks are learned from data of any kind-morphological, electrophysiological, -omics and neuroimaging-, thereby broadening the scope-molecular, cellular, structural, functional, cognitive and medical- of the brain aspects to be studied.

Bayesian network analysis revealed the connectivity difference of the default mode network from the resting-state to task-state

Functional magnetic resonance imaging (fMRI) studies have converged to reveal the default mode network (DMN), a constellation of regions that display co-activation during resting-state but co-deactivation during attention-demanding tasks in the brain. Here, we employed a Bayesian network (BN) analysis method to construct a directed effective connectivity model of the DMN and compared the organizational architecture and interregional directed connections under both resting-state and task-state. The analysis results indicated that the DMN was consistently organized into two closely interacting subsystems in both resting-state and task-state. The directed connections between DMN regions, however, changed significantly from the resting-state to task-state condition. The results suggest that the DMN intrinsically maintains a relatively stable structure whether at rest or performing tasks but has different information processing mechanisms under varied states.

Abnormal synchrony and effective connectivity in patients with schizophrenia and auditory hallucinations

Auditory hallucinations (AH) are the most frequent positive symptoms in patients with schizophrenia. Hallucinations have been related to emotional processing disturbances, altered functional connectivity and effective connectivity deficits. Previously, we observed that, compared to healthy controls, the limbic network responses of patients with auditory hallucinations differed when the subjects were listening to emotionally charged words. We aimed to compare the synchrony patterns and effective connectivity of task-related networks between schizophrenia patients with and without AH and healthy controls. Schizophrenia patients with AH (n = 27) and without AH (n = 14) were compared with healthy participants (n = 31). We examined functional connectivity by analyzing correlations and cross-correlations among previously detected independent component analysis time courses. Granger causality was used to infer the information flow direction in the brain regions. The results demonstrate that the patterns of cortico-cortical functional synchrony differentiated the patients with AH from the patients without AH and from the healthy participants. Additionally, Granger-causal relationships between the networks clearly differentiated the groups. In the patients with AH, the principal causal source was an occipital-cerebellar component, versus a temporal component in the patients without AH and the healthy controls. These data indicate that an anomalous process of neural connectivity exists when patients with AH process emotional auditory stimuli. Additionally, a central role is suggested for the cerebellum in processing emotional stimuli in patients with persistent AH.

Review of fMRI Data Analysis

Classification of brain states obtained through functional magnetic resonance imaging (fMRI) poses a serious challenges for neuroimaging community to uncover discriminating patterns of brain state activity that define independent thought processes. This challenge came into existence because of the large number of voxels in a typical fMRI scan, the classifier is presented with a massive feature set coupled with a relatively small training samples. One of the most popular research topics in last few years is the application of machine learning algorithms for mental states classification, decoding brain activation, and finding the variable of interest from fMRI data. In classification scenario, different algorithms have different biases, in the sequel performances differs across datasets, and for a particular dataset the accuracy varies from classifier to classifier. To overcome the limitations of individual techniques, hybridization or fusion of these machine learning techniques emerged in recent years which have shown promising result and open up new direction of research. This paper reviews the machine learning techniques ranging from individual classifiers, ensemble, and hybrid techniques used in cognitive classification with a well balance treatment of their applications, performance, and limitations. It also discusses many open research challenges for further research.

A multiple kernel learning approach to perform classification of groups from complex-valued fMRI data analysis: application to schizophrenia

FMRI data are acquired as complex-valued spatiotemporal images. Despite the fact that several studies have identified the presence of novel information in the phase images, they are usually discarded due to their noisy nature. Several approaches have been devised to incorporate magnitude and phase data, but none of them has performed between-group inference or classification. Multiple kernel learning (MKL) is a powerful field of machine learning that finds an automatic combination of kernel functions that can be applied to multiple data sources. By analyzing this combination of kernels, the most informative data sources can be found, hence providing a better understanding of the analyzed learning task. This paper presents a methodology based on a new MKL algorithm (ν-MKL) capable of achieving a tunable sparse selection of features' sets (brain regions' patterns) that improves the classification accuracy rate of healthy controls and schizophrenia patients by 5% when phase data is included. In addition, the proposed method achieves accuracy rates that are equivalent to those obtained by the state of the art lp-norm MKL algorithm on the schizophrenia dataset and we argue that it better identifies the brain regions that show discriminative activation between groups. This claim is supported by the more accurate detection achieved by ν-MKL of the degree of information present on regions of spatial maps extracted from a simulated fMRI dataset. In summary, we present an MKL-based methodology that improves schizophrenia characterization by using both magnitude and phase fMRI data and is also capable of detecting the brain regions that convey most of the discriminative information between patients and controls.

Bayesian network models in brain functional connectivity analysis

Much effort has been made to better understand the complex integration of distinct parts of the human brain using functional magnetic resonance imaging (fMRI). Altered functional connectivity between brain regions is associated with many neurological and mental illnesses, such as Alzheimer and Parkinson diseases, addiction, and depression. In computational science, Bayesian networks (BN) have been used in a broad range of studies to model complex data set in the presence of uncertainty and when expert prior knowledge is needed. However, little is done to explore the use of BN in connectivity analysis of fMRI data. In this paper, we present an up-to-date literature review and methodological details of connectivity analyses using BN, while highlighting caveats in a real-world application. We present a BN model of fMRI dataset obtained from sixty healthy subjects performing the stop-signal task (SST), a paradigm widely used to investigate response inhibition. Connectivity results are validated with the extant literature including our previous studies. By exploring the link strength of the learned BN's and correlating them to behavioral performance measures, this novel use of BN in connectivity analysis provides new insights to the functional neural pathways underlying response inhibition.

High-order interactions observed in multi-task intrinsic networks are dominant indicators of aberrant brain function in schizophrenia

Identifying the complex activity relationships present in rich, modern neuroimaging data sets remains a key challenge for neuroscience. The problem is hard because (a) the underlying spatial and temporal networks may be nonlinear and multivariate and (b) the observed data may be driven by numerous latent factors. Further, modern experiments often produce data sets containing multiple stimulus contexts or tasks processed by the same subjects. Fusing such multi-session data sets may reveal additional structure, but raises further statistical challenges. We present a novel analysis method for extracting complex activity networks from such multifaceted imaging data sets. Compared to previous methods, we choose a new point in the trade-off space, sacrificing detailed generative probability models and explicit latent variable inference in order to achieve robust estimation of multivariate, nonlinear group factors ("network clusters"). We apply our method to identify relationships of task-specific intrinsic networks in schizophrenia patients and control subjects from a large fMRI study. After identifying network-clusters characterized by within- and between-task interactions, we find significant differences between patient and control groups in interaction strength among networks. Our results are consistent with known findings of brain regions exhibiting deviations in schizophrenic patients. However, we also find high-order, nonlinear interactions that discriminate groups but that are not detected by linear, pairwise methods. We additionally identify high-order relationships that provide new insights into schizophrenia but that have not been found by traditional univariate or second-order methods. Overall, our approach can identify key relationships that are missed by existing analysis methods, without losing the ability to find relationships that are known to be important.

Graph theoretical analysis of resting magnetoencephalographic functional connectivity networks

Complex networks have been observed to comprise small-world properties, believed to represent an optimal organization of local specialization and global integration of information processing at reduced wiring cost. Here, we applied magnitude squared coherence to resting magnetoencephalographic time series in reconstructed source space, acquired from controls and patients with schizophrenia, and generated frequency-dependent adjacency matrices modeling functional connectivity between virtual channels. After configuring undirected binary and weighted graphs, we found that all human networks demonstrated highly localized clustering and short characteristic path lengths. The most conservatively thresholded networks showed efficient wiring, with topographical distance between connected vertices amounting to one-third as observed in surrogate randomized topologies. Nodal degrees of the human networks conformed to a heavy-tailed exponentially truncated power-law, compatible with the existence of hubs, which included theta and alpha bilateral cerebellar tonsil, beta and gamma bilateral posterior cingulate, and bilateral thalamus across all frequencies. We conclude that all networks showed small-worldness, minimal physical connection distance, and skewed degree distributions characteristic of physically-embedded networks, and that these calculations derived from graph theoretical mathematics did not quantifiably distinguish between subject populations, independent of bandwidth. However, post-hoc measurements of edge computations at the scale of the individual vertex revealed trends of reduced gamma connectivity across the posterior medial parietal cortex in patients, an observation consistent with our prior resting activation study that found significant reduction of synthetic aperture magnetometry gamma power across similar regions. The basis of these small differences remains unclear.

Cognitive and neuroplasticity mechanisms by which congenital or early blindness may confer a protective effect against schizophrenia

Several authors have noted that there are no reported cases of people with schizophrenia who were born blind or who developed blindness shortly after birth, suggesting that congenital or early (C/E) blindness may serve as a protective factor against schizophrenia. By what mechanisms might this effect operate? Here, we hypothesize that C/E blindness offers protection by strengthening cognitive functions whose impairment characterizes schizophrenia, and by constraining cognitive processes that exhibit excessive flexibility in schizophrenia. After briefly summarizing evidence that schizophrenia is fundamentally a cognitive disorder, we review areas of perceptual and cognitive function that are both impaired in the illness and augmented in C/E blindness, as compared to healthy sighted individuals. We next discuss: (1) the role of neuroplasticity in driving these cognitive changes in C/E blindness; (2) evidence that C/E blindness does not confer protective effects against other mental disorders; and (3) evidence that other forms of C/E sensory loss (e.g., deafness) do not reduce the risk of schizophrenia. We conclude by discussing implications of these data for designing cognitive training interventions to reduce schizophrenia-related cognitive impairment, and perhaps to reduce the likelihood of the development of the disorder itself.

Machine learning and radiology

In this paper, we give a short introduction to machine learning and survey its applications in radiology. We focused on six categories of applications in radiology: medical image segmentation, registration, computer aided detection and diagnosis, brain function or activity analysis and neurological disease diagnosis from fMR images, content-based image retrieval systems for CT or MRI images, and text analysis of radiology reports using natural language processing (NLP) and natural language understanding (NLU). This survey shows that machine learning plays a key role in many radiology applications. Machine learning identifies complex patterns automatically and helps radiologists make intelligent decisions on radiology data such as conventional radiographs, CT, MRI, and PET images and radiology reports. In many applications, the performance of machine learning-based automatic detection and diagnosis systems has shown to be comparable to that of a well-trained and experienced radiologist. Technology development in machine learning and radiology will benefit from each other in the long run. Key contributions and common characteristics of machine learning techniques in radiology are discussed. We also discuss the problem of translating machine learning applications to the radiology clinical setting, including advantages and potential barriers.

Characterization of groups using composite kernels and multi-source fMRI analysis data: application to schizophrenia

Pattern classification of brain imaging data can enable the automatic detection of differences in cognitive processes of specific groups of interest. Furthermore, it can also give neuroanatomical information related to the regions of the brain that are most relevant to detect these differences by means of feature selection procedures, which are also well-suited to deal with the high dimensionality of brain imaging data. This work proposes the application of recursive feature elimination using a machine learning algorithm based on composite kernels to the classification of healthy controls and patients with schizophrenia. This framework, which evaluates nonlinear relationships between voxels, analyzes whole-brain fMRI data from an auditory task experiment that is segmented into anatomical regions and recursively eliminates the uninformative ones based on their relevance estimates, thus yielding the set of most discriminative brain areas for group classification. The collected data was processed using two analysis methods: the general linear model (GLM) and independent component analysis (ICA). GLM spatial maps as well as ICA temporal lobe and default mode component maps were then input to the classifier. A mean classification accuracy of up to 95% estimated with a leave-two-out cross-validation procedure was achieved by doing multi-source data classification. In addition, it is shown that the classification accuracy rate obtained by using multi-source data surpasses that reached by using single-source data, hence showing that this algorithm takes advantage of the complimentary nature of GLM and ICA.

Large-scale directional connections among multi resting-state neural networks in human brain: a functional MRI and Bayesian network modeling study

This study examined the large-scale connectivity among multiple resting-state networks (RSNs) in the human brain. Independent component analysis was first applied to the resting-state functional MRI (fMRI) data acquired from 12 healthy young subjects for the separation of RSNs. Four sensory (lateral and medial visual, auditory, and sensory-motor) RSNs and four cognitive (default-mode, self-referential, dorsal and ventral attention) RSNs were identified. Gaussian Bayesian network (BN) learning approach was then used for the examination of the conditional dependencies among these RSNs and the construction of the network-to-network directional connectivity patterns. The BN based results demonstrated that sensory networks and cognitive networks were hierarchically organized. Specially, we found the sensory networks were highly intra-dependent and the cognitive networks were strongly intra-influenced. In addition, the results depicted dominant bottom-up connectivity from sensory networks to cognitive networks in which the self-referential and the default-mode networks might play respectively important roles in the process of resting-state information transfer and integration. The present study characterized the global connectivity relations among RSNs and delineated more characteristics of spontaneous activity dynamics.

Effective connectivity analysis of fMRI and MEG data collected under identical paradigms

Estimation of effective connectivity, a measure of the influence among brain regions, can potentially reveal valuable information about organization of brain networks. Effective connectivity is usually evaluated from the functional data of a single modality. In this paper we show why that may lead to incorrect conclusions about effective connectivity. In this paper we use Bayesian networks to estimate connectivity on two different modalities. We analyze structures of estimated effective connectivity networks using aggregate statistics from the field of complex networks. Our study is conducted on functional MRI and magnetoencephalography data collected from the same subjects under identical paradigms. Results showed some similarities but also revealed some striking differences in the conclusions one would make on the fMRI data compared with the MEG data and are strongly supportive of the use of multiple modalities in order to gain a more complete picture of how the brain is organized given the limited information one modality is able to provide.

Are posterior default-mode networks more robust than anterior default-mode networks? Evidence from resting-state fMRI data analysis

Intrinsic brain activity known as default-mode networks (DMNs) has been observed predominantly within the medial/superior frontal areas, anterior/posterior cingulate gyri, and precuneus using blood-oxygenation-level-dependent (BOLD) functional MRI (fMRI). Despite anecdotal evidence of distinct spatial patterns reflecting neuropsychiatric conditions in these DMNs, rigorous analysis of the characteristic traits of DMNs has been limited in previous studies. In this letter, the reproducibility and potential variability of the anterior and posterior DMNs were evaluated based on individual-level variations in effect sizes, activated areas, and causal interactions. Our results indicated that the DMNs were indeed reproducible between sessions/subjects. Region-specific traits were also observed: the posterior DMN seemed more robust to individual-level variations than the anterior DMN. The proposed analytical methods and reported findings may be useful in the development of a wide range of applications, including those involving clinical populations, which utilize the characteristic traits of DMNs.

Altered default mode network connectivity in Alzheimer's disease--a resting functional MRI and Bayesian network study

A number of functional magnetic resonance imaging (fMRI) studies reported the existence of default mode network (DMN) and its disruption due to the presence of a disease such as Alzheimer's disease (AD). In this investigation, first, we used the independent component analysis (ICA) technique to confirm the DMN difference between patients with AD and normal control (NC) reported in previous studies. Consistent with the previous studies, the decreased resting-state functional connectivity of DMN in AD was identified in posterior cingulated cortex (PCC), medial prefrontal cortex (MPFC), inferior parietal cortex (IPC), inferior temporal cortex (ITC), and hippocampus (HC). Moreover, we introduced Bayesian network (BN) to study the effective connectivity of DMN and the difference between AD and NC. When compared the DMN effective connectivity in AD with the one in NC using a nonparametric random permutation test, we found that connections from left HC to left IPC, left ITC to right HC, right HC to left IPC, to MPFC and to PCC were all lost. In addition, in AD group, the connection directions between right HC and left HC, between left HC and left ITC, and between right IPC and right ITC were opposite to those in NC group. The connections of right HC to other regions, except left HC, within the BN were all statistically in-distinguishable from 0, suggesting an increased right hippocampal pathological and functional burden in AD. The altered effective connectivity in patients with AD may reveal more characteristics of the disease and may serve as a potential biomarker.

Impaired cerebellar functional connectivity in schizophrenia patients and their healthy siblings

The long-standing notion of schizophrenia as a disorder of connectivity is supported by emerging evidence from recent neuroimaging studies, suggesting impairments of both structural and functional connectivity in schizophrenia. However, investigations are generally restricted to supratentorial brain regions, thereby excluding the cerebellum. As increasing evidence suggests that the cerebellum contributes to cognitive and affective processing, aberrant connectivity in schizophrenia may include cerebellar dysconnectivity. Moreover, as schizophrenia is highly heritable, unaffected family members of schizophrenia patients may exhibit similar connectivity profiles. The present study applies resting-state functional magnetic resonance imaging to determine cerebellar functional connectivity profiles, and the familial component of cerebellar connectivity profiles, in 62 schizophrenia patients and 67 siblings of schizophrenia patients. Compared to healthy control subjects, schizophrenia patients showed impaired functional connectivity between the cerebellum and several left-sided cerebral regions, including the hippocampus, thalamus, middle cingulate gyrus, triangular part of the inferior frontal gyrus, supplementary motor area, and lingual gyrus (all p < 0.0025, whole-brain significant). Importantly, siblings of schizophrenia patients showed several similarities to patients in cerebellar functional connectivity, suggesting that cerebellar dysconnectivity in schizophrenia might be related to familial factors. In conclusion, our findings suggest that dysconnectivity in schizophrenia involves the cerebellum and that this defect may be related to the risk to develop the illness.

Dynamic causal modelling of effective connectivity from fMRI: are results reproducible and sensitive to Parkinson's disease and its treatment?

Dynamic causal modelling (DCM) of functional magnetic resonance imaging (fMRI) data offers new insights into the pathophysiology of neurological disease and mechanisms of effective therapies. Current applications can be used both to identify the most likely functional brain network underlying observed data and estimate the networks' connectivity parameters. We examined the reproducibility of DCM in healthy subjects (young 18–48 years, n = 27; old 50–80 years, n = 15) in the context of action selection. We then examined the effects of Parkinson's disease (50–78 years, Hoehn and Yahr stage 1–2.5, n = 16) and dopaminergic therapy. Forty-eight models were compared, for each of 90 sessions from 58 subjects. Model-evidences clustered according to sets of structurally similar models, with high correlations over two sessions in healthy older subjects. The same model was identified as most likely in healthy controls on both sessions and in medicated patients. In this most likely network model, the selection of action was associated with enhanced coupling between prefrontal cortex and the pre-supplementary motor area. However, the parameters for intrinsic connectivity and contextual modulation in this model were poorly correlated across sessions. A different model was identified in patients with Parkinson's disease after medication withdrawal. In “off” patients, action selection was associated with enhanced connectivity from prefrontal to lateral premotor cortex. This accords with independent evidence of a dopamine-dependent functional disconnection of the SMA in Parkinson's disease. Together, these results suggest that DCM model selection is robust and sensitive enough to study clinical populations and their pharmacological treatment. For critical inferences, model selection may be sufficient. However, caution is required when comparing groups or drug effects in terms of the connectivity parameter estimates, if there are significant posterior covariances among parameters.

Neuroscientific psychiatric diagnosis

The DSM is not brain-related and is thus unable to relate clinical assessments to putative brain disturbances. 'Clinical brain profiling' (CBP) involves the rearrangement of clinical findings to assess the relevant disturbances in brain dynamics. CBP has three major pathological dimensions, (1) disorders of basic brain organization and development (2) disorders of connectivity dynamics and balance and (3) disorders of plasticity dynamics and neural resilience. CBP is a useful platform for the development of a brain-related neuroscientific diagnosis for psychiatry. Once the underlying pathology of a mental disorder is known an effective intervention can be designed to cure the disorder.

Auditory oddball deficits in schizophrenia: an independent component analysis of the fMRI multisite function BIRN study

Deficits in the connectivity between brain regions have been suggested to play a major role in the pathophysiology of schizophrenia. A functional magnetic resonance imaging (fMRI) analysis of schizophrenia was implemented using independent component analysis (ICA) to identify multiple temporally cohesive, spatially distributed regions of brain activity that represent functionally connected networks. We hypothesized that functional connectivity differences would be seen in auditory networks comprised of regions such as superior temporal gyrus as well as executive networks that consisted of frontal-parietal areas. Eight networks were found to be implicated in schizophrenia during the auditory oddball paradigm. These included a bilateral temporal network containing the superior and middle temporal gyrus; a default-mode network comprised of the posterior cingulate, precuneus, and middle frontal gyrus; and multiple dorsal lateral prefrontal cortex networks that constituted various levels of between-group differences. Highly task-related sensory networks were also found. These results indicate that patients with schizophrenia show functional connectivity differences in networks related to auditory processing, executive control, and baseline functional activity. Overall, these findings support the idea that the cognitive deficits associated with schizophrenia are widespread and that a functional connectivity approach can help elucidate the neural correlates of this disorder.